{
  "metrics": [
    {
      "name": "num_perplexity_tokens",
      "display_name": "# tokens",
      "description": "Average number of tokens in the predicted output (for language modeling, the input too)."
    },
    {
      "name": "num_bytes",
      "display_name": "# bytes",
      "description": "Average number of bytes in the predicted output (for language modeling, the input too)."
    },
    {
      "name": "num_references",
      "display_name": "# ref",
      "description": "Number of references."
    },
    {
      "name": "num_train_trials",
      "display_name": "# trials",
      "description": "Number of trials, where in each trial we choose an independent, random set of training instances."
    },
    {
      "name": "estimated_num_tokens_cost",
      "display_name": "cost",
      "description": "An estimate of the number of tokens (including prompt and output completions) needed to perform the request."
    },
    {
      "name": "num_prompt_tokens",
      "display_name": "# prompt tokens",
      "description": "Number of tokens in the prompt."
    },
    {
      "name": "num_prompt_characters",
      "display_name": "# prompt chars",
      "description": "Number of characters in the prompt."
    },
    {
      "name": "num_completion_tokens",
      "display_name": "# completion tokens",
      "description": "Actual number of completion tokens (over all completions)."
    },
    {
      "name": "num_output_tokens",
      "display_name": "# output tokens",
      "description": "Actual number of output tokens."
    },
    {
      "name": "max_num_output_tokens",
      "display_name": "Max output tokens",
      "description": "Maximum number of output tokens (overestimate since we might stop earlier due to stop sequences)."
    },
    {
      "name": "num_requests",
      "display_name": "# requests",
      "description": "Number of distinct API requests."
    },
    {
      "name": "num_instances",
      "display_name": "# eval",
      "description": "Number of evaluation instances."
    },
    {
      "name": "num_train_instances",
      "display_name": "# train",
      "description": "Number of training instances (e.g., in-context examples)."
    },
    {
      "name": "prompt_truncated",
      "display_name": "truncated",
      "description": "Fraction of instances where the prompt itself was truncated (implies that there were no in-context examples)."
    },
    {
      "name": "finish_reason_length",
      "display_name": "finish b/c length",
      "description": "Fraction of instances where the the output was terminated because of the max tokens limit."
    },
    {
      "name": "finish_reason_stop",
      "display_name": "finish b/c stop",
      "description": "Fraction of instances where the the output was terminated because of the stop sequences."
    },
    {
      "name": "finish_reason_endoftext",
      "display_name": "finish b/c endoftext",
      "description": "Fraction of instances where the the output was terminated because the end of text token was generated."
    },
    {
      "name": "finish_reason_unknown",
      "display_name": "finish b/c unknown",
      "description": "Fraction of instances where the the output was terminated for unknown reasons."
    },
    {
      "name": "num_completions",
      "display_name": "# completions",
      "description": "Number of completions."
    },
    {
      "name": "predicted_index",
      "display_name": "Predicted index",
      "description": "Integer index of the reference (0, 1, ...) that was predicted by the model (for multiple-choice)."
    },
    {
      "name": "inference_runtime",
      "display_name": "Observed inference runtime (s)",
      "short_display_name": "Observed inference time (s)",
      "description": "Average observed time to process a request to the model (via an API, and thus depends on particular deployment).",
      "lower_is_better": true
    },
    {
      "name": "exact_match",
      "display_name": "Exact match",
      "short_display_name": "EM",
      "description": "Fraction of instances that the predicted output matches a correct reference exactly.",
      "lower_is_better": false
    },
    {
      "name": "quasi_exact_match",
      "display_name": "Quasi-exact match",
      "short_display_name": "EM",
      "description": "Fraction of instances that the predicted output matches a correct reference up to light processing.",
      "lower_is_better": false
    },
    {
      "name": "prefix_exact_match",
      "display_name": "Prefix exact match",
      "short_display_name": "PEM",
      "description": "Fraction of instances that the predicted output matches the prefix of a correct reference exactly.",
      "lower_is_better": false
    },
    {
      "name": "quasi_prefix_exact_match",
      "display_name": "Prefix quasi-exact match",
      "short_display_name": "PEM",
      "description": "Fraction of instances that the predicted output matches the prefix of a correct reference up to light processing.",
      "lower_is_better": false
    },
    {
      "name": "ifeval_strict_accuracy",
      "display_name": "IFEval strict accuracy",
      "short_display_name": "IFEval Strict Acc",
      "description": "Fraction of instructions in the instance that are correctly followed.",
      "lower_is_better": false
    },
    {
      "name": "chain_of_thought_correctness",
      "display_name": "COT correct",
      "short_display_name": "COT correct",
      "description": "Fraction of correct answers after chain of thought",
      "lower_is_better": false
    },
    {
      "name": "wildbench_score",
      "display_name": "WildBench Score",
      "short_display_name": "WB Score",
      "description": "Score of the AI output judged by GPT-4o.",
      "lower_is_better": false
    },
    {
      "name": "wildbench_score_rescaled",
      "display_name": "WildBench Score",
      "short_display_name": "WB Score",
      "description": "Score of the AI output judged by GPT-4o, rescaled to be between 0 and 1.",
      "lower_is_better": false
    },
    {
      "name": "bigcodebench_p@1",
      "display_name": "BigCodeBench Pass@1",
      "short_display_name": "Pass@1",
      "description": "Accuracy of the AI output judged by BigCodeBench official evaluator.",
      "lower_is_better": false
    },
    {
      "name": "omni_math_accuracy",
      "display_name": "Omni-MATH Accuracy",
      "short_display_name": "Acc",
      "description": "Accuracy of the AI output judged by GPT-4.",
      "lower_is_better": false
    }
  ],
  "perturbations": [],
  "metric_groups": [
    {
      "name": "accuracy",
      "display_name": "Accuracy",
      "metrics": [
        {
          "name": "${main_name}",
          "split": "${main_split}"
        }
      ],
      "aggregation_strategies": [
        "mean"
      ]
    },
    {
      "name": "efficiency",
      "display_name": "Efficiency",
      "metrics": [
        {
          "name": "inference_runtime",
          "split": "${main_split}"
        }
      ],
      "aggregation_strategies": [
        "mean"
      ]
    },
    {
      "name": "general_information",
      "display_name": "General information",
      "metrics": [
        {
          "name": "num_instances",
          "split": "${main_split}"
        },
        {
          "name": "num_train_instances",
          "split": "${main_split}"
        },
        {
          "name": "prompt_truncated",
          "split": "${main_split}"
        },
        {
          "name": "num_prompt_tokens",
          "split": "${main_split}"
        },
        {
          "name": "num_output_tokens",
          "split": "${main_split}"
        }
      ],
      "hide_win_rates": true
    }
  ],
  "run_groups": [
    {
      "name": "core_scenarios",
      "display_name": "Core Scenarios",
      "description": "Core Scenarios",
      "metric_groups": [],
      "subgroups": [
        "mmlu_pro",
        "gpqa",
        "ifeval",
        "wildbench",
        "omni_math"
      ],
      "subgroup_display_mode": "by_metric",
      "subgroup_metric_groups_hidden": [],
      "environment": {},
      "category": "All scenarios",
      "visibility": "all_groups",
      "todo": false,
      "adapter_keys_shown": [
        "model_deployment",
        "model"
      ]
    },
    {
      "name": "mmlu_pro",
      "display_name": "MMLU-Pro",
      "description": "MMLU-Pro",
      "metric_groups": [
        "accuracy",
        "efficiency",
        "general_information"
      ],
      "subgroups": [],
      "subgroup_display_mode": "by_metric",
      "subgroup_metric_groups_hidden": [],
      "environment": {
        "main_name": "chain_of_thought_correctness",
        "main_split": "test"
      },
      "category": "Scenarios",
      "visibility": "all_groups",
      "taxonomy": {
        "task": "?",
        "what": "?",
        "when": "?",
        "who": "?",
        "language": "English"
      },
      "todo": false,
      "adapter_keys_shown": [
        "model_deployment",
        "model"
      ]
    },
    {
      "name": "gpqa",
      "display_name": "GPQA",
      "description": "GPQA",
      "metric_groups": [
        "accuracy",
        "efficiency",
        "general_information"
      ],
      "subgroups": [],
      "subgroup_display_mode": "by_metric",
      "subgroup_metric_groups_hidden": [],
      "environment": {
        "main_name": "chain_of_thought_correctness",
        "main_split": "test"
      },
      "category": "Scenarios",
      "visibility": "all_groups",
      "taxonomy": {
        "task": "question answering",
        "what": "graduate-level questions in biology, physics, and chemistry",
        "when": "2023",
        "who": "domain experts",
        "language": "English"
      },
      "todo": false,
      "adapter_keys_shown": [
        "model_deployment",
        "model"
      ]
    },
    {
      "name": "ifeval",
      "display_name": "IFEval",
      "description": "IFEval",
      "metric_groups": [
        "accuracy",
        "efficiency",
        "general_information"
      ],
      "subgroups": [],
      "subgroup_display_mode": "by_metric",
      "subgroup_metric_groups_hidden": [],
      "environment": {
        "main_name": "ifeval_strict_accuracy",
        "main_split": "test"
      },
      "category": "Scenarios",
      "visibility": "all_groups",
      "taxonomy": {
        "task": "instruction following",
        "what": "verifiable general domain instruction following",
        "when": "2023",
        "who": "human annotators",
        "language": "English"
      },
      "todo": false,
      "adapter_keys_shown": [
        "model_deployment",
        "model"
      ]
    },
    {
      "name": "wildbench",
      "display_name": "WildBench",
      "description": "WildBench",
      "metric_groups": [
        "accuracy",
        "efficiency",
        "general_information"
      ],
      "subgroups": [],
      "subgroup_display_mode": "by_metric",
      "subgroup_metric_groups_hidden": [],
      "environment": {
        "main_name": "wildbench_score_rescaled",
        "main_split": "test"
      },
      "category": "Scenarios",
      "visibility": "all_groups",
      "taxonomy": {
        "task": "instruction following",
        "what": "GPT-judged instruction following with instructions collected from real-user conversations",
        "when": "2024",
        "who": "real-world users",
        "language": "English"
      },
      "todo": false,
      "adapter_keys_shown": [
        "model_deployment",
        "model"
      ]
    },
    {
      "name": "omni_math",
      "display_name": "Omni-MATH",
      "description": "Omni-MATH",
      "metric_groups": [
        "accuracy",
        "efficiency",
        "general_information"
      ],
      "subgroups": [],
      "subgroup_display_mode": "by_metric",
      "subgroup_metric_groups_hidden": [],
      "environment": {
        "main_name": "omni_math_accuracy",
        "main_split": "test"
      },
      "category": "Scenarios",
      "visibility": "all_groups",
      "taxonomy": {
        "task": "mathematics",
        "what": "universal Olympiad level mathematic benchmark",
        "when": "2024",
        "who": "human annotators",
        "language": "English"
      },
      "todo": false,
      "adapter_keys_shown": [
        "model_deployment",
        "model"
      ]
    }
  ],
  "adapter": [
    {
      "name": "method",
      "description": "The high-level strategy for converting instances into a prompt for the language model."
    },
    {
      "name": "global_prefix",
      "description": "The string that is prepended to the entire prompt."
    },
    {
      "name": "global_suffix",
      "description": "The string that is appended to the entire prompt."
    },
    {
      "name": "instructions",
      "description": "The description of the task that is included at the very beginning of the prompt."
    },
    {
      "name": "input_prefix",
      "description": "The string that is included before each input (e.g., 'Question:')."
    },
    {
      "name": "input_suffix",
      "description": "The string that is included after each input (e.g., '\\n')."
    },
    {
      "name": "reference_prefix",
      "description": "The string that is included before each reference (for multiple-choice questions)."
    },
    {
      "name": "reference_prefix_characters",
      "description": "The characters that are used to identify choices for multiple-choice questions e.g. [\"A\", \"B\", \"C\", \"D\"]. If unset, defaults to the sequence of ascending characters starting from the first character of reference_prefix."
    },
    {
      "name": "reference_suffix",
      "description": "The string that is included after each reference (for multiple-choice questions)."
    },
    {
      "name": "chain_of_thought_prefix",
      "description": "The string that is included before each chain of thought. (e.g., 'Let's think step by step')"
    },
    {
      "name": "chain_of_thought_suffix",
      "description": "The string that is included after each chain of thought. (e.g., 'The correct answer is')"
    },
    {
      "name": "output_prefix",
      "description": "The string that is included before the correct answer/predicted output (e.g., 'Answer:')."
    },
    {
      "name": "output_suffix",
      "description": "The string that is included after the correct answer/predicted output (e.g., '\\n')."
    },
    {
      "name": "instance_prefix",
      "description": "The string that is included before each instance (e.g., '\\n\\n')."
    },
    {
      "name": "substitutions",
      "description": "A list of regular expression substitutions (e.g., replacing '\\n' with ';\\n') to perform at the very end on the prompt."
    },
    {
      "name": "max_train_instances",
      "description": "Maximum number of training instances to include in the prompt (currently by randomly sampling)."
    },
    {
      "name": "max_eval_instances",
      "description": "Maximum number of instances to evaluate on (over all splits - test, valid, etc.)."
    },
    {
      "name": "num_outputs",
      "description": "Maximum number of possible outputs to generate by sampling multiple outputs."
    },
    {
      "name": "num_train_trials",
      "description": "Number of trials, where in each trial we choose an independent, random set of training instances. Used to compute variance."
    },
    {
      "name": "num_trials",
      "description": "Number of trials, where we query the model with the same requests, but different random seeds."
    },
    {
      "name": "sample_train",
      "description": "If true, randomly sample N training examples; if false, select N consecutive training examples"
    },
    {
      "name": "model_deployment",
      "description": "Name of the language model deployment (<host_organization>/<model name>) to send requests to."
    },
    {
      "name": "model",
      "description": "Name of the language model (<creator_organization>/<model name>) to send requests to."
    },
    {
      "name": "temperature",
      "description": "Temperature parameter used in generation."
    },
    {
      "name": "max_tokens",
      "description": "Maximum number of tokens to generate."
    },
    {
      "name": "stop_sequences",
      "description": "List of stop sequences. Output generation will be stopped if any stop sequence is encountered."
    },
    {
      "name": "random",
      "description": "Random seed (string), which guarantees reproducibility."
    },
    {
      "name": "multi_label",
      "description": "If true, for instances with multiple correct reference, the gold answer should be considered to be all of the correct references rather than any of the correct references."
    },
    {
      "name": "image_generation_parameters",
      "description": "Parameters for image generation."
    },
    {
      "name": "reeval_parameters",
      "description": "Parameters for reeval evaluation."
    },
    {
      "name": "eval_splits",
      "description": "The splits from which evaluation instances will be drawn."
    },
    {
      "name": "output_mapping_pattern",
      "description": "Pattern to apply to the output before applying the output mapping for the joint multiple choice adapter. If the pattern has no group, the output mapping will be applied to the first match. If the pattern has a group, the output mapping will be applied to the group of the first match."
    }
  ],
  "models": [
    {
      "name": "amazon/nova-premier-v1:0",
      "display_name": "Amazon Nova Premier",
      "short_display_name": "Amazon Nova Premier",
      "description": "Amazon Nova Premier is a capable multimodal foundation model and teacher for model distillation that processes text, images, and videos with a one-million token context window. ([model card](https://www.amazon.science/publications/amazon-nova-premier-technical-report-and-model-card), [blog](https://aws.amazon.com/blogs/aws/amazon-nova-premier-our-most-capable-model-for-complex-tasks-and-teacher-for-model-distillation/))",
      "creator_organization": "Amazon",
      "access": "limited",
      "todo": false,
      "release_date": "2025-04-30"
    },
    {
      "name": "amazon/nova-pro-v1:0",
      "display_name": "Amazon Nova Pro",
      "short_display_name": "Amazon Nova Pro",
      "description": "Amazon Nova Pro is a highly capable multimodal model that balances of accuracy, speed, and cost for a wide range of tasks ([model card](https://www.amazon.science/publications/the-amazon-nova-family-of-models-technical-report-and-model-card))",
      "creator_organization": "Amazon",
      "access": "limited",
      "todo": false,
      "release_date": "2024-12-03"
    },
    {
      "name": "amazon/nova-lite-v1:0",
      "display_name": "Amazon Nova Lite",
      "short_display_name": "Amazon Nova Lite",
      "description": "Amazon Nova Lite is a low-cost multimodal model that is fast for processing images, video, documents and text. ([model card](https://www.amazon.science/publications/the-amazon-nova-family-of-models-technical-report-and-model-card))",
      "creator_organization": "Amazon",
      "access": "limited",
      "todo": false,
      "release_date": "2024-12-03"
    },
    {
      "name": "amazon/nova-micro-v1:0",
      "display_name": "Amazon Nova Micro",
      "short_display_name": "Amazon Nova Micro",
      "description": "Amazon Nova Micro is a text-only model that delivers low-latency responses at low cost. ([model card](https://www.amazon.science/publications/the-amazon-nova-family-of-models-technical-report-and-model-card))",
      "creator_organization": "Amazon",
      "access": "limited",
      "todo": false,
      "release_date": "2024-12-03"
    },
    {
      "name": "anthropic/claude-3-5-haiku-20241022",
      "display_name": "Claude 3.5 Haiku (20241022)",
      "short_display_name": "Claude 3.5 Haiku (20241022)",
      "description": "Claude 3.5 Haiku is a Claude 3 family model which matches the performance of Claude 3 Opus at a similar speed to the previous generation of Haiku ([blog](https://www.anthropic.com/news/3-5-models-and-computer-use)).",
      "creator_organization": "Anthropic",
      "access": "limited",
      "todo": false,
      "release_date": "2024-11-04"
    },
    {
      "name": "anthropic/claude-3-5-sonnet-20241022",
      "display_name": "Claude 3.5 Sonnet (20241022)",
      "short_display_name": "Claude 3.5 Sonnet (20241022)",
      "description": "Claude 3.5 Sonnet is a Claude 3 family model which outperforms Claude 3 Opus while operating faster and at a lower cost ([blog](https://www.anthropic.com/news/claude-3-5-sonnet)). This is an upgraded snapshot released on 2024-10-22 ([blog](https://www.anthropic.com/news/3-5-models-and-computer-use)).",
      "creator_organization": "Anthropic",
      "access": "limited",
      "todo": false,
      "release_date": "2024-10-22"
    },
    {
      "name": "anthropic/claude-3-7-sonnet-20250219",
      "display_name": "Claude 3.7 Sonnet (20250219)",
      "short_display_name": "Claude 3.7 Sonnet (20250219)",
      "description": "Claude 3.7 Sonnet is a Claude 3 family hybrid reasoning model that can produce near-instant responses or extended, step-by-step thinking that is made visible to the user ([blog](https://www.anthropic.com/news/claude-3-7-sonnet)).",
      "creator_organization": "Anthropic",
      "access": "limited",
      "todo": false,
      "release_date": "2025-02-24"
    },
    {
      "name": "anthropic/claude-sonnet-4-20250514",
      "display_name": "Claude 4 Sonnet (20250514)",
      "short_display_name": "Claude 4 Sonnet (20250514)",
      "description": "Claude 4 Sonnet is a hybrid model offering two modes - near-instant responses and extended thinking for deeper reasoning ([blog](https://www.anthropic.com/news/claude-4)).",
      "creator_organization": "Anthropic",
      "access": "limited",
      "todo": false,
      "release_date": "2025-05-14"
    },
    {
      "name": "anthropic/claude-sonnet-4-20250514-thinking-10k",
      "display_name": "Claude 4 Sonnet (20250514, extended thinking)",
      "short_display_name": "Claude 4 Sonnet (20250514, extended thinking)",
      "description": "Claude 4 Sonnet is a hybrid model offering two modes - near-instant responses and extended thinking for deeper reasoning ([blog](https://www.anthropic.com/news/claude-4)). Extended thinking is enabled with 10k budget tokens.",
      "creator_organization": "Anthropic",
      "access": "limited",
      "todo": false,
      "release_date": "2025-05-14"
    },
    {
      "name": "anthropic/claude-opus-4-20250514",
      "display_name": "Claude 4 Opus (20250514)",
      "short_display_name": "Claude 4 Opus (20250514)",
      "description": "Claude 4 Opus is a hybrid model offering two modes - near-instant responses and extended thinking for deeper reasoning ([blog](https://www.anthropic.com/news/claude-4)).",
      "creator_organization": "Anthropic",
      "access": "limited",
      "todo": false,
      "release_date": "2025-05-14"
    },
    {
      "name": "anthropic/claude-opus-4-20250514-thinking-10k",
      "display_name": "Claude 4 Opus (20250514, extended thinking)",
      "short_display_name": "Claude 4 Opus (20250514, extended thinking)",
      "description": "Claude 4 Opus is a hybrid model offering two modes - near-instant responses and extended thinking for deeper reasoning ([blog](https://www.anthropic.com/news/claude-4)). Extended thinking is enabled with 10k budget tokens.",
      "creator_organization": "Anthropic",
      "access": "limited",
      "todo": false,
      "release_date": "2025-05-14"
    },
    {
      "name": "anthropic/claude-sonnet-4-5-20250929",
      "display_name": "Claude 4.5 Sonnet (20250929)",
      "short_display_name": "Claude 4.5 Sonnet (20250929)",
      "description": "Claude 4.5 Sonnet is a model from Anthropic that shows particular strengths in software coding, in agentic tasks where it runs in a loop and uses tools, and in using computers. ([blog](https://www.anthropic.com/news/claude-sonnet-4-5), [system card](https://assets.anthropic.com/m/12f214efcc2f457a/original/Claude-Sonnet-4-5-System-Card.pdf))",
      "creator_organization": "Anthropic",
      "access": "limited",
      "todo": false,
      "release_date": "2025-09-29"
    },
    {
      "name": "anthropic/claude-haiku-4-5-20251001",
      "display_name": "Claude 4.5 Haiku (20251001)",
      "short_display_name": "Claude 4.5 Haiku (20251001)",
      "description": "Claude 4.5 Haiku is a hybrid model from Anthropic in their small, fast model class that is particularly effective at coding tasks and computer use. ([blog](https://www.anthropic.com/news/claude-haiku-4-5), [system card](https://assets.anthropic.com/m/99128ddd009bdcb/Claude-Haiku-4-5-System-Card.pdf))",
      "creator_organization": "Anthropic",
      "access": "limited",
      "todo": false,
      "release_date": "2025-10-15"
    },
    {
      "name": "deepseek-ai/deepseek-v3",
      "display_name": "DeepSeek v3",
      "short_display_name": "DeepSeek v3",
      "description": "DeepSeek v3 a Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. It adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures. ([paper](https://github.com/deepseek-ai/DeepSeek-V3/blob/main/DeepSeek_V3.pdf))",
      "creator_organization": "DeepSeek",
      "access": "open",
      "todo": false,
      "release_date": "2024-12-24",
      "num_parameters": 685000000000
    },
    {
      "name": "deepseek-ai/deepseek-r1-0528",
      "display_name": "DeepSeek-R1-0528",
      "short_display_name": "DeepSeek-R1-0528",
      "description": "DeepSeek-R1-0528 is a minor version upgrade from DeepSeek R1 that has improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. ([paper](https://arxiv.org/abs/2501.12948))",
      "creator_organization": "DeepSeek",
      "access": "open",
      "todo": false,
      "release_date": "2025-05-28",
      "num_parameters": 685000000000
    },
    {
      "name": "google/gemini-1.5-pro-002",
      "display_name": "Gemini 1.5 Pro (002)",
      "short_display_name": "Gemini 1.5 Pro (002)",
      "description": "Gemini 1.5 Pro is a multimodal mixture-of-experts model capable of recalling and reasoning over fine-grained information from long contexts. This model is accessed through Vertex AI and has all safety thresholds set to `BLOCK_NONE`. ([paper](https://arxiv.org/abs/2403.05530))",
      "creator_organization": "Google",
      "access": "limited",
      "todo": false,
      "release_date": "2024-09-24"
    },
    {
      "name": "google/gemini-1.5-flash-002",
      "display_name": "Gemini 1.5 Flash (002)",
      "short_display_name": "Gemini 1.5 Flash (002)",
      "description": "Gemini 1.5 Flash is a multimodal mixture-of-experts model capable of recalling and reasoning over fine-grained information from long contexts. This model is accessed through Vertex AI and has all safety thresholds set to `BLOCK_NONE`. ([paper](https://arxiv.org/abs/2403.05530))",
      "creator_organization": "Google",
      "access": "limited",
      "todo": false,
      "release_date": "2024-09-24"
    },
    {
      "name": "google/gemini-2.0-flash-001",
      "display_name": "Gemini 2.0 Flash",
      "short_display_name": "Gemini 2.0 Flash",
      "description": "Gemini 2.0 Flash is a member of the Gemini 2.0 series of models, a suite of highly-capable, natively multimodal models designed to power agentic systems. ([model card](https://storage.googleapis.com/model-cards/documents/gemini-2-flash.pdf), [documentation](https://ai.google.dev/gemini-api/docs/models/gemini))",
      "creator_organization": "Google",
      "access": "limited",
      "todo": false,
      "release_date": "2025-02-01"
    },
    {
      "name": "google/gemini-2.0-flash-lite-preview-02-05",
      "display_name": "Gemini 2.0 Flash Lite (02-05 preview)",
      "short_display_name": "Gemini 2.0 Flash Lite (02-05 preview)",
      "description": "Gemini 2.0 Flash Lite (02-05 preview) ([model card](https://storage.googleapis.com/model-cards/documents/gemini-2-flash.pdf), [documentation](https://ai.google.dev/gemini-api/docs/models/gemini))",
      "creator_organization": "Google",
      "access": "limited",
      "todo": false,
      "release_date": "2025-02-05"
    },
    {
      "name": "google/gemini-2.5-flash-lite",
      "display_name": "Gemini 2.5 Flash-Lite",
      "short_display_name": "Gemini 2.5 Flash-Lite",
      "description": "Gemini 2.5 Flash-Lite ([blog](https://blog.google/products/gemini/gemini-2-5-model-family-expands/))",
      "creator_organization": "Google",
      "access": "limited",
      "todo": false,
      "release_date": "2025-07-22"
    },
    {
      "name": "google/gemini-2.5-flash-preview-04-17",
      "display_name": "Gemini 2.5 Flash (04-17 preview)",
      "short_display_name": "Gemini 2.5 Flash (04-17 preview)",
      "description": "Gemini 2.5 Flash (04-17 preview) ([documentation](https://ai.google.dev/gemini-api/docs/models/gemini))",
      "creator_organization": "Google",
      "access": "limited",
      "todo": false,
      "release_date": "2025-04-17"
    },
    {
      "name": "google/gemini-2.5-pro-preview-03-25",
      "display_name": "Gemini 2.5 Pro (03-25 preview)",
      "short_display_name": "Gemini 2.5 Pro (03-25 preview)",
      "description": "Gemini 2.5 Pro (03-25 preview) ([documentation](https://ai.google.dev/gemini-api/docs/models/gemini))",
      "creator_organization": "Google",
      "access": "limited",
      "todo": false,
      "release_date": "2025-04-09"
    },
    {
      "name": "google/gemini-3-pro-preview",
      "display_name": "Gemini 3 Pro (Preview)",
      "short_display_name": "Gemini 3 Pro (Preview)",
      "description": "Gemini 3.0 models are thinking models, capable of reasoning through their thoughts before responding, resulting in enhanced performance and improved accuracy. ([blog](https://blog.google/products/gemini/gemini-3/), [blog](https://blog.google/technology/developers/gemini-3-developers/))",
      "creator_organization": "Google",
      "access": "limited",
      "todo": false,
      "release_date": "2025-11-18"
    },
    {
      "name": "marin-community/marin-8b-instruct",
      "display_name": "Marin 8B Instruct",
      "short_display_name": "Marin 8B Instruct",
      "description": "Marin 8B Instruct is an open-source chatbot trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT.",
      "creator_organization": "Marin Community",
      "access": "open",
      "todo": false,
      "release_date": "2025-05-15",
      "num_parameters": 8030000000
    },
    {
      "name": "meta/llama-3.1-8b-instruct-turbo",
      "display_name": "Llama 3.1 Instruct Turbo (8B)",
      "short_display_name": "Llama 3.1 Instruct Turbo (8B)",
      "description": "Llama 3.1 (8B) is part of the Llama 3 family of dense Transformer models that that natively support multilinguality, coding, reasoning, and tool usage. ([paper](https://ai.meta.com/research/publications/the-llama-3-herd-of-models/), [blog](https://ai.meta.com/blog/meta-llama-3-1/)) Turbo is Together's implementation, providing a near negligible difference in quality from the reference implementation with faster performance and lower cost, currently using FP8 quantization. ([blog](https://www.together.ai/blog/llama-31-quality))",
      "creator_organization": "Meta",
      "access": "open",
      "todo": false,
      "release_date": "2024-07-23",
      "num_parameters": 8000000000
    },
    {
      "name": "meta/llama-3.1-70b-instruct-turbo",
      "display_name": "Llama 3.1 Instruct Turbo (70B)",
      "short_display_name": "Llama 3.1 Instruct Turbo (70B)",
      "description": "Llama 3.1 (70B) is part of the Llama 3 family of dense Transformer models that that natively support multilinguality, coding, reasoning, and tool usage. ([paper](https://ai.meta.com/research/publications/the-llama-3-herd-of-models/), [blog](https://ai.meta.com/blog/meta-llama-3-1/)) Turbo is Together's implementation, providing a near negligible difference in quality from the reference implementation with faster performance and lower cost, currently using FP8 quantization. ([blog](https://www.together.ai/blog/llama-31-quality))",
      "creator_organization": "Meta",
      "access": "open",
      "todo": false,
      "release_date": "2024-07-23",
      "num_parameters": 70000000000
    },
    {
      "name": "meta/llama-3.1-405b-instruct-turbo",
      "display_name": "Llama 3.1 Instruct Turbo (405B)",
      "short_display_name": "Llama 3.1 Instruct Turbo (405B)",
      "description": "Llama 3.1 (405B) is part of the Llama 3 family of dense Transformer models that that natively support multilinguality, coding, reasoning, and tool usage. ([paper](https://ai.meta.com/research/publications/the-llama-3-herd-of-models/), [blog](https://ai.meta.com/blog/meta-llama-3-1/)) Turbo is Together's implementation, providing a near negligible difference in quality from the reference implementation with faster performance and lower cost, currently using FP8 quantization. ([blog](https://www.together.ai/blog/llama-31-quality))",
      "creator_organization": "Meta",
      "access": "open",
      "todo": false,
      "release_date": "2024-07-23",
      "num_parameters": 405000000000
    },
    {
      "name": "meta/llama-4-scout-17b-16e-instruct",
      "display_name": "Llama 4 Scout (17Bx16E) Instruct",
      "short_display_name": "Llama 4 Scout (17Bx16E) Instruct",
      "description": "Llama 4 Scout (17Bx16E) Instruct is part of the Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences using a mixture-of-experts architecture. ([blog](https://ai.meta.com/blog/llama-4-multimodal-intelligence/))",
      "creator_organization": "Meta",
      "access": "open",
      "todo": false,
      "release_date": "2025-04-05",
      "num_parameters": 109000000000
    },
    {
      "name": "meta/llama-4-maverick-17b-128e-instruct-fp8",
      "display_name": "Llama 4 Maverick (17Bx128E) Instruct FP8",
      "short_display_name": "Llama 4 Maverick (17Bx128E) Instruct FP8",
      "description": "Llama 4 Maverick (17Bx128E) Instruct FP8 is part of the Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences using a mixture-of-experts architecture. ([blog](https://ai.meta.com/blog/llama-4-multimodal-intelligence/))",
      "creator_organization": "Meta",
      "access": "open",
      "todo": false,
      "release_date": "2025-04-05",
      "num_parameters": 402000000000
    },
    {
      "name": "allenai/olmo-2-1124-7b-instruct",
      "display_name": "OLMo 2 7B Instruct November 2024",
      "short_display_name": "OLMo 2 7B Instruct November 2024",
      "description": "OLMo 2 is a family of 7B and 13B models trained on up to 5T tokens. ([blog](https://allenai.org/blog/olmo2))",
      "creator_organization": "Allen Institute for AI",
      "access": "open",
      "todo": false,
      "release_date": "2024-11-26",
      "num_parameters": 7300000000
    },
    {
      "name": "allenai/olmo-2-1124-13b-instruct",
      "display_name": "OLMo 2 13B Instruct November 2024",
      "short_display_name": "OLMo 2 13B Instruct November 2024",
      "description": "OLMo 2 is a family of 7B and 13B models trained on up to 5T tokens. ([blog](https://allenai.org/blog/olmo2))",
      "creator_organization": "Allen Institute for AI",
      "access": "open",
      "todo": false,
      "release_date": "2024-11-26",
      "num_parameters": 13700000000
    },
    {
      "name": "allenai/olmo-2-0325-32b-instruct",
      "display_name": "OLMo 2 32B Instruct March 2025",
      "short_display_name": "OLMo 2 32B Instruct March 2025",
      "description": "OLMo 2 32B Instruct March 2025 is trained up to 6T tokens and post-trained using Tulu 3.1. ([blog](https://allenai.org/blog/olmo2-32B))",
      "creator_organization": "Allen Institute for AI",
      "access": "open",
      "todo": false,
      "release_date": "2025-03-13",
      "num_parameters": 32200000000
    },
    {
      "name": "allenai/olmoe-1b-7b-0125-instruct",
      "display_name": "OLMoE 1B-7B Instruct January 2025",
      "short_display_name": "OLMoE 1B-7B Instruct January 2025",
      "description": "OLMoE 1B-7B Instruct January 2025 is a fully open language model leveraging sparse Mixture-of-Experts (MoE). It has 7B parameters but uses only 1B per input token. It was pretrained on 5T tokens. ([blog](https://allenai.org/blog/olmoe-an-open-small-and-state-of-the-art-mixture-of-experts-model-c258432d0514), [paper](https://arxiv.org/abs/2409.02060))",
      "creator_organization": "Allen Institute for AI",
      "access": "open",
      "todo": false,
      "release_date": "2025-03-13",
      "num_parameters": 32200000000
    },
    {
      "name": "mistralai/mistral-7b-instruct-v0.3",
      "display_name": "Mistral Instruct v0.3 (7B)",
      "short_display_name": "Mistral Instruct v0.3 (7B)",
      "description": "Mistral v0.3 Instruct 7B is a 7.3B parameter transformer model that uses Grouped-Query Attention (GQA). Compared to v0.1, v0.2 has a 32k context window and no Sliding-Window Attention (SWA). ([blog post](https://mistral.ai/news/la-plateforme/))",
      "creator_organization": "Mistral AI",
      "access": "open",
      "todo": false,
      "release_date": "2024-05-22",
      "num_parameters": 7300000000
    },
    {
      "name": "mistralai/mixtral-8x7b-instruct-v0.1",
      "display_name": "Mixtral Instruct (8x7B)",
      "short_display_name": "Mixtral Instruct (8x7B)",
      "description": "Mixtral Instruct (8x7B) is a version of Mixtral (8x7B) that was optimized through supervised fine-tuning and direct preference optimisation (DPO) for careful instruction following. ([blog post](https://mistral.ai/news/mixtral-of-experts/)).",
      "creator_organization": "Mistral AI",
      "access": "open",
      "todo": false,
      "release_date": "2023-12-11",
      "num_parameters": 46700000000
    },
    {
      "name": "mistralai/mixtral-8x22b-instruct-v0.1",
      "display_name": "Mixtral Instruct (8x22B)",
      "short_display_name": "Mixtral Instruct (8x22B)",
      "description": "Mistral AI's mixture-of-experts model that uses 39B active parameters out of 141B ([blog post](https://mistral.ai/news/mixtral-8x22b/)).",
      "creator_organization": "Mistral AI",
      "access": "open",
      "todo": false,
      "release_date": "2024-04-10",
      "num_parameters": 176000000000
    },
    {
      "name": "mistralai/mistral-small-2503",
      "display_name": "Mistral Small 3.1 (2503)",
      "short_display_name": "Mistral Small 3.1 (2503)",
      "description": "Mistral Small 3.1 (2503) is a model with improved text performance, multimodal understanding, and an expanded context window of up to 128k tokens. ([blog](https://mistral.ai/news/mistral-small-3-1))",
      "creator_organization": "Mistral AI",
      "access": "open",
      "todo": false,
      "release_date": "2025-03-17",
      "num_parameters": 23600000000
    },
    {
      "name": "mistralai/mistral-large-2411",
      "display_name": "Mistral Large (2411)",
      "short_display_name": "Mistral Large (2411)",
      "description": "Mistral Large (2411) is a 123B parameter model that has a 128k context window. ([blog](https://mistral.ai/news/pixtral-large/))",
      "creator_organization": "Mistral AI",
      "access": "open",
      "todo": false,
      "release_date": "2024-11-18",
      "num_parameters": 123000000000
    },
    {
      "name": "moonshotai/kimi-k2-instruct",
      "display_name": "Kimi K2 Instruct",
      "short_display_name": "Kimi K2 Instruct",
      "description": "Kimi K2 Instruct is a mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters trained with the Muon optimizer on 15.5T tokens. ([blog](https://moonshotai.github.io/Kimi-K2/))",
      "creator_organization": "Moonshot AI",
      "access": "open",
      "todo": false,
      "release_date": "2024-07-14",
      "num_parameters": 1029173256720
    },
    {
      "name": "openai/gpt-4o-2024-11-20",
      "display_name": "GPT-4o (2024-11-20)",
      "short_display_name": "GPT-4o (2024-11-20)",
      "description": "GPT-4o (2024-11-20) is a large multimodal model that accepts as input any combination of text, audio, and image and generates any combination of text, audio, and image outputs. ([blog](https://openai.com/index/introducing-structured-outputs-in-the-api/))",
      "creator_organization": "OpenAI",
      "access": "limited",
      "todo": false,
      "release_date": "2024-11-20"
    },
    {
      "name": "openai/gpt-4o-mini-2024-07-18",
      "display_name": "GPT-4o mini (2024-07-18)",
      "short_display_name": "GPT-4o mini (2024-07-18)",
      "description": "GPT-4o mini (2024-07-18) is a multimodal model with a context window of 128K tokens and improved handling of non-English text. ([blog](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/))",
      "creator_organization": "OpenAI",
      "access": "limited",
      "todo": false,
      "release_date": "2024-07-18"
    },
    {
      "name": "openai/gpt-4.1-2025-04-14",
      "display_name": "GPT-4.1 (2025-04-14)",
      "short_display_name": "GPT-4.1 (2025-04-14)",
      "description": "GPT-4.1 (2025-04-14) is a multimdodal model in the GPT-4.1 family, which outperforms the GPT-4o family, with major gains in coding and instruction following. They also have larger context windows of 1 million tokens and are able to better use that context with improved long-context comprehension. ([blog](https://openai.com/index/gpt-4-1/))",
      "creator_organization": "OpenAI",
      "access": "limited",
      "todo": false,
      "release_date": "2025-04-14"
    },
    {
      "name": "openai/gpt-4.1-mini-2025-04-14",
      "display_name": "GPT-4.1 mini (2025-04-14)",
      "short_display_name": "GPT-4.1 mini (2025-04-14)",
      "description": "GPT-4.1 mini (2025-04-14) is a multimdodal model in the GPT-4.1 family, which outperforms the GPT-4o family, with major gains in coding and instruction following. They also have larger context windows of 1 million tokens and are able to better use that context with improved long-context comprehension. ([blog](https://openai.com/index/gpt-4-1/))",
      "creator_organization": "OpenAI",
      "access": "limited",
      "todo": false,
      "release_date": "2025-04-14"
    },
    {
      "name": "openai/gpt-4.1-nano-2025-04-14",
      "display_name": "GPT-4.1 nano (2025-04-14)",
      "short_display_name": "GPT-4.1 nano (2025-04-14)",
      "description": "GPT-4.1 nano (2025-04-14) is a multimdodal model in the GPT-4.1 family, which outperforms the GPT-4o family, with major gains in coding and instruction following. They also have larger context windows of 1 million tokens and are able to better use that context with improved long-context comprehension. ([blog](https://openai.com/index/gpt-4-1/))",
      "creator_organization": "OpenAI",
      "access": "limited",
      "todo": false,
      "release_date": "2025-04-14"
    },
    {
      "name": "openai/gpt-5-2025-08-07",
      "display_name": "GPT-5 (2025-08-07)",
      "short_display_name": "GPT-5 (2025-08-07)",
      "description": "GPT-5 (2025-08-07) is a multimdodal model trained for real-world coding tasks and long-running agentic tasks. ([blog](https://openai.com/index/introducing-gpt-5-for-developers/), [system card](https://cdn.openai.com/pdf/8124a3ce-ab78-4f06-96eb-49ea29ffb52f/gpt5-system-card-aug7.pdf))",
      "creator_organization": "OpenAI",
      "access": "limited",
      "todo": false,
      "release_date": "2025-08-07"
    },
    {
      "name": "openai/gpt-5-mini-2025-08-07",
      "display_name": "GPT-5 mini (2025-08-07)",
      "short_display_name": "GPT-5 mini (2025-08-07)",
      "description": "GPT-5 mini (2025-08-07) is a multimdodal model trained for real-world coding tasks and long-running agentic tasks. ([blog](https://openai.com/index/introducing-gpt-5-for-developers/), [system card](https://cdn.openai.com/pdf/8124a3ce-ab78-4f06-96eb-49ea29ffb52f/gpt5-system-card-aug7.pdf))",
      "creator_organization": "OpenAI",
      "access": "limited",
      "todo": false,
      "release_date": "2025-08-07"
    },
    {
      "name": "openai/gpt-5-nano-2025-08-07",
      "display_name": "GPT-5 nano (2025-08-07)",
      "short_display_name": "GPT-5 nano (2025-08-07)",
      "description": "GPT-5 nano (2025-08-07) is a multimdodal model trained for real-world coding tasks and long-running agentic tasks. ([blog](https://openai.com/index/introducing-gpt-5-for-developers/), [system card](https://cdn.openai.com/pdf/8124a3ce-ab78-4f06-96eb-49ea29ffb52f/gpt5-system-card-aug7.pdf))",
      "creator_organization": "OpenAI",
      "access": "limited",
      "todo": false,
      "release_date": "2025-08-07"
    },
    {
      "name": "openai/gpt-5.1-2025-11-13",
      "display_name": "GPT-5.1 (2025-11-13)",
      "short_display_name": "GPT-5.1 (2025-11-13)",
      "description": "GPT-5.1 (2025-11-13) is a model in the GPT-5 model family, and has similar training for code generation, bug fixing, refactoring, instruction following, long context and tool calling. ([blog](https://openai.com/index/gpt-5-1-for-developers/))",
      "creator_organization": "OpenAI",
      "access": "limited",
      "todo": false,
      "release_date": "2025-11-13"
    },
    {
      "name": "openai/o3-2025-04-16",
      "display_name": "o3 (2025-04-16)",
      "short_display_name": "o3 (2025-04-16)",
      "description": "o3 is a reasoning model for math, science, coding, and visual reasoning tasks. ([blog post](https://openai.com/index/introducing-o3-and-o4-mini/))",
      "creator_organization": "OpenAI",
      "access": "limited",
      "todo": false,
      "release_date": "2025-04-16"
    },
    {
      "name": "openai/o4-mini-2025-04-16",
      "display_name": "o4-mini (2025-04-16)",
      "short_display_name": "o4-mini (2025-04-16)",
      "description": "o4-mini is an o-series model optimized for fast, effective reasoning with exceptionally efficient performance in coding and visual tasks. ([blog post](https://openai.com/index/introducing-o3-and-o4-mini/))",
      "creator_organization": "OpenAI",
      "access": "limited",
      "todo": false,
      "release_date": "2025-04-16"
    },
    {
      "name": "openai/gpt-oss-20b",
      "display_name": "gpt-oss-20b",
      "short_display_name": "gpt-oss-20b",
      "description": "gpt-oss-20b is an open-weight language model that was trained using a mix of reinforcement learning and other techniques informed by OpenAI's internal models. It uses a mixture-of-experts architecture and activates 3.6B parameters per token. ([blog](https://openai.com/index/introducing-gpt-oss/))",
      "creator_organization": "OpenAI",
      "access": "open",
      "todo": false,
      "release_date": "2025-08-05"
    },
    {
      "name": "openai/gpt-oss-120b",
      "display_name": "gpt-oss-120b",
      "short_display_name": "gpt-oss-120b",
      "description": "gpt-oss-120b is an open-weight language model that was trained using a mix of reinforcement learning and other techniques informed by OpenAI's internal models. It uses a mixture-of-experts architecture and activates 5.1B parameters per token. ([blog](https://openai.com/index/introducing-gpt-oss/))",
      "creator_organization": "OpenAI",
      "access": "open",
      "todo": false,
      "release_date": "2025-08-05"
    },
    {
      "name": "qwen/qwen2.5-7b-instruct-turbo",
      "display_name": "Qwen2.5 Instruct Turbo (7B)",
      "short_display_name": "Qwen2.5 Instruct Turbo (7B)",
      "description": "Qwen2.5 Instruct Turbo (7B) was trained on 18 trillion tokens and supports 29 languages, and shows improvements over Qwen2 in knowledge, coding, mathematics, instruction following, generating long texts, and processing structure data. ([blog](https://qwenlm.github.io/blog/qwen2.5/)) Turbo is Together's cost-efficient implementation, providing fast FP8 performance while maintaining quality, closely matching FP16 reference models. ([blog](https://www.together.ai/blog/together-inference-engine-2))",
      "creator_organization": "Qwen",
      "access": "open",
      "todo": false,
      "release_date": "2024-09-19"
    },
    {
      "name": "qwen/qwen2.5-72b-instruct-turbo",
      "display_name": "Qwen2.5 Instruct Turbo (72B)",
      "short_display_name": "Qwen2.5 Instruct Turbo (72B)",
      "description": "Qwen2.5 Instruct Turbo (72B) was trained on 18 trillion tokens and supports 29 languages, and shows improvements over Qwen2 in knowledge, coding, mathematics, instruction following, generating long texts, and processing structure data. ([blog](https://qwenlm.github.io/blog/qwen2.5/)) Turbo is Together's cost-efficient implementation, providing fast FP8 performance while maintaining quality, closely matching FP16 reference models. ([blog](https://www.together.ai/blog/together-inference-engine-2))",
      "creator_organization": "Qwen",
      "access": "open",
      "todo": false,
      "release_date": "2024-09-19"
    },
    {
      "name": "qwen/qwen3-235b-a22b-fp8-tput",
      "display_name": "Qwen3 235B A22B FP8 Throughput",
      "short_display_name": "Qwen3 235B A22B FP8 Throughput",
      "description": "Qwen3 235B A22B FP8 Throughput is a hybrid instruct and reasoning mixture-of-experts model ([blog](https://qwenlm.github.io/blog/qwen3/)).",
      "creator_organization": "Qwen",
      "access": "open",
      "todo": false,
      "release_date": "2025-04-29"
    },
    {
      "name": "qwen/qwen3-next-80b-a3b-thinking",
      "display_name": "Qwen3-Next 80B A3B Thinking",
      "short_display_name": "Qwen3-Next 80B A3B Thinking",
      "description": "Qwen3-Next is a new model architecture for improving training and inference efficiency under long-context and large-parameter settings. Compared to the MoE structure of Qwen3, Qwen3-Next introduces a hybrid attention mechanism, a highly sparse Mixture-of-Experts (MoE) structure, training-stability-friendly optimizations, and a multi-token prediction mechanism for faster inference. ([blog](https://qwen.ai/blog?id=4074cca80393150c248e508aa62983f9cb7d27cd&from=research.latest-advancements-list))",
      "creator_organization": "Qwen",
      "access": "open",
      "todo": false,
      "release_date": "2025-07-21"
    },
    {
      "name": "qwen/qwen3-235b-a22b-instruct-2507-fp8",
      "display_name": "Qwen3 235B A22B Instruct 2507 FP8",
      "short_display_name": "Qwen3 235B A22B Instruct 2507 FP8",
      "description": "Qwen3 235B A22B Instruct 2507 FP8 is an updated version of the non-thinking mode of Qwen3 235B A22B FP8.",
      "creator_organization": "Qwen",
      "access": "open",
      "todo": false,
      "release_date": "2025-07-21"
    },
    {
      "name": "writer/palmyra-x-004",
      "display_name": "Palmyra-X-004",
      "short_display_name": "Palmyra-X-004",
      "description": "Palmyra-X-004 language model with a large context window of up to 128,000 tokens that excels in processing and understanding complex tasks.",
      "creator_organization": "Writer",
      "access": "limited",
      "todo": false,
      "release_date": "2024-09-12"
    },
    {
      "name": "writer/palmyra-x5",
      "display_name": "Palmyra X5",
      "short_display_name": "Palmyra X5",
      "description": "Palmyra X5 is a language model for enterprise that uses a Mixture of Experts (MoE) architecture and a hybrid attention mechanism that blends linear and softmax attention. ([blog](https://writer.com/engineering/long-context-palmyra-x5/))",
      "creator_organization": "Writer",
      "access": "limited",
      "todo": false,
      "release_date": "2025-04-28"
    },
    {
      "name": "writer/palmyra-med",
      "display_name": "Palmyra Med",
      "short_display_name": "Palmyra Med",
      "description": "Palmyra Med is a model intended for medical applications.",
      "creator_organization": "Writer",
      "access": "open",
      "todo": false,
      "release_date": "2024-07-31"
    },
    {
      "name": "writer/palmyra-fin",
      "display_name": "Palmyra Fin",
      "short_display_name": "Palmyra Fin",
      "description": "Palmyra Fin is a financial LLM built using combining a well-curated set of financial training data with custom fine-tuning instruction data([blog](https://writer.com/blog/palmyra-med-fin-models/)).",
      "creator_organization": "Writer",
      "access": "limited",
      "todo": false,
      "release_date": "2024-07-31"
    },
    {
      "name": "xai/grok-3-beta",
      "display_name": "Grok 3 Beta",
      "short_display_name": "Grok 3 Beta",
      "description": "Grok 3 Beta is a model trained on xAI's Colossus supercluster with significant improvements in reasoning, mathematics, coding, world knowledge, and instruction-following tasks. ([blog](https://x.ai/news/grok-3))",
      "creator_organization": "xAI",
      "access": "limited",
      "todo": false,
      "release_date": "2025-04-03"
    },
    {
      "name": "xai/grok-3-mini-beta",
      "display_name": "Grok 3 mini Beta",
      "short_display_name": "Grok 3 mini Beta",
      "description": "Grok 3 mini Beta is a model trained on xAI's Colossus supercluster with significant improvements in reasoning, mathematics, coding, world knowledge, and instruction-following tasks. ([blog](https://x.ai/news/grok-3))",
      "creator_organization": "xAI",
      "access": "limited",
      "todo": false,
      "release_date": "2025-04-03"
    },
    {
      "name": "xai/grok-4-0709",
      "display_name": "Grok 4 (0709)",
      "short_display_name": "Grok 4 (0709)",
      "description": "Grok 4 (0709) is a model that includes native tool use and real-time search integration. ([blog](https://x.ai/news/grok-4))",
      "creator_organization": "xAI",
      "access": "limited",
      "todo": false,
      "release_date": "2025-07-09"
    },
    {
      "name": "zai-org/glm-4.5-air-fp8",
      "display_name": "GLM-4.5-Air-FP8",
      "short_display_name": "GLM-4.5-Air-FP8",
      "description": "GLM-4.5-Air-FP8 is a hybrid reasoning model designed to unify reasoning, coding, and agentic capabilities into a single model. It has 106 billion total parameters and 12 billion active parameters. The thinking mode is enabled by default. ([blog](https://z.ai/blog/glm-4.5))",
      "creator_organization": "Z.ai",
      "access": "open",
      "todo": false,
      "release_date": "2025-07-28",
      "num_parameters": 110000000000
    },
    {
      "name": "ibm/granite-3.3-8b-instruct",
      "display_name": "IBM Granite 3.3 8B Instruct",
      "short_display_name": "IBM Granite 3.3 8B Instruct",
      "description": "IBM Granite 3.3 8B Instruct is an 8-billion parameter 128K context length language model fine-tuned for improved reasoning and instruction-following capabilities. ([model card](https://huggingface.co/ibm-granite/granite-3.3-8b-instruct))",
      "creator_organization": "IBM",
      "access": "open",
      "todo": false,
      "release_date": "2025-04-16",
      "num_parameters": 8170000000
    },
    {
      "name": "ibm/granite-4.0-h-small",
      "display_name": "IBM Granite 4.0 Small",
      "short_display_name": "IBM Granite 4.0 Small",
      "description": "IBM Granite 4.0 Small is a hybrid model with 32B total parameters and 9B active parameters that uses the Mixture of Experts (MoE) routing strategy with Mamba-2 and Transformer-based self-attention components.",
      "creator_organization": "IBM",
      "access": "open",
      "todo": false,
      "num_parameters": 32000000000
    },
    {
      "name": "ibm/granite-4.0-micro",
      "display_name": "IBM Granite 4.0 Micro",
      "short_display_name": "IBM Granite 4.0 Micro",
      "description": "IBM Granite 4.0 Micro is a dense Transformer model with 3B total parameters that provides an alternative option for users when Mamba2 support is not yet optimized.",
      "creator_organization": "IBM",
      "access": "open",
      "todo": false,
      "num_parameters": 3000000000
    }
  ]
}