| eval-run:android-world.gemini-2-5-pro.2025-06 | eval-run:android-world.gemini-2-5-pro.2025-06 | benchmarks |
| eval-run:arc-challenge.claude-sonnet-4-5.2025-09 | eval-run:arc-challenge.claude-sonnet-4-5.2025-09 | benchmarks |
| eval-run:bfcl.claude-sonnet-4-5.2025-09 | eval-run:bfcl.claude-sonnet-4-5.2025-09 | benchmarks |
| eval-run:bfcl.gpt-5.2025-08 | eval-run:bfcl.gpt-5.2025-08 | benchmarks |
| eval-run:evalplus.gpt-5.2025-08 | eval-run:evalplus.gpt-5.2025-08 | benchmarks |
| eval-run:gaia.claude-code.2025 | eval-run:gaia.claude-code.2025 | benchmarks |
| eval-run:gpqa-diamond.claude-opus-4-5.2025-09 | eval-run:gpqa-diamond.claude-opus-4-5.2025-09 | benchmarks |
| eval-run:gpqa-diamond.gemini-2-5-pro.2025-06 | eval-run:gpqa-diamond.gemini-2-5-pro.2025-06 | benchmarks |
| eval-run:gpqa-diamond.gemini-3-1-pro.2026-02-19 | eval-run:gpqa-diamond.gemini-3-1-pro.2026-02-19 | benchmarks |
| eval-run:gpqa-diamond.gemini-3-pro.2025-11-18 | eval-run:gpqa-diamond.gemini-3-pro.2025-11-18 | benchmarks |
| eval-run:gpqa-diamond.gpt-5-4-mini.2026-03-17 | eval-run:gpqa-diamond.gpt-5-4-mini.2026-03-17 | benchmarks |
| eval-run:gpqa-diamond.gpt-5-4.2026-03-17 | eval-run:gpqa-diamond.gpt-5-4.2026-03-17 | benchmarks |
| eval-run:gpqa-diamond.gpt-5.2025-08 | eval-run:gpqa-diamond.gpt-5.2025-08 | benchmarks |
| eval-run:gpqa.claude-haiku-4-5.2025-10 | eval-run:gpqa.claude-haiku-4-5.2025-10 | benchmarks |
| eval-run:gpqa.claude-sonnet-4-5.2025-09 | eval-run:gpqa.claude-sonnet-4-5.2025-09 | benchmarks |
| eval-run:gpqa.deepseek-r1.2025-01 | eval-run:gpqa.deepseek-r1.2025-01 | benchmarks |
| eval-run:gpqa.gemini-2-5-pro.2025-06 | eval-run:gpqa.gemini-2-5-pro.2025-06 | benchmarks |
| eval-run:gpqa.gpt-5.2025-08 | eval-run:gpqa.gpt-5.2025-08 | benchmarks |
| eval-run:gsm8k.claude-sonnet-4-5.2025-09 | eval-run:gsm8k.claude-sonnet-4-5.2025-09 | benchmarks |
| eval-run:gsm8k.gemma-2-27b.2024-06 | eval-run:gsm8k.gemma-2-27b.2024-06 | benchmarks |
| eval-run:harmbench.claude-opus-4-5.2025-09 | eval-run:harmbench.claude-opus-4-5.2025-09 | benchmarks |
| eval-run:hellaswag.claude-opus-4-5.2025-09 | eval-run:hellaswag.claude-opus-4-5.2025-09 | benchmarks |
| eval-run:human-eval-plus.claude-sonnet-4-5.2025-09 | eval-run:human-eval-plus.claude-sonnet-4-5.2025-09 | benchmarks |
| eval-run:human-eval-plus.gpt-5.2025-08 | eval-run:human-eval-plus.gpt-5.2025-08 | benchmarks |
| eval-run:human-eval.claude-sonnet-4-6.2025-11 | eval-run:human-eval.claude-sonnet-4-6.2025-11 | benchmarks |
| eval-run:human-eval.codestral-25-01.2025-01 | eval-run:human-eval.codestral-25-01.2025-01 | benchmarks |
| eval-run:human-eval.deepseek-v3.2024-12 | eval-run:human-eval.deepseek-v3.2024-12 | benchmarks |
| eval-run:human-eval.gpt-5.2025-08 | eval-run:human-eval.gpt-5.2025-08 | benchmarks |
| eval-run:human-eval.llama-3-1-405b.2024-07 | eval-run:human-eval.llama-3-1-405b.2024-07 | benchmarks |
| eval-run:human-eval.llama-3-3-70b.2024-12 | eval-run:human-eval.llama-3-3-70b.2024-12 | benchmarks |
| eval-run:human-eval.llama-4-405b.2024-07 | eval-run:human-eval.llama-4-405b.2024-07 | benchmarks |
| eval-run:human-eval.mistral-large-2.2024-07 | eval-run:human-eval.mistral-large-2.2024-07 | benchmarks |
| eval-run:human-eval.qwen-2-5-72b.2024-09 | eval-run:human-eval.qwen-2-5-72b.2024-09 | benchmarks |
| eval-run:human-eval.qwen-2-5-coder-32b.2024-11 | eval-run:human-eval.qwen-2-5-coder-32b.2024-11 | benchmarks |
| eval-run:livecodebench.gemini-2-5-pro.2025-06 | eval-run:livecodebench.gemini-2-5-pro.2025-06 | benchmarks |
| eval-run:livecodebench.gpt-5.2025-08 | eval-run:livecodebench.gpt-5.2025-08 | benchmarks |
| eval-run:livecodebench.qwen-2-5-coder-32b.2024-11 | eval-run:livecodebench.qwen-2-5-coder-32b.2024-11 | benchmarks |
| eval-run:math.deepseek-r1.2025-01 | eval-run:math.deepseek-r1.2025-01 | benchmarks |
| eval-run:math.gpt-5.2025-08 | eval-run:math.gpt-5.2025-08 | benchmarks |
| eval-run:math.o3.2025-04 | eval-run:math.o3.2025-04 | benchmarks |
| eval-run:mbpp.qwen-2-5-coder-32b.2024-11 | eval-run:mbpp.qwen-2-5-coder-32b.2024-11 | benchmarks |
| eval-run:mgsm.gemini-2-5-pro.2025-06 | eval-run:mgsm.gemini-2-5-pro.2025-06 | benchmarks |
| eval-run:mmlu.claude-sonnet-4-6.2025-11 | eval-run:mmlu.claude-sonnet-4-6.2025-11 | benchmarks |
| eval-run:mmlu.command-r-plus.2024-08 | eval-run:mmlu.command-r-plus.2024-08 | benchmarks |
| eval-run:mmlu.deepseek-r1.2025-01 | eval-run:mmlu.deepseek-r1.2025-01 | benchmarks |
| eval-run:mmlu.deepseek-v3.2024-12 | eval-run:mmlu.deepseek-v3.2024-12 | benchmarks |
| eval-run:mmlu.gemma-2-27b.2024-06 | eval-run:mmlu.gemma-2-27b.2024-06 | benchmarks |
| eval-run:mmlu.llama-3-1-405b.2024-07 | eval-run:mmlu.llama-3-1-405b.2024-07 | benchmarks |
| eval-run:mmlu.llama-3-3-70b.2024-12 | eval-run:mmlu.llama-3-3-70b.2024-12 | benchmarks |
| eval-run:mmlu.llama-4-405b.2024-07 | eval-run:mmlu.llama-4-405b.2024-07 | benchmarks |