| eval-run:android-world.gemini-2-5-pro.2025-06 | eval-run:android-world.gemini-2-5-pro.2025-06 | 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.gemini-2-5-pro.2025-06 | eval-run:gpqa.gemini-2-5-pro.2025-06 | benchmarks |
| eval-run:livecodebench.gemini-2-5-pro.2025-06 | eval-run:livecodebench.gemini-2-5-pro.2025-06 | benchmarks |
| eval-run:mgsm.gemini-2-5-pro.2025-06 | eval-run:mgsm.gemini-2-5-pro.2025-06 | benchmarks |
| eval-run:swe-bench-verified.gemini-2-5-pro.2025-06 | eval-run:swe-bench-verified.gemini-2-5-pro.2025-06 | benchmarks |