GPQA Diamond 86.4% storage.googleapis.com for Gemini 2.5 Pro on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) GPQA Diamond Accuracy Reported July 2, 2025 Technical report Google Self-reported Google DeepMind Record for Gemini 2.5 Pro on Graduate-Level Google-Proof Q&A Diamond GPQA Diamond — Epoch AI harness Configuration: Epoch AI harness 83.8% epoch.ai for Gemini 2.5 Pro on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness (opens in a new tab) Archived copy (opens in a new tab) GPQA Diamond Accuracy Reported October 7, 2026 Evaluated March 31, 2025 at 4:06 PM UTC Benchmark leaderboard Epoch AI Independent Record for Gemini 2.5 Pro on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Vals AI harness Configuration: Vals AI harness: mean of zero-shot and few-shot CoT 80.8% vals.ai for Gemini 2.5 Pro on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) GPQA Diamond Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Gemini 2.5 Pro on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness Humanity's Last Exam Full set — Scale AI evaluation 18.2% labs.scale.com for Gemini 2.5 Pro on Humanity's Last Exam Full set — Scale AI evaluation (opens in a new tab) Archived copy (opens in a new tab) Humanity's Last Exam Accuracy Reported October 3, 2026 Benchmark leaderboard Scale AI Independent Record for Gemini 2.5 Pro on Humanity's Last Exam Full set — Scale AI evaluation Humanity's Last Exam Text only — Scale AI evaluation 18.4% labs.scale.com for Gemini 2.5 Pro on Humanity's Last Exam Text only — Scale AI evaluation (opens in a new tab) Archived copy (opens in a new tab) Humanity's Last Exam Accuracy Reported October 7, 2026 Benchmark leaderboard Scale AI Independent Record for Gemini 2.5 Pro on Humanity's Last Exam Text only — Scale AI evaluation MMMU 82.0% storage.googleapis.com for Gemini 2.5 Pro on Massive Multi-discipline Multimodal Understanding MMMU (opens in a new tab) MMMU Accuracy Reported July 2, 2025 Technical report Google Self-reported Google DeepMind Record for Gemini 2.5 Pro on Massive Multi-discipline Multimodal Understanding MMMU MMLU-Pro Original — Vals AI harness Configuration: Vals AI harness 84.1% vals.ai for Gemini 2.5 Pro on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Gemini 2.5 Pro on MMLU-Pro Original — Vals AI harness MMMU-Pro Vals AI harness Configuration: Vals AI harness 81.3% vals.ai for Gemini 2.5 Pro on MMMU-Pro Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) MMMU-Pro accuracy Setting: Standard (4 options) Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Gemini 2.5 Pro on MMMU-Pro Vals AI harness SWE-bench Verified 59.6% storage.googleapis.com for Gemini 2.5 Pro on SWE-bench Verified (opens in a new tab) Resolved Tasks Reported July 2, 2025 Technical report Google Self-reported Google DeepMind Record for Gemini 2.5 Pro on SWE-bench Verified SWE-bench Verified — mini-swe-agent Configuration: mini-swe-agent harness 53.6% github.com for Gemini 2.5 Pro on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported July 26, 2025 Benchmark repository SWE-bench Independent SWE-bench Team Record for Gemini 2.5 Pro on SWE-bench Verified — mini-swe-agent