APEX-Agents Original Effort: High 35.3% mercor.com for Gemini 3.1 Pro (high) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Gemini 3.1 Pro on APEX-Agents Original AutomationBench 1.0.6 Effort: Low 4.6% zapier.com for Gemini 3.1 Pro (low) on AutomationBench 1.0.6 (opens in a new tab) Archived copy (opens in a new tab) Task pass rate Reported October 7, 2026 Benchmark leaderboard Zapier Independent Zapier AutomationBench Team Record for Gemini 3.1 Pro on AutomationBench 1.0.6 AutomationBench 1.0.6 Effort: Medium 7.0% zapier.com for Gemini 3.1 Pro (medium) on AutomationBench 1.0.6 (opens in a new tab) Archived copy (opens in a new tab) Task pass rate Reported October 7, 2026 Benchmark leaderboard Zapier Independent Zapier AutomationBench Team Record for Gemini 3.1 Pro on AutomationBench 1.0.6 AutomationBench 1.0.6 Effort: High 8.7% zapier.com for Gemini 3.1 Pro (high) on AutomationBench 1.0.6 (opens in a new tab) Archived copy (opens in a new tab) Task pass rate Reported October 7, 2026 Benchmark leaderboard Zapier Independent Zapier AutomationBench Team Record for Gemini 3.1 Pro on AutomationBench 1.0.6 BrowseComp 130-question subset — Mercor web research agent Effort: High Configuration: Mercor web research agent, 100 steps, 3 hours 75.6% mercor.com for Gemini 3.1 Pro (high) on BrowseComp 130-question subset — Mercor web research agent (opens in a new tab) Archived copy (opens in a new tab) BrowseComp Accuracy Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Gemini 3.1 Pro on BrowseComp 130-question subset — Mercor web research agent BrowseComp Effort: High 85.9% deepmind.google for Gemini 3.1 Pro (High) on BrowseComp BrowseComp (opens in a new tab) BrowseComp Accuracy Reported February 19, 2026 Model card Google DeepMind Self-reported Record for Gemini 3.1 Pro on BrowseComp BrowseComp Chartography October 2026 leaderboard Effort: High 26.1% surgehq.ai for Gemini 3.1 Pro (High) on Chartography October 2026 leaderboard (opens in a new tab) Archived copy (opens in a new tab) Chartography Pass@1 Reported October 7, 2026 Benchmark leaderboard Surge AI Independent Record for Gemini 3.1 Pro on Chartography October 2026 leaderboard CharXiv Descriptive and reasoning — Mercor single-shot Effort: High Configuration: Mercor single-shot agent 94.6% mercor.com for Gemini 3.1 Pro (high) on CharXiv Descriptive and reasoning — Mercor single-shot (opens in a new tab) Archived copy (opens in a new tab) CharXiv Accuracy Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Gemini 3.1 Pro on CharXiv Descriptive and reasoning — Mercor single-shot DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps Effort: High Configuration: Mercor mini-swe-agent, 500 steps, 2 hours 7.7% mercor.com for Gemini 3.1 Pro (high) on DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps (opens in a new tab) Archived copy (opens in a new tab) DeepSWE Pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Gemini 3.1 Pro on DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps Finance Agent Benchmark 2 — October 2026 evaluation Effort: High 43.0% vals.ai for Gemini 3.1 Pro (high) on Finance Agent Benchmark 2 — October 2026 evaluation (opens in a new tab) Archived copy (opens in a new tab) Finance Agent Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Gemini 3.1 Pro on Finance Agent Benchmark 2 — October 2026 evaluation GPQA Diamond Effort: High 94.3% deepmind.google for Gemini 3.1 Pro (High) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) GPQA Diamond Accuracy Reported February 19, 2026 Model card Google DeepMind Self-reported Record for Gemini 3.1 Pro on Graduate-Level Google-Proof Q&A Diamond GPQA Diamond — Epoch AI harness Effort: High Configuration: Epoch AI harness 94.4% epoch.ai for Gemini 3.1 Pro (high) 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 August 6, 2026 at 10:30 PM UTC Benchmark leaderboard Epoch AI Independent Record for Gemini 3.1 Pro on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Epoch AI harness Configuration: Epoch AI harness 94.1% epoch.ai for Gemini 3.1 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 February 20, 2026 at 5:01 AM UTC Benchmark leaderboard Epoch AI Independent Record for Gemini 3.1 Pro on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Mercor single-shot Effort: High Configuration: Mercor single-shot agent 94.2% mercor.com for Gemini 3.1 Pro (high) on Graduate-Level Google-Proof Q&A Diamond — Mercor single-shot (opens in a new tab) Archived copy (opens in a new tab) GPQA Diamond Accuracy Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Gemini 3.1 Pro on Graduate-Level Google-Proof Q&A Diamond — Mercor single-shot GPQA Diamond — Vals AI harness Effort: High Configuration: Vals AI harness: mean of zero-shot and few-shot CoT 95.5% vals.ai for Gemini 3.1 Pro (high) 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 3.1 Pro on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness HLAB October 2026 evaluation Effort: High 0.0% vals.ai for Gemini 3.1 Pro (high) on Harvey's Legal Agent Benchmark October 2026 evaluation (opens in a new tab) Archived copy (opens in a new tab) HLAB Task Pass Rate Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Gemini 3.1 Pro on Harvey's Legal Agent Benchmark October 2026 evaluation Humanity's Last Exam Full set — No tools Effort: High Configuration: No tools 44.4% deepmind.google for Gemini 3.1 Pro (High) on Humanity's Last Exam Full set — No tools (opens in a new tab) Humanity's Last Exam Accuracy Reported February 19, 2026 Model card Google DeepMind Self-reported Record for Gemini 3.1 Pro on Humanity's Last Exam Full set — No tools Humanity's Last Exam Full set — Scale AI evaluation Effort: High Reported as: thinking high 46.4% labs.scale.com for Gemini 3.1 Pro (thinking high) 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 3.1 Pro on Humanity's Last Exam Full set — Scale AI evaluation Humanity's Last Exam Text only — Mercor single-shot Effort: High Configuration: Mercor single-shot agent 44.1% mercor.com for Gemini 3.1 Pro (high) on Humanity's Last Exam Text only — Mercor single-shot (opens in a new tab) Archived copy (opens in a new tab) Humanity's Last Exam Accuracy Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Gemini 3.1 Pro on Humanity's Last Exam Text only — Mercor single-shot Humanity's Last Exam Text only — Scale AI evaluation Effort: High Reported as: thinking high 47.3% labs.scale.com for Gemini 3.1 Pro (thinking high) 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 3.1 Pro on Humanity's Last Exam Text only — Scale AI evaluation MCP Atlas Public, April 2026 update Effort: High 78.2% labs.scale.com for Gemini 3.1 Pro (high) on MCP Atlas Public, April 2026 update (opens in a new tab) Pass rate Reported September 24, 2026 Benchmark leaderboard Scale AI Independent Record for Gemini 3.1 Pro on MCP Atlas Public, April 2026 update MedXpertQA MM — Mercor single-shot Effort: High Configuration: Mercor single-shot agent 80.2% mercor.com for Gemini 3.1 Pro (high) on MedXpertQA MM — Mercor single-shot (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Gemini 3.1 Pro on MedXpertQA MM — Mercor single-shot MMLU-Pro Original — Mercor single-shot Effort: High Configuration: Mercor single-shot agent 91.3% mercor.com for Gemini 3.1 Pro (high) on MMLU-Pro Original — Mercor single-shot (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Gemini 3.1 Pro on MMLU-Pro Original — Mercor single-shot MMLU-Pro Original — Vals AI harness Effort: High Configuration: Vals AI harness 91.0% vals.ai for Gemini 3.1 Pro (high) 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 3.1 Pro on MMLU-Pro Original — Vals AI harness MMMU-Pro 1,730 questions — Mercor single-shot Effort: High Configuration: Mercor single-shot agent 84.3% mercor.com for Gemini 3.1 Pro (high) on MMMU-Pro 1,730 questions — Mercor single-shot (opens in a new tab) Archived copy (opens in a new tab) MMMU-Pro accuracy Setting: Not stated Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Gemini 3.1 Pro on MMMU-Pro 1,730 questions — Mercor single-shot MMMU-Pro No tools Effort: High Configuration: No tools 80.5% deepmind.google for Gemini 3.1 Pro (High) on MMMU-Pro No tools (opens in a new tab) MMMU-Pro accuracy Setting: Overall (Standard 10 options + Vision) Reported February 19, 2026 Model card Google DeepMind Self-reported Record for Gemini 3.1 Pro on MMMU-Pro No tools MMMU-Pro Vals AI harness Effort: High Configuration: Vals AI harness 88.2% vals.ai for Gemini 3.1 Pro (high) 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 3.1 Pro on MMMU-Pro Vals AI harness PostTrainBench 1.1 — OpenCode Configuration: OpenCode harness 22.0% posttrainbench.com for Gemini 3.1 Pro on PostTrainBench 1.1 — OpenCode (opens in a new tab) Archived copy (opens in a new tab) PostTrainBench Weighted Aggregate Reported October 6, 2026 Benchmark leaderboard PostTrainBench Independent PostTrainBench Team Record for Gemini 3.1 Pro on PostTrainBench 1.1 — OpenCode PostTrainBench 1.2 — OpenCode Configuration: OpenCode harness 18.1% posttrainbench.com for Gemini 3.1 Pro on PostTrainBench 1.2 — OpenCode (opens in a new tab) Archived copy (opens in a new tab) PostTrainBench Weighted Aggregate Reported October 6, 2026 Benchmark leaderboard PostTrainBench Independent PostTrainBench Team Record for Gemini 3.1 Pro on PostTrainBench 1.2 — OpenCode Riemann-bench October 2026 leaderboard Effort: High 33.6% surgehq.ai for Gemini 3.1 Pro (High) on Riemann-bench October 2026 leaderboard (opens in a new tab) Archived copy (opens in a new tab) Riemann-bench Pass@1 Reported October 7, 2026 Benchmark leaderboard Surge AI Independent Record for Gemini 3.1 Pro on Riemann-bench October 2026 leaderboard SimpleQA Verified Original — Epoch AI harness Effort: High Configuration: Epoch AI harness 73.5% epoch.ai for Gemini 3.1 Pro (high) on SimpleQA Verified Original — Epoch AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported October 7, 2026 Evaluated August 10, 2026 at 9:35 PM UTC Benchmark leaderboard Epoch AI Independent Record for Gemini 3.1 Pro on SimpleQA Verified Original — Epoch AI harness SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps Effort: High Configuration: Mercor mini-swe-agent, 250 steps, 1 hour 18.0% mercor.com for Gemini 3.1 Pro (high) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Gemini 3.1 Pro on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps SWE Atlas Codebase QnA — Public; mini-swe-agent Configuration: mini-swe-agent harness 13.5% labs.scale.com for Gemini 3.1 Pro on SWE Atlas Codebase QnA — Public; mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Scale AI Independent Record for Gemini 3.1 Pro on SWE Atlas Codebase QnA — Public; mini-swe-agent SWE Atlas Refactoring — Gemini CLI Configuration: Gemini CLI harness 33.8% labs.scale.com for Gemini 3.1 Pro on SWE Atlas Refactoring — Gemini CLI (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Scale AI Independent Record for Gemini 3.1 Pro on SWE Atlas Refactoring — Gemini CLI SWE-bench Multilingual — Mercor mini-swe-agent, 1000 steps Effort: High Configuration: Mercor mini-swe-agent, 1000 steps, 3 hours 65.1% mercor.com for Gemini 3.1 Pro (high) on SWE-bench Multilingual — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Gemini 3.1 Pro on SWE-bench Multilingual — Mercor mini-swe-agent, 1000 steps SWE-bench Verified Effort: High 80.6% deepmind.google for Gemini 3.1 Pro (High) on SWE-bench Verified (opens in a new tab) Resolved Tasks Reported February 19, 2026 Model card Google DeepMind Self-reported Record for Gemini 3.1 Pro on SWE-bench Verified SWE-bench Verified — Mercor mini-swe-agent, 1000 steps Effort: High Configuration: Mercor mini-swe-agent, 1000 steps, 3 hours 78.4% mercor.com for Gemini 3.1 Pro (high) on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Gemini 3.1 Pro on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps SWE-bench Verified — Vals AI mini-swe-agent Effort: High Configuration: mini-swe-agent harness 78.8% vals.ai for Gemini 3.1 Pro (high) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for Gemini 3.1 Pro on SWE-bench Verified — Vals AI mini-swe-agent SWE-bench Pro Private — Scale AI mini-swe-agent Reported as: thinking Configuration: mini-swe-agent harness 32.2% labs.scale.com for Gemini 3.1 Pro (thinking) on SWE-bench Pro Private — Scale AI mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Public tasks resolved Reported October 7, 2026 Benchmark leaderboard Scale AI Independent Record for Gemini 3.1 Pro on SWE-bench Pro Private — Scale AI mini-swe-agent SWE-bench Pro Public Effort: High 54.2% deepmind.google for Gemini 3.1 Pro (High) on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported February 19, 2026 Model card Google DeepMind Self-reported Record for Gemini 3.1 Pro on SWE-bench Pro Public SWE-bench Pro Public — Scale AI mini-swe-agent Reported as: thinking Configuration: mini-swe-agent harness 46.1% labs.scale.com for Gemini 3.1 Pro (thinking) on SWE-bench Pro Public — Scale AI mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Public tasks resolved Reported October 7, 2026 Benchmark leaderboard Scale AI Independent Record for Gemini 3.1 Pro on SWE-bench Pro Public — Scale AI mini-swe-agent Terminal-Bench 2.0 Effort: High 68.5% deepmind.google for Gemini 3.1 Pro (High) on Terminal-Bench 2.0 (opens in a new tab) Terminal-Bench Accuracy Reported February 19, 2026 Model card Google DeepMind Self-reported Record for Gemini 3.1 Pro on Terminal-Bench 2.0 Terminal-Bench 2.0 — Vals AI Terminus 2 Effort: High Configuration: Terminus-2 harness 67.4% vals.ai for Gemini 3.1 Pro (high) on Terminal-Bench 2.0 — Vals AI Terminus 2 (opens in a new tab) Archived copy (opens in a new tab) Terminal-Bench Accuracy Reported June 4, 2026 Benchmark leaderboard Vals AI Independent Record for Gemini 3.1 Pro on Terminal-Bench 2.0 — Vals AI Terminus 2 Terminal-Bench 2.1 — Mercor Terminus 2 Effort: High Configuration: Mercor Terminus 2, 1000 steps, 3 hours 72.7% mercor.com for Gemini 3.1 Pro (high) on Terminal-Bench 2.1 — Mercor Terminus 2 (opens in a new tab) Archived copy (opens in a new tab) Terminal-Bench Accuracy Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for Gemini 3.1 Pro on Terminal-Bench 2.1 — Mercor Terminus 2 Terminal-Bench 2.1 — Vals AI Terminus 2 Effort: High Configuration: Terminus-2 harness 70.8% vals.ai for Gemini 3.1 Pro (high) on Terminal-Bench 2.1 — Vals AI Terminus 2 (opens in a new tab) Archived copy (opens in a new tab) Terminal-Bench Accuracy Reported September 28, 2026 Benchmark leaderboard Vals AI Independent Record for Gemini 3.1 Pro on Terminal-Bench 2.1 — Vals AI Terminus 2 Terminal-Bench 4.0 — Vals AI mini-swe-agent Effort: High Configuration: mini-swe-agent harness 2.5% vals.ai for Gemini 3.1 Pro (high) on Terminal-Bench 4.0 — Vals AI mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Terminal-Bench Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Gemini 3.1 Pro on Terminal-Bench 4.0 — Vals AI mini-swe-agent Toolathlon Original 48.8% toolathlon.xyz for Gemini 3.1 Pro on Toolathlon Original (opens in a new tab) Archived copy (opens in a new tab) Tasks completed Reported March 13, 2026 Benchmark leaderboard Toolathlon Independent Toolathlon Authors Record for Gemini 3.1 Pro on Toolathlon Original Toolathlon Verified Effort: High 61.1% toolathlon.xyz for Gemini 3.1 Pro (high) on Toolathlon Verified (opens in a new tab) Archived copy (opens in a new tab) Tasks completed Reported July 1, 2026 Benchmark leaderboard Toolathlon Independent Toolathlon Authors Record for Gemini 3.1 Pro on Toolathlon Verified Vals Index 2.1 Effort: High 33.4% vals.ai for Gemini 3.1 Pro (high) on Vals Index 2.1 (opens in a new tab) Archived copy (opens in a new tab) Vals Index GDP-weighted Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Gemini 3.1 Pro on Vals Index 2.1 Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation Effort: High Configuration: OpenHands harness 32.0% vals.ai for Gemini 3.1 Pro (high) on Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation (opens in a new tab) Archived copy (opens in a new tab) Vibe Code Bench Score Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for Gemini 3.1 Pro on Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation