APEX-Agents Original Effort: Max 60.0% mercor.com for GPT-6.1 Sol (max) 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 GPT-6.1 Sol on APEX-Agents Original AutomationBench 1.0.6 Effort: Low 24.7% openai.com for GPT-6.1 Sol (low) on AutomationBench 1.0.6 (opens in a new tab) Task pass rate Reported September 29, 2026 Launch post OpenAI Self-reported Record for GPT-6.1 Sol on AutomationBench 1.0.6 AutomationBench 1.0.6 Effort: Medium 31.7% openai.com for GPT-6.1 Sol (medium) on AutomationBench 1.0.6 (opens in a new tab) Task pass rate Reported September 29, 2026 Launch post OpenAI Self-reported Record for GPT-6.1 Sol on AutomationBench 1.0.6 AutomationBench 1.0.6 Effort: High 33.2% openai.com for GPT-6.1 Sol (high) on AutomationBench 1.0.6 (opens in a new tab) Task pass rate Reported September 29, 2026 Launch post OpenAI Self-reported Record for GPT-6.1 Sol on AutomationBench 1.0.6 AutomationBench 1.0.6 Effort: xHigh 35.5% openai.com for GPT-6.1 Sol (xhigh) on AutomationBench 1.0.6 (opens in a new tab) Task pass rate Reported September 29, 2026 Launch post OpenAI Self-reported Record for GPT-6.1 Sol on AutomationBench 1.0.6 AutomationBench 1.0.6 Effort: Max 36.1% openai.com for GPT-6.1 Sol (max) on AutomationBench 1.0.6 (opens in a new tab) Task pass rate Reported September 29, 2026 Launch post OpenAI Self-reported Record for GPT-6.1 Sol on AutomationBench 1.0.6 BrowseComp 130-question subset — Mercor web research agent Effort: Max Configuration: Mercor web research agent, 100 steps, 3 hours 95.4% mercor.com for GPT-6.1 Sol (max) 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 GPT-6.1 Sol on BrowseComp 130-question subset — Mercor web research agent CharXiv Descriptive and reasoning — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 96.0% mercor.com for GPT-6.1 Sol (max) 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 GPT-6.1 Sol on CharXiv Descriptive and reasoning — Mercor single-shot Coronavirus–ACE2 Cell-Entry Screen Original 0.423 deploymentsafety.openai.com for GPT-6.1 Sol on Coronavirus–ACE2 Cell-Entry Screen Original (opens in a new tab) Composite score Reported September 29, 2026 System card addendum OpenAI Self-reported Record for GPT-6.1 Sol on Coronavirus–ACE2 Cell-Entry Screen Original DeepSWE 1.1 Effort: Low 64.4% openai.com for GPT-6.1 Sol (low) on DeepSWE 1.1 (opens in a new tab) DeepSWE Pass@1 Reported September 29, 2026 Launch post OpenAI Self-reported Record for GPT-6.1 Sol on DeepSWE 1.1 DeepSWE 1.1 Effort: Medium 73.0% openai.com for GPT-6.1 Sol (medium) on DeepSWE 1.1 (opens in a new tab) DeepSWE Pass@1 Reported September 29, 2026 Launch post OpenAI Self-reported Record for GPT-6.1 Sol on DeepSWE 1.1 DeepSWE 1.1 Effort: High 75.2% openai.com for GPT-6.1 Sol (high) on DeepSWE 1.1 (opens in a new tab) DeepSWE Pass@1 Reported September 29, 2026 Launch post OpenAI Self-reported Record for GPT-6.1 Sol on DeepSWE 1.1 DeepSWE 1.1 Effort: xHigh 71.9% openai.com for GPT-6.1 Sol (xhigh) on DeepSWE 1.1 (opens in a new tab) DeepSWE Pass@1 Reported September 29, 2026 Launch post OpenAI Self-reported Record for GPT-6.1 Sol on DeepSWE 1.1 DeepSWE 1.1 Effort: Max 71.9% openai.com for GPT-6.1 Sol (max) on DeepSWE 1.1 (opens in a new tab) DeepSWE Pass@1 Reported September 29, 2026 Launch post OpenAI Self-reported Record for GPT-6.1 Sol on DeepSWE 1.1 DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps Effort: Max Configuration: Mercor mini-swe-agent, 500 steps, 2 hours 72.3% mercor.com for GPT-6.1 Sol (max) 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 GPT-6.1 Sol on DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps Finance Agent Benchmark 2 — October 2026 evaluation Effort: Max 52.0% vals.ai for GPT-6.1 Sol (max) 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 GPT-6.1 Sol on Finance Agent Benchmark 2 — October 2026 evaluation GDP.pdf Effort: Low 27.0% openai.com for GPT-6.1 Sol (low) on GDP.pdf GDP.pdf (opens in a new tab) GDP.pdf All Pass Rate Reported September 29, 2026 Launch post OpenAI Self-reported Record for GPT-6.1 Sol on GDP.pdf GDP.pdf GDP.pdf Effort: Medium 30.0% openai.com for GPT-6.1 Sol (medium) on GDP.pdf GDP.pdf (opens in a new tab) GDP.pdf All Pass Rate Reported September 29, 2026 Launch post OpenAI Self-reported Record for GPT-6.1 Sol on GDP.pdf GDP.pdf GDP.pdf Effort: High 32.0% openai.com for GPT-6.1 Sol (high) on GDP.pdf GDP.pdf (opens in a new tab) GDP.pdf All Pass Rate Reported September 29, 2026 Launch post OpenAI Self-reported Record for GPT-6.1 Sol on GDP.pdf GDP.pdf GDP.pdf Effort: xHigh 31.8% openai.com for GPT-6.1 Sol (xhigh) on GDP.pdf GDP.pdf (opens in a new tab) GDP.pdf All Pass Rate Reported September 29, 2026 Launch post OpenAI Self-reported Record for GPT-6.1 Sol on GDP.pdf GDP.pdf GDP.pdf Effort: Max 31.0% openai.com for GPT-6.1 Sol (max) on GDP.pdf GDP.pdf (opens in a new tab) GDP.pdf All Pass Rate Reported September 29, 2026 Launch post OpenAI Self-reported Record for GPT-6.1 Sol on GDP.pdf GDP.pdf GPQA Diamond — Epoch AI harness Effort: Max Configuration: Epoch AI harness 95.4% epoch.ai for GPT-6.1 Sol (max) 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 September 29, 2026 at 10:00 PM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-6.1 Sol on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 95.1% mercor.com for GPT-6.1 Sol (max) 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 GPT-6.1 Sol on Graduate-Level Google-Proof Q&A Diamond — Mercor single-shot HLAB October 2026 evaluation Effort: Max 5.4% vals.ai for GPT-6.1 Sol (max) 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 GPT-6.1 Sol on Harvey's Legal Agent Benchmark October 2026 evaluation MedXpertQA MM — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 85.7% mercor.com for GPT-6.1 Sol (max) 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 GPT-6.1 Sol on MedXpertQA MM — Mercor single-shot MMLU-Pro Original — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 91.0% mercor.com for GPT-6.1 Sol (max) 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 GPT-6.1 Sol on MMLU-Pro Original — Mercor single-shot MMMU-Pro 1,730 questions — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 85.8% mercor.com for GPT-6.1 Sol (max) 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 GPT-6.1 Sol on MMMU-Pro 1,730 questions — Mercor single-shot OSWorld 2.0 v2026.08.08 Offline — Partial Effort: Low 59.0% openai.com for GPT-6.1 Sol (low) on OSWorld 2.0 v2026.08.08 Offline — Partial (opens in a new tab) OSWorld Partial Score Reported September 29, 2026 Launch post OpenAI Self-reported Record for GPT-6.1 Sol on OSWorld 2.0 v2026.08.08 Offline — Partial OSWorld 2.0 v2026.08.08 Offline — Partial Effort: Medium 66.8% openai.com for GPT-6.1 Sol (medium) on OSWorld 2.0 v2026.08.08 Offline — Partial (opens in a new tab) OSWorld Partial Score Reported September 29, 2026 Launch post OpenAI Self-reported Record for GPT-6.1 Sol on OSWorld 2.0 v2026.08.08 Offline — Partial OSWorld 2.0 v2026.08.08 Offline — Partial Effort: High 69.6% openai.com for GPT-6.1 Sol (high) on OSWorld 2.0 v2026.08.08 Offline — Partial (opens in a new tab) OSWorld Partial Score Reported September 29, 2026 Launch post OpenAI Self-reported Record for GPT-6.1 Sol on OSWorld 2.0 v2026.08.08 Offline — Partial OSWorld 2.0 v2026.08.08 Offline — Partial Effort: xHigh 69.4% openai.com for GPT-6.1 Sol (xhigh) on OSWorld 2.0 v2026.08.08 Offline — Partial (opens in a new tab) OSWorld Partial Score Reported September 29, 2026 Launch post OpenAI Self-reported Record for GPT-6.1 Sol on OSWorld 2.0 v2026.08.08 Offline — Partial OSWorld 2.0 v2026.08.08 Offline — Partial Effort: Max 71.4% openai.com for GPT-6.1 Sol (max) on OSWorld 2.0 v2026.08.08 Offline — Partial (opens in a new tab) OSWorld Partial Score Reported September 29, 2026 Launch post OpenAI Self-reported Record for GPT-6.1 Sol on OSWorld 2.0 v2026.08.08 Offline — Partial Phage–plasmid Co-evolution Original 12.946 deploymentsafety.openai.com for GPT-6.1 Sol on Phage–plasmid Co-evolution Original (opens in a new tab) Negative log-likelihood Reported September 29, 2026 System card addendum OpenAI Self-reported Record for GPT-6.1 Sol on Phage–plasmid Co-evolution Original PostTrainBench 1.2 — Codex CLI Effort: Max Configuration: Codex harness 38.8% posttrainbench.com for GPT-6.1 Sol (Max) on PostTrainBench 1.2 — Codex CLI (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 GPT-6.1 Sol on PostTrainBench 1.2 — Codex CLI SHP2 Protein Function Prediction Original 0.332 deploymentsafety.openai.com for GPT-6.1 Sol on SHP2 Protein Function Prediction Original (opens in a new tab) Mean R² across three assay datasets Reported September 29, 2026 System card addendum OpenAI Self-reported Record for GPT-6.1 Sol on SHP2 Protein Function Prediction Original SimpleQA Verified Original — Epoch AI harness Effort: Max Configuration: Epoch AI harness 73.9% epoch.ai for GPT-6.1 Sol (max) 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 September 29, 2026 at 10:00 PM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-6.1 Sol on SimpleQA Verified Original — Epoch AI harness SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps Effort: Max Configuration: Mercor mini-swe-agent, 250 steps, 1 hour 48.4% mercor.com for GPT-6.1 Sol (max) 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 GPT-6.1 Sol on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps SWE-bench Multilingual — Mercor mini-swe-agent, 1000 steps Effort: Max Configuration: Mercor mini-swe-agent, 1000 steps, 3 hours 84.9% mercor.com for GPT-6.1 Sol (max) 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 GPT-6.1 Sol on SWE-bench Multilingual — Mercor mini-swe-agent, 1000 steps SWE-bench Verified — Mercor mini-swe-agent, 1000 steps Effort: Max Configuration: Mercor mini-swe-agent, 1000 steps, 3 hours 87.3% mercor.com for GPT-6.1 Sol (max) 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 GPT-6.1 Sol on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps Terminal-Bench 4.0 — Codex Effort: Max Configuration: Codex harness 58.2% tbench.ai for GPT-6.1 Sol (max) on Terminal-Bench 4.0 — Codex (opens in a new tab) Archived copy (opens in a new tab) Terminal-Bench Accuracy Reported September 29, 2026 Benchmark leaderboard Terminal-Bench Independent Terminal-Bench Team Record for GPT-6.1 Sol on Terminal-Bench 4.0 — Codex Terminal-Bench 4.0 — Mercor mini-swe-agent Effort: Max Configuration: Mercor mini-swe-agent, 1000 steps, 8 hours 59.6% mercor.com for GPT-6.1 Sol (max) on Terminal-Bench 4.0 — Mercor mini-swe-agent (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 GPT-6.1 Sol on Terminal-Bench 4.0 — Mercor mini-swe-agent Terminal-Bench 4.0 — Vals AI mini-swe-agent Effort: Max Configuration: mini-swe-agent harness 55.1% vals.ai for GPT-6.1 Sol (max) 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 GPT-6.1 Sol on Terminal-Bench 4.0 — Vals AI mini-swe-agent Terminal-Bench Science 0.1 Effort: Low 43.7% openai.com for GPT-6.1 Sol (low) on Terminal-Bench Science 0.1 (opens in a new tab) Terminal-Bench Accuracy Reported September 29, 2026 Launch post OpenAI Self-reported Record for GPT-6.1 Sol on Terminal-Bench Science 0.1 Terminal-Bench Science 0.1 Effort: Medium 47.6% openai.com for GPT-6.1 Sol (medium) on Terminal-Bench Science 0.1 (opens in a new tab) Terminal-Bench Accuracy Reported September 29, 2026 Launch post OpenAI Self-reported Record for GPT-6.1 Sol on Terminal-Bench Science 0.1 Terminal-Bench Science 0.1 Effort: High 51.1% openai.com for GPT-6.1 Sol (high) on Terminal-Bench Science 0.1 (opens in a new tab) Terminal-Bench Accuracy Reported September 29, 2026 Launch post OpenAI Self-reported Record for GPT-6.1 Sol on Terminal-Bench Science 0.1 Terminal-Bench Science 0.1 Effort: xHigh 53.7% openai.com for GPT-6.1 Sol (xhigh) on Terminal-Bench Science 0.1 (opens in a new tab) Terminal-Bench Accuracy Reported September 29, 2026 Launch post OpenAI Self-reported Record for GPT-6.1 Sol on Terminal-Bench Science 0.1 Terminal-Bench Science 0.1 Effort: Max 57.0% openai.com for GPT-6.1 Sol (max) on Terminal-Bench Science 0.1 (opens in a new tab) Terminal-Bench Accuracy Reported September 29, 2026 Launch post OpenAI Self-reported Record for GPT-6.1 Sol on Terminal-Bench Science 0.1 Vals Index 2.1 Effort: Max 61.2% vals.ai for GPT-6.1 Sol (max) 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 GPT-6.1 Sol on Vals Index 2.1 Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation Effort: Max Configuration: OpenHands harness 88.9% vals.ai for GPT-6.1 Sol (max) 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 GPT-6.1 Sol on Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation