AutomationBench 1.0.6 Effort: Low 11.7% openai.com for GPT-5.6 Sol (low) on AutomationBench 1.0.6 (opens in a new tab) Task pass rate Reported September 22, 2026 Launch post OpenAI Self-reported Record for GPT-5.6 Sol on AutomationBench 1.0.6 AutomationBench 1.0.6 Effort: Medium 19.6% openai.com for GPT-5.6 Sol (medium) on AutomationBench 1.0.6 (opens in a new tab) Task pass rate Reported September 22, 2026 Launch post OpenAI Self-reported Record for GPT-5.6 Sol on AutomationBench 1.0.6 AutomationBench 1.0.6 Effort: High 24.8% openai.com for GPT-5.6 Sol (high) on AutomationBench 1.0.6 (opens in a new tab) Task pass rate Reported September 22, 2026 Launch post OpenAI Self-reported Record for GPT-5.6 Sol on AutomationBench 1.0.6 AutomationBench 1.0.6 Effort: xHigh 26.3% openai.com for GPT-5.6 Sol (xhigh) on AutomationBench 1.0.6 (opens in a new tab) Task pass rate Reported September 22, 2026 Launch post OpenAI Self-reported Record for GPT-5.6 Sol on AutomationBench 1.0.6 AutomationBench 1.0.6 Effort: Max 28.8% openai.com for GPT-5.6 Sol (max) on AutomationBench 1.0.6 (opens in a new tab) Task pass rate Reported September 22, 2026 Launch post OpenAI Self-reported Record for GPT-5.6 Sol on AutomationBench 1.0.6 AutomationBench 1.0.6 3.8% zapier.com for GPT-5.6 Sol 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 GPT-5.6 Sol on AutomationBench 1.0.6 BrowseComp 130-question subset — Mercor web research agent Effort: xHigh Configuration: Mercor web research agent, 100 steps, 3 hours 90.6% mercor.com for GPT-5.6 Sol (xhigh) 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-5.6 Sol on BrowseComp 130-question subset — Mercor web research agent BrowseComp 90.4% openai.com for GPT-5.6 Sol on BrowseComp BrowseComp (opens in a new tab) BrowseComp Accuracy Reported July 9, 2026 Launch post OpenAI Self-reported Record for GPT-5.6 Sol on BrowseComp BrowseComp Chartography October 2026 leaderboard Effort: Max 45.0% surgehq.ai for GPT-5.6 Sol (Max) 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 GPT-5.6 Sol on Chartography October 2026 leaderboard CursorBench 4.0 Effort: Low 24.6% cursor.com for GPT-5.6 Sol (low) on CursorBench 4.0 (opens in a new tab) Archived copy (opens in a new tab) CursorBench Accuracy Reported October 7, 2026 Benchmark leaderboard Cursor Independent Record for GPT-5.6 Sol on CursorBench 4.0 CursorBench 4.0 Effort: Medium 31.1% cursor.com for GPT-5.6 Sol (medium) on CursorBench 4.0 (opens in a new tab) Archived copy (opens in a new tab) CursorBench Accuracy Reported October 7, 2026 Benchmark leaderboard Cursor Independent Record for GPT-5.6 Sol on CursorBench 4.0 CursorBench 4.0 Effort: High 35.7% cursor.com for GPT-5.6 Sol (high) on CursorBench 4.0 (opens in a new tab) Archived copy (opens in a new tab) CursorBench Accuracy Reported October 7, 2026 Benchmark leaderboard Cursor Independent Record for GPT-5.6 Sol on CursorBench 4.0 CursorBench 4.0 Effort: xHigh 37.7% cursor.com for GPT-5.6 Sol (xhigh) on CursorBench 4.0 (opens in a new tab) Archived copy (opens in a new tab) CursorBench Accuracy Reported October 7, 2026 Benchmark leaderboard Cursor Independent Record for GPT-5.6 Sol on CursorBench 4.0 CursorBench 4.0 Effort: Max 41.7% cursor.com for GPT-5.6 Sol (max) on CursorBench 4.0 (opens in a new tab) Archived copy (opens in a new tab) CursorBench Accuracy Reported October 7, 2026 Benchmark leaderboard Cursor Independent Record for GPT-5.6 Sol on CursorBench 4.0 DeepSWE 1.1 Effort: Low 45.4% openai.com for GPT-5.6 Sol (low) on DeepSWE 1.1 (opens in a new tab) DeepSWE Pass@1 Reported September 22, 2026 Launch post OpenAI Self-reported Record for GPT-5.6 Sol on DeepSWE 1.1 DeepSWE 1.1 Effort: Medium 61.1% openai.com for GPT-5.6 Sol (medium) on DeepSWE 1.1 (opens in a new tab) DeepSWE Pass@1 Reported September 22, 2026 Launch post OpenAI Self-reported Record for GPT-5.6 Sol on DeepSWE 1.1 DeepSWE 1.1 Effort: High 69.4% openai.com for GPT-5.6 Sol (high) on DeepSWE 1.1 (opens in a new tab) DeepSWE Pass@1 Reported September 22, 2026 Launch post OpenAI Self-reported Record for GPT-5.6 Sol on DeepSWE 1.1 DeepSWE 1.1 Effort: xHigh 70.7% openai.com for GPT-5.6 Sol (xhigh) on DeepSWE 1.1 (opens in a new tab) DeepSWE Pass@1 Reported September 22, 2026 Launch post OpenAI Self-reported Record for GPT-5.6 Sol on DeepSWE 1.1 DeepSWE 1.1 Effort: Max 73.0% deepswe.datacurve.ai for GPT-5.6 Sol (max) on DeepSWE 1.1 (opens in a new tab) DeepSWE Pass@1 Reported September 22, 2026 Benchmark leaderboard Datacurve Independent Record for GPT-5.6 Sol on DeepSWE 1.1 DeepSWE 1.1 72.7% openai.com for GPT-5.6 Sol on DeepSWE 1.1 (opens in a new tab) DeepSWE Pass@1 Reported July 9, 2026 Launch post OpenAI Self-reported Record for GPT-5.6 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 70.5% mercor.com for GPT-5.6 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-5.6 Sol on DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps Finance Agent Benchmark 2 — October 2026 evaluation Effort: Max 53.8% vals.ai for GPT-5.6 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-5.6 Sol on Finance Agent Benchmark 2 — October 2026 evaluation FrontierSWE 2 — October 2026 evaluation Configuration: Proximus harness, 5 trials, 20-hour budget 32.2% frontierswe.com for GPT-5.6 Sol on FrontierSWE 2 — October 2026 evaluation (opens in a new tab) Archived copy (opens in a new tab) FrontierSWE Score Reported October 7, 2026 Benchmark leaderboard Proximal Independent Record for GPT-5.6 Sol on FrontierSWE 2 — October 2026 evaluation GDP.pdf 30.7% openai.com for GPT-5.6 Sol on GDP.pdf GDP.pdf (opens in a new tab) GDP.pdf All Pass Rate Reported July 9, 2026 Launch post OpenAI Self-reported Record for GPT-5.6 Sol on GDP.pdf GDP.pdf GPQA Diamond 94.6% openai.com for GPT-5.6 Sol on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) GPQA Diamond Accuracy Reported July 9, 2026 Launch post OpenAI Self-reported Record for GPT-5.6 Sol on Graduate-Level Google-Proof Q&A Diamond GPQA Diamond — Epoch AI harness Effort: None Configuration: Epoch AI harness 82.8% epoch.ai for GPT-5.6 Sol (none) 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 7, 2026 at 1:00 AM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-5.6 Sol on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Epoch AI harness Effort: Low Configuration: Epoch AI harness 89.9% epoch.ai for GPT-5.6 Sol (low) 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 7, 2026 at 12:46 AM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-5.6 Sol on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Epoch AI harness Effort: Max Configuration: Epoch AI harness 93.5% epoch.ai for GPT-5.6 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 July 9, 2026 at 2:07 AM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-5.6 Sol on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Vals AI harness Effort: Max Configuration: Vals AI harness: mean of zero-shot and few-shot CoT 95.2% vals.ai for GPT-5.6 Sol (max) 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 GPT-5.6 Sol on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness HLAB October 2026 evaluation Effort: Max 2.5% vals.ai for GPT-5.6 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-5.6 Sol on Harvey's Legal Agent Benchmark October 2026 evaluation Humanity's Last Exam Text only — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 47.0% mercor.com for GPT-5.6 Sol (max) 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 GPT-5.6 Sol on Humanity's Last Exam Text only — Mercor single-shot MCP Atlas Public, April 2026 update Reported as: sol 81.8% labs.scale.com for GPT-5.6 Sol (sol) 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 GPT-5.6 Sol on MCP Atlas Public, April 2026 update MMLU-Pro Original — Vals AI harness Effort: Max Configuration: Vals AI harness 89.1% vals.ai for GPT-5.6 Sol (max) 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 GPT-5.6 Sol on MMLU-Pro Original — Vals AI harness MMMU-Pro 1,730 questions — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 83.6% mercor.com for GPT-5.6 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-5.6 Sol on MMMU-Pro 1,730 questions — Mercor single-shot MMMU-Pro No tools Configuration: No tools 83.0% openai.com for GPT-5.6 Sol on MMMU-Pro No tools (opens in a new tab) MMMU-Pro accuracy Setting: Not stated Reported July 9, 2026 Launch post OpenAI Self-reported Record for GPT-5.6 Sol on MMMU-Pro No tools MMMU-Pro Vals AI harness Effort: Max Configuration: Vals AI harness 88.8% vals.ai for GPT-5.6 Sol (max) 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 GPT-5.6 Sol on MMMU-Pro Vals AI harness MMMU-Pro With tools Configuration: With tools 84.6% openai.com for GPT-5.6 Sol on MMMU-Pro With tools (opens in a new tab) MMMU-Pro accuracy Setting: Not stated Reported July 9, 2026 Launch post OpenAI Self-reported Record for GPT-5.6 Sol on MMMU-Pro With tools OSWorld 2.0 v2026.08.08 Offline — Partial Effort: Low 29.8% openai.com for GPT-5.6 Sol (low) on OSWorld 2.0 v2026.08.08 Offline — Partial (opens in a new tab) OSWorld Partial Score Reported September 22, 2026 Launch post OpenAI Self-reported Record for GPT-5.6 Sol on OSWorld 2.0 v2026.08.08 Offline — Partial OSWorld 2.0 v2026.08.08 Offline — Partial Effort: Medium 49.7% openai.com for GPT-5.6 Sol (medium) on OSWorld 2.0 v2026.08.08 Offline — Partial (opens in a new tab) OSWorld Partial Score Reported September 22, 2026 Launch post OpenAI Self-reported Record for GPT-5.6 Sol on OSWorld 2.0 v2026.08.08 Offline — Partial OSWorld 2.0 v2026.08.08 Offline — Partial Effort: High 56.5% openai.com for GPT-5.6 Sol (high) on OSWorld 2.0 v2026.08.08 Offline — Partial (opens in a new tab) OSWorld Partial Score Reported September 22, 2026 Launch post OpenAI Self-reported Record for GPT-5.6 Sol on OSWorld 2.0 v2026.08.08 Offline — Partial OSWorld 2.0 v2026.08.08 Offline — Partial Effort: xHigh 60.9% openai.com for GPT-5.6 Sol (xhigh) on OSWorld 2.0 v2026.08.08 Offline — Partial (opens in a new tab) OSWorld Partial Score Reported September 22, 2026 Launch post OpenAI Self-reported Record for GPT-5.6 Sol on OSWorld 2.0 v2026.08.08 Offline — Partial OSWorld 2.0 v2026.08.08 Offline — Partial Effort: Max 66.2% openai.com for GPT-5.6 Sol (max) on OSWorld 2.0 v2026.08.08 Offline — Partial (opens in a new tab) OSWorld Partial Score Reported September 22, 2026 Launch post OpenAI Self-reported Record for GPT-5.6 Sol on OSWorld 2.0 v2026.08.08 Offline — Partial PostTrainBench 1.1 — Codex CLI Effort: Max Configuration: Codex harness 36.2% posttrainbench.com for GPT-5.6 Sol (Max) on PostTrainBench 1.1 — 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-5.6 Sol on PostTrainBench 1.1 — Codex CLI PostTrainBench 1.2 — Codex CLI Effort: Max Configuration: Codex harness 31.0% posttrainbench.com for GPT-5.6 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-5.6 Sol on PostTrainBench 1.2 — Codex CLI Riemann-bench October 2026 leaderboard Effort: Max 74.4% surgehq.ai for GPT-5.6 Sol (Max) 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 GPT-5.6 Sol on Riemann-bench October 2026 leaderboard SimpleQA Verified Original — Epoch AI harness Effort: Max Configuration: Epoch AI harness 69.7% epoch.ai for GPT-5.6 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 August 10, 2026 at 11:44 PM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-5.6 Sol on SimpleQA Verified Original — Epoch AI harness SWE Atlas Codebase QnA — Public; Codex Effort: xHigh Configuration: Codex harness 46.0% labs.scale.com for GPT-5.6 Sol (xHigh) on SWE Atlas Codebase QnA — Public; Codex (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 GPT-5.6 Sol on SWE Atlas Codebase QnA — Public; Codex SWE-bench Verified — Vals AI mini-swe-agent Effort: Max Configuration: mini-swe-agent harness 96.2% vals.ai for GPT-5.6 Sol (max) 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 GPT-5.6 Sol on SWE-bench Verified — Vals AI mini-swe-agent Terminal-Bench 2.1 88.8% openai.com for GPT-5.6 Sol on Terminal-Bench 2.1 (opens in a new tab) Terminal-Bench Accuracy Reported July 9, 2026 Launch post OpenAI Self-reported Record for GPT-5.6 Sol on Terminal-Bench 2.1 Terminal-Bench 2.1 — Vals AI Terminus 2 Effort: Max Configuration: Terminus-2 harness 85.8% vals.ai for GPT-5.6 Sol (max) 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 GPT-5.6 Sol on Terminal-Bench 2.1 — Vals AI Terminus 2