APEX-Agents Original Effort: xHigh 52.4% mercor.com for GPT-5.4 (xhigh) 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-5.4 on APEX-Agents Original AutomationBench 1.0.6 Effort: Low 1.5% zapier.com for GPT-5.4 (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 GPT-5.4 on AutomationBench 1.0.6 AutomationBench 1.0.6 Effort: Medium 5.3% zapier.com for GPT-5.4 (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 GPT-5.4 on AutomationBench 1.0.6 AutomationBench 1.0.6 Effort: High 10.1% zapier.com for GPT-5.4 (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 GPT-5.4 on AutomationBench 1.0.6 AutomationBench 1.0.6 Effort: xHigh 11.6% zapier.com for GPT-5.4 (xhigh) 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-5.4 on AutomationBench 1.0.6 AutomationBench 1.0.6 0.2% zapier.com for GPT-5.4 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-5.4 on AutomationBench 1.0.6 BrowseComp 130-question subset — Mercor web research agent Effort: xHigh Configuration: Mercor web research agent, 100 steps, 3 hours 73.3% mercor.com for GPT-5.4 (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-5.4 on BrowseComp 130-question subset — Mercor web research agent BrowseComp Effort: xHigh 82.7% openai.com for GPT-5.4 (xhigh) on BrowseComp BrowseComp (opens in a new tab) BrowseComp Accuracy Reported March 5, 2026 Launch post OpenAI Self-reported Record for GPT-5.4 on BrowseComp BrowseComp Chartography October 2026 leaderboard Effort: xHigh 29.6% surgehq.ai for GPT-5.4 (xHigh) 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-5.4 on Chartography October 2026 leaderboard CharXiv Descriptive and reasoning — Mercor single-shot Effort: xHigh Configuration: Mercor single-shot agent 93.4% mercor.com for GPT-5.4 (xhigh) 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-5.4 on CharXiv Descriptive and reasoning — Mercor single-shot DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps Effort: xHigh Configuration: Mercor mini-swe-agent, 500 steps, 2 hours 49.0% mercor.com for GPT-5.4 (xhigh) 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-5.4 on DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps GDPval Effort: xHigh 83.0% openai.com for GPT-5.4 (xhigh) on GDPval GDPval (opens in a new tab) Wins or ties Reported March 5, 2026 Launch post OpenAI Self-reported Record for GPT-5.4 on GDPval GDPval GPQA Diamond Effort: xHigh 92.8% openai.com for GPT-5.4 (xhigh) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) GPQA Diamond Accuracy Reported March 5, 2026 Launch post OpenAI Self-reported Record for GPT-5.4 on Graduate-Level Google-Proof Q&A Diamond GPQA Diamond — Epoch AI harness Effort: None Configuration: Epoch AI harness 74.7% epoch.ai for GPT-5.4 (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 July 15, 2026 at 3:14 AM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-5.4 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Epoch AI harness Effort: Low Configuration: Epoch AI harness 84.8% epoch.ai for GPT-5.4 (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 July 15, 2026 at 3:14 AM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-5.4 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Epoch AI harness Effort: Medium Configuration: Epoch AI harness 88.9% epoch.ai for GPT-5.4 (medium) 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 15, 2026 at 3:14 AM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-5.4 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Epoch AI harness Effort: High Configuration: Epoch AI harness 89.9% epoch.ai for GPT-5.4 (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 July 15, 2026 at 3:14 AM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-5.4 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Epoch AI harness Effort: xHigh Configuration: Epoch AI harness 93.3% epoch.ai for GPT-5.4 (xhigh) 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 6, 2026 at 2:57 AM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-5.4 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Mercor single-shot Effort: xHigh Configuration: Mercor single-shot agent 93.2% mercor.com for GPT-5.4 (xhigh) 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-5.4 on Graduate-Level Google-Proof Q&A Diamond — Mercor single-shot GPQA Diamond — Vals AI harness Effort: xHigh Configuration: Vals AI harness: mean of zero-shot and few-shot CoT 91.7% vals.ai for GPT-5.4 (xhigh) 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-5.4 on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness HLAB October 2026 evaluation Effort: xHigh 0.0% vals.ai for GPT-5.4 (xhigh) 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-5.4 on Harvey's Legal Agent Benchmark October 2026 evaluation Humanity's Last Exam Full set — No tools Effort: xHigh Configuration: No tools 39.8% openai.com for GPT-5.4 (xhigh) on Humanity's Last Exam Full set — No tools (opens in a new tab) Humanity's Last Exam Accuracy Reported March 5, 2026 Launch post OpenAI Self-reported Record for GPT-5.4 on Humanity's Last Exam Full set — No tools Humanity's Last Exam Full set — Scale AI evaluation Effort: xHigh Reported as: xhigh thinking 36.2% labs.scale.com for GPT-5.4 (xhigh thinking) 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 GPT-5.4 on Humanity's Last Exam Full set — Scale AI evaluation Humanity's Last Exam Full set — With tools Effort: xHigh Configuration: With tools 52.1% openai.com for GPT-5.4 (xhigh) on Humanity's Last Exam Full set — With tools (opens in a new tab) Humanity's Last Exam Accuracy Reported March 5, 2026 Launch post OpenAI Self-reported Record for GPT-5.4 on Humanity's Last Exam Full set — With tools Humanity's Last Exam Text only — Mercor single-shot Effort: xHigh Configuration: Mercor single-shot agent 44.1% mercor.com for GPT-5.4 (xhigh) 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-5.4 on Humanity's Last Exam Text only — Mercor single-shot Humanity's Last Exam Text only — Scale AI evaluation Effort: xHigh Reported as: xhigh thinking 36.5% labs.scale.com for GPT-5.4 (xhigh thinking) 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 GPT-5.4 on Humanity's Last Exam Text only — Scale AI evaluation MCP Atlas Public, April 2026 update Effort: xHigh 70.6% labs.scale.com for GPT-5.4 (xhigh) 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-5.4 on MCP Atlas Public, April 2026 update MedXpertQA MM — Mercor single-shot Effort: xHigh Configuration: Mercor single-shot agent 74.2% mercor.com for GPT-5.4 (xhigh) 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-5.4 on MedXpertQA MM — Mercor single-shot MMLU-Pro Original — Mercor single-shot Effort: xHigh Configuration: Mercor single-shot agent 88.2% mercor.com for GPT-5.4 (xhigh) 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-5.4 on MMLU-Pro Original — Mercor single-shot MMLU-Pro Original — Vals AI harness Effort: xHigh Configuration: Vals AI harness 87.5% vals.ai for GPT-5.4 (xhigh) 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-5.4 on MMLU-Pro Original — Vals AI harness MMMU-Pro 1,730 questions — Mercor single-shot Effort: xHigh Configuration: Mercor single-shot agent 80.8% mercor.com for GPT-5.4 (xhigh) 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-5.4 on MMMU-Pro 1,730 questions — Mercor single-shot MMMU-Pro No tools Effort: xHigh Configuration: No tools 81.2% openai.com for GPT-5.4 (xhigh) on MMMU-Pro No tools (opens in a new tab) MMMU-Pro accuracy Setting: Not stated Reported March 5, 2026 Launch post OpenAI Self-reported Record for GPT-5.4 on MMMU-Pro No tools MMMU-Pro Vals AI harness Effort: xHigh Configuration: Vals AI harness 87.5% vals.ai for GPT-5.4 (xhigh) 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-5.4 on MMMU-Pro Vals AI harness MMMU-Pro With tools Effort: xHigh Configuration: With tools 82.1% openai.com for GPT-5.4 (xhigh) on MMMU-Pro With tools (opens in a new tab) MMMU-Pro accuracy Setting: Not stated Reported March 5, 2026 Launch post OpenAI Self-reported Record for GPT-5.4 on MMMU-Pro With tools OSWorld Verified Effort: xHigh 75.0% openai.com for GPT-5.4 (xhigh) on OSWorld Verified (opens in a new tab) OSWorld-Verified success rate Reported March 5, 2026 Launch post OpenAI Self-reported Record for GPT-5.4 on OSWorld Verified PostTrainBench 1.1 — Codex CLI Effort: High Configuration: Codex harness 19.0% posttrainbench.com for GPT-5.4 (High) 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-5.4 on PostTrainBench 1.1 — Codex CLI PostTrainBench 1.2 — Codex CLI Effort: High Configuration: Codex harness 17.8% posttrainbench.com for GPT-5.4 (High) 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-5.4 on PostTrainBench 1.2 — Codex CLI Riemann-bench October 2026 leaderboard Effort: xHigh 41.6% surgehq.ai for GPT-5.4 (xHigh) 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-5.4 on Riemann-bench October 2026 leaderboard SimpleQA Verified Original — Epoch AI harness Effort: xHigh Configuration: Epoch AI harness 45.1% epoch.ai for GPT-5.4 (xhigh) 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 27, 2026 at 7:28 PM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-5.4 on SimpleQA Verified Original — Epoch AI harness SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps Effort: xHigh Configuration: Mercor mini-swe-agent, 250 steps, 1 hour 37.1% mercor.com for GPT-5.4 (xhigh) 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-5.4 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps SWE Atlas Codebase QnA — Public; Codex Effort: xHigh Configuration: Codex harness 40.8% labs.scale.com for GPT-5.4 (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-5.4 on SWE Atlas Codebase QnA — Public; Codex SWE Atlas Codebase QnA — Public; mini-swe-agent Effort: xHigh Configuration: mini-swe-agent harness 36.3% labs.scale.com for GPT-5.4 (xHigh) 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 GPT-5.4 on SWE Atlas Codebase QnA — Public; mini-swe-agent SWE Atlas Refactoring — Codex Effort: xHigh Configuration: Codex harness 44.3% labs.scale.com for GPT-5.4 (xHigh) on SWE Atlas Refactoring — 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-5.4 on SWE Atlas Refactoring — Codex SWE-bench Multilingual — Mercor mini-swe-agent, 1000 steps Effort: xHigh Configuration: Mercor mini-swe-agent, 1000 steps, 3 hours 77.0% mercor.com for GPT-5.4 (xhigh) 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-5.4 on SWE-bench Multilingual — Mercor mini-swe-agent, 1000 steps SWE-bench Verified — Epoch AI harness Effort: High Configuration: Epoch AI harness 76.9% epoch.ai for GPT-5.4 (high) on SWE-bench Verified — Epoch AI harness (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Evaluated March 6, 2026 at 11:07 AM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-5.4 on SWE-bench Verified — Epoch AI harness SWE-bench Verified — Mercor mini-swe-agent, 1000 steps Effort: xHigh Configuration: Mercor mini-swe-agent, 1000 steps, 3 hours 78.1% mercor.com for GPT-5.4 (xhigh) 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-5.4 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps SWE-bench Verified — Vals AI mini-swe-agent Effort: xHigh Configuration: mini-swe-agent harness 78.2% vals.ai for GPT-5.4 (xhigh) 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-5.4 on SWE-bench Verified — Vals AI mini-swe-agent SWE-bench Pro Private — Scale AI mini-swe-agent Effort: xHigh Configuration: mini-swe-agent harness 43.4% labs.scale.com for GPT-5.4 (xHigh) 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 GPT-5.4 on SWE-bench Pro Private — Scale AI mini-swe-agent SWE-bench Pro Public Effort: xHigh 57.7% openai.com for GPT-5.4 (xhigh) on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported March 5, 2026 Launch post OpenAI Self-reported Record for GPT-5.4 on SWE-bench Pro Public SWE-bench Pro Public — Scale AI mini-swe-agent Effort: xHigh Configuration: mini-swe-agent harness 59.1% labs.scale.com for GPT-5.4 (xHigh) 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 GPT-5.4 on SWE-bench Pro Public — Scale AI mini-swe-agent