APEX-Agents Original Effort: Max 44.3% mercor.com for GPT-6 Luna (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 Luna on APEX-Agents Original AutomationBench 1.0.6 Effort: None 0.3% zapier.com for GPT-6 Luna (none) 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-6 Luna on AutomationBench 1.0.6 AutomationBench 1.0.6 Effort: Low 1.2% openai.com for GPT-6 Luna (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-6 Luna on AutomationBench 1.0.6 AutomationBench 1.0.6 Effort: Medium 9.4% openai.com for GPT-6 Luna (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-6 Luna on AutomationBench 1.0.6 AutomationBench 1.0.6 Effort: High 14.5% openai.com for GPT-6 Luna (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-6 Luna on AutomationBench 1.0.6 AutomationBench 1.0.6 Effort: xHigh 12.6% openai.com for GPT-6 Luna (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-6 Luna on AutomationBench 1.0.6 AutomationBench 1.0.6 Effort: Max 20.7% openai.com for GPT-6 Luna (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-6 Luna on AutomationBench 1.0.6 BrowseComp 130-question subset — Mercor web research agent Effort: Max Configuration: Mercor web research agent, 100 steps, 3 hours 83.3% mercor.com for GPT-6 Luna (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 Luna on BrowseComp 130-question subset — Mercor web research agent Chartography October 2026 leaderboard Effort: Max 29.1% surgehq.ai for GPT-6 Luna (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-6 Luna on Chartography October 2026 leaderboard CharXiv Descriptive and reasoning — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 90.9% mercor.com for GPT-6 Luna (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 Luna on CharXiv Descriptive and reasoning — Mercor single-shot DeepSWE 1.1 Effort: Low 2.4% openai.com for GPT-6 Luna (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-6 Luna on DeepSWE 1.1 DeepSWE 1.1 Effort: Medium 44.5% openai.com for GPT-6 Luna (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-6 Luna on DeepSWE 1.1 DeepSWE 1.1 Effort: High 59.3% openai.com for GPT-6 Luna (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-6 Luna on DeepSWE 1.1 DeepSWE 1.1 Effort: xHigh 61.3% openai.com for GPT-6 Luna (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-6 Luna on DeepSWE 1.1 DeepSWE 1.1 Effort: Max 66.6% openai.com for GPT-6 Luna (max) on DeepSWE 1.1 (opens in a new tab) DeepSWE Pass@1 Reported September 22, 2026 Launch post OpenAI Self-reported Record for GPT-6 Luna on DeepSWE 1.1 DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps Effort: Max Configuration: Mercor mini-swe-agent, 500 steps, 2 hours 67.0% mercor.com for GPT-6 Luna (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 Luna on DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps Finance Agent Benchmark 2 — October 2026 evaluation Effort: Max 49.9% vals.ai for GPT-6 Luna (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 Luna on Finance Agent Benchmark 2 — October 2026 evaluation GPQA Diamond — Epoch AI harness Effort: Max Configuration: Epoch AI harness 90.5% epoch.ai for GPT-6 Luna (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 22, 2026 at 10:14 PM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-6 Luna on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 89.9% mercor.com for GPT-6 Luna (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 Luna on Graduate-Level Google-Proof Q&A Diamond — Mercor single-shot HLAB October 2026 evaluation Effort: Max 2.9% vals.ai for GPT-6 Luna (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 Luna 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 38.7% mercor.com for GPT-6 Luna (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-6 Luna on Humanity's Last Exam Text only — Mercor single-shot MedXpertQA MM — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 64.8% mercor.com for GPT-6 Luna (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 Luna on MedXpertQA MM — Mercor single-shot MMLU-Pro Original — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 86.2% mercor.com for GPT-6 Luna (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 Luna on MMLU-Pro Original — Mercor single-shot MMMU-Pro 1,730 questions — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 76.6% mercor.com for GPT-6 Luna (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 Luna on MMMU-Pro 1,730 questions — Mercor single-shot OSWorld 2.0 v2026.08.08 Offline — Partial Effort: Low 8.3% openai.com for GPT-6 Luna (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-6 Luna on OSWorld 2.0 v2026.08.08 Offline — Partial OSWorld 2.0 v2026.08.08 Offline — Partial Effort: Medium 31.5% openai.com for GPT-6 Luna (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-6 Luna on OSWorld 2.0 v2026.08.08 Offline — Partial OSWorld 2.0 v2026.08.08 Offline — Partial Effort: High 41.4% openai.com for GPT-6 Luna (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-6 Luna on OSWorld 2.0 v2026.08.08 Offline — Partial OSWorld 2.0 v2026.08.08 Offline — Partial Effort: xHigh 46.7% openai.com for GPT-6 Luna (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-6 Luna on OSWorld 2.0 v2026.08.08 Offline — Partial OSWorld 2.0 v2026.08.08 Offline — Partial Effort: Max 52.7% openai.com for GPT-6 Luna (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-6 Luna on OSWorld 2.0 v2026.08.08 Offline — Partial Riemann-bench October 2026 leaderboard Effort: Max 59.2% surgehq.ai for GPT-6 Luna (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-6 Luna on Riemann-bench October 2026 leaderboard SimpleQA Verified Original — Epoch AI harness Effort: Max Configuration: Epoch AI harness 41.4% epoch.ai for GPT-6 Luna (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 22, 2026 at 10:14 PM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-6 Luna 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 33.9% mercor.com for GPT-6 Luna (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 Luna 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 78.2% mercor.com for GPT-6 Luna (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 Luna 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 76.1% mercor.com for GPT-6 Luna (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 Luna on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps Terminal-Bench 2.1 — Vals AI Terminus 2 Effort: Max Configuration: Terminus-2 harness 73.0% vals.ai for GPT-6 Luna (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-6 Luna on Terminal-Bench 2.1 — Vals AI Terminus 2 Terminal-Bench 4.0 — Codex Effort: Max Configuration: Codex harness 16.4% tbench.ai for GPT-6 Luna (max) on Terminal-Bench 4.0 — Codex (opens in a new tab) Archived copy (opens in a new tab) Terminal-Bench Accuracy Reported September 22, 2026 Benchmark leaderboard Terminal-Bench Independent Terminal-Bench Team Record for GPT-6 Luna 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 13.5% mercor.com for GPT-6 Luna (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 Luna 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 13.6% vals.ai for GPT-6 Luna (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 Luna on Terminal-Bench 4.0 — Vals AI mini-swe-agent Vals Index 2.1 Effort: Max 51.2% vals.ai for GPT-6 Luna (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 Luna on Vals Index 2.1 Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation Effort: Max Configuration: OpenHands harness 81.6% vals.ai for GPT-6 Luna (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 Luna on Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation