APEX-Agents Original Effort: Max 64.7% mercor.com for GPT-6 Astra (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 Astra on APEX-Agents Original AutomationBench 1.0.6 Effort: None 25.3% zapier.com for GPT-6 Astra (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 Astra on AutomationBench 1.0.6 AutomationBench 1.0.6 Effort: Low 30.3% openai.com for GPT-6 Astra (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 Astra on AutomationBench 1.0.6 AutomationBench 1.0.6 Effort: Medium 34.1% openai.com for GPT-6 Astra (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 Astra on AutomationBench 1.0.6 AutomationBench 1.0.6 Effort: High 37.1% openai.com for GPT-6 Astra (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 Astra on AutomationBench 1.0.6 AutomationBench 1.0.6 Effort: xHigh 39.0% openai.com for GPT-6 Astra (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 Astra on AutomationBench 1.0.6 AutomationBench 1.0.6 Effort: Max 41.4% openai.com for GPT-6 Astra (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 Astra on AutomationBench 1.0.6 BenchCAD Vision2Code — With tools Reported as: with tools Configuration: With tools 95.9% openai.com for GPT-6 Astra (with tools) on BenchCAD Vision2Code — With tools (opens in a new tab) Geometric Overlap Reported September 3, 2026 Launch post OpenAI Self-reported Record for GPT-6 Astra on BenchCAD Vision2Code — With tools BrowseComp 130-question subset — Mercor web research agent Effort: xHigh Configuration: Mercor web research agent, 100 steps, 3 hours 94.2% mercor.com for GPT-6 Astra (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-6 Astra on BrowseComp 130-question subset — Mercor web research agent BrowseComp 91.5% openai.com for GPT-6 Astra on BrowseComp BrowseComp (opens in a new tab) BrowseComp Accuracy Reported September 3, 2026 Launch post OpenAI Self-reported Record for GPT-6 Astra on BrowseComp BrowseComp Chartography October 2026 leaderboard Effort: Max 71.0% surgehq.ai for GPT-6 Astra (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 Astra on Chartography October 2026 leaderboard CharXiv Descriptive and reasoning — Mercor single-shot Effort: xHigh Configuration: Mercor single-shot agent 95.8% mercor.com for GPT-6 Astra (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-6 Astra on CharXiv Descriptive and reasoning — Mercor single-shot CharXiv Descriptive and reasoning — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 96.1% mercor.com for GPT-6 Astra (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 Astra on CharXiv Descriptive and reasoning — Mercor single-shot CWE-bench 1 — Codex Effort: High Configuration: Codex harness 68.0% cwe-bench.com for GPT-6 Astra (high) on CWE-bench 1 — Codex (opens in a new tab) Archived copy (opens in a new tab) CWE-bench Programmatic Pass@1 Reported October 7, 2026 Benchmark leaderboard Collinear AI Independent Record for GPT-6 Astra on CWE-bench 1 — Codex DeepSWE 1.1 Effort: Low 67.0% openai.com for GPT-6 Astra (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 Astra on DeepSWE 1.1 DeepSWE 1.1 Effort: Medium 72.8% openai.com for GPT-6 Astra (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 Astra on DeepSWE 1.1 DeepSWE 1.1 Effort: High 73.2% openai.com for GPT-6 Astra (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 Astra on DeepSWE 1.1 DeepSWE 1.1 Effort: xHigh 74.0% deepswe.datacurve.ai for GPT-6 Astra (xhigh) on DeepSWE 1.1 (opens in a new tab) DeepSWE Pass@1 Reported September 22, 2026 Benchmark leaderboard Datacurve Independent Record for GPT-6 Astra on DeepSWE 1.1 DeepSWE 1.1 Effort: Max 73.2% openai.com for GPT-6 Astra (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 Astra on DeepSWE 1.1 DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps Effort: Max Configuration: Mercor mini-swe-agent, 500 steps, 2 hours 72.0% mercor.com for GPT-6 Astra (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 Astra on DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps Finance Agent Benchmark 2 — October 2026 evaluation Effort: Max 53.5% vals.ai for GPT-6 Astra (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 Astra on Finance Agent Benchmark 2 — October 2026 evaluation FrontierSWE 2 — October 2026 evaluation Configuration: Proximus harness, 5 trials, 20-hour budget 65.5% frontierswe.com for GPT-6 Astra 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-6 Astra on FrontierSWE 2 — October 2026 evaluation GPQA Diamond 96.0% openai.com for GPT-6 Astra on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) GPQA Diamond Accuracy Reported September 3, 2026 Launch post OpenAI Self-reported Record for GPT-6 Astra on Graduate-Level Google-Proof Q&A Diamond GPQA Diamond — Epoch AI harness Effort: Max Configuration: Epoch AI harness 95.8% epoch.ai for GPT-6 Astra (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 August 30, 2026 at 2:57 PM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-6 Astra on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Mercor single-shot Effort: xHigh Configuration: Mercor single-shot agent 96.2% mercor.com for GPT-6 Astra (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-6 Astra on Graduate-Level Google-Proof Q&A Diamond — Mercor single-shot HLAB October 2026 evaluation Effort: Max 5.4% vals.ai for GPT-6 Astra (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 Astra on Harvey's Legal Agent Benchmark October 2026 evaluation Humanity's Last Exam Full set — Scale AI evaluation 54.8% labs.scale.com for GPT-6 Astra 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-6 Astra on Humanity's Last Exam Full set — Scale AI evaluation Humanity's Last Exam Text only — Mercor single-shot Effort: xHigh Configuration: Mercor single-shot agent 55.6% mercor.com for GPT-6 Astra (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-6 Astra on Humanity's Last Exam Text only — Mercor single-shot Humanity's Last Exam Text only — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 52.2% mercor.com for GPT-6 Astra (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 Astra on Humanity's Last Exam Text only — Mercor single-shot Humanity's Last Exam Text only — Scale AI evaluation 54.2% labs.scale.com for GPT-6 Astra 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-6 Astra on Humanity's Last Exam Text only — Scale AI evaluation MedXpertQA MM — Mercor single-shot Effort: xHigh Configuration: Mercor single-shot agent 86.5% mercor.com for GPT-6 Astra (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-6 Astra on MedXpertQA MM — Mercor single-shot MedXpertQA MM — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 86.8% mercor.com for GPT-6 Astra (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 Astra on MedXpertQA MM — Mercor single-shot MMLU-Pro Original — Mercor single-shot Effort: xHigh Configuration: Mercor single-shot agent 91.0% mercor.com for GPT-6 Astra (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-6 Astra on MMLU-Pro Original — Mercor single-shot MMLU-Pro Original — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 91.5% mercor.com for GPT-6 Astra (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 Astra on MMLU-Pro Original — Mercor single-shot MMMU-Pro 1,730 questions — Mercor single-shot Effort: xHigh Configuration: Mercor single-shot agent 86.8% mercor.com for GPT-6 Astra (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-6 Astra on MMMU-Pro 1,730 questions — Mercor single-shot MMMU-Pro 1,730 questions — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 87.5% mercor.com for GPT-6 Astra (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 Astra on MMMU-Pro 1,730 questions — Mercor single-shot OSWorld 2.0 v2026.08.08 Offline — Partial Effort: Low 62.2% openai.com for GPT-6 Astra (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 Astra on OSWorld 2.0 v2026.08.08 Offline — Partial OSWorld 2.0 v2026.08.08 Offline — Partial Effort: Medium 69.3% openai.com for GPT-6 Astra (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 Astra on OSWorld 2.0 v2026.08.08 Offline — Partial OSWorld 2.0 v2026.08.08 Offline — Partial Effort: High 70.0% openai.com for GPT-6 Astra (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 Astra on OSWorld 2.0 v2026.08.08 Offline — Partial OSWorld 2.0 v2026.08.08 Offline — Partial Effort: xHigh 71.3% openai.com for GPT-6 Astra (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 Astra on OSWorld 2.0 v2026.08.08 Offline — Partial OSWorld 2.0 v2026.08.08 Offline — Partial Effort: Max 73.5% openai.com for GPT-6 Astra (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 Astra on OSWorld 2.0 v2026.08.08 Offline — Partial OSWorld 2.0 v2026.08.08 Offline — Partial 72.6% openai.com for GPT-6 Astra on OSWorld 2.0 v2026.08.08 Offline — Partial (opens in a new tab) OSWorld Partial Score Reported September 3, 2026 Launch post OpenAI Self-reported Record for GPT-6 Astra on OSWorld 2.0 v2026.08.08 Offline — Partial PostTrainBench 1.2 — Codex CLI Effort: Max Configuration: Codex harness 41.9% posttrainbench.com for GPT-6 Astra (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 Astra on PostTrainBench 1.2 — Codex CLI Riemann-bench October 2026 leaderboard Effort: Max 72.0% surgehq.ai for GPT-6 Astra (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 Astra on Riemann-bench October 2026 leaderboard SimpleQA Verified Original — Epoch AI harness Effort: Max Configuration: Epoch AI harness 75.6% epoch.ai for GPT-6 Astra (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 30, 2026 at 2:57 PM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-6 Astra 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 48.9% mercor.com for GPT-6 Astra (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-6 Astra on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps Effort: Max Configuration: Mercor mini-swe-agent, 250 steps, 1 hour 47.8% mercor.com for GPT-6 Astra (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 Astra on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps SWE Atlas Codebase QnA — Public; Codex Effort: xHigh Configuration: Codex harness 59.1% labs.scale.com for GPT-6 Astra (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-6 Astra on SWE Atlas Codebase QnA — Public; Codex SWE Atlas Refactoring — Codex Effort: xHigh Configuration: Codex harness 59.1% labs.scale.com for GPT-6 Astra (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-6 Astra on SWE Atlas Refactoring — Codex Terminal-Bench 2.1 — Vals AI Terminus 2 Effort: Max Configuration: Terminus-2 harness 87.3% vals.ai for GPT-6 Astra (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 Astra on Terminal-Bench 2.1 — Vals AI Terminus 2