GPT-6 Astra vs Qwen4-Max
GPT-6 Astra leads by 3.4 capability points (≈95% interval +0.8 to +6.1): a clear lead over Qwen4-Max · P(higher) ≈ 99%
Wins 29 of 45 shared benchmarks (16 lost)
Capability vs. relative cost
GPT-6 AstraQwen4-MaxClosed weightsOpen weights
Benchmark wins29 – 16 · 45 shared
Comparing matching setups only (5 benchmarks excluded) · suites counted once
Area← GPT-6 AstraQwen4-Max →
Data: Artificial Analysis, Surge AI, Vals AI and 6 othersatlas.village.dev
Margins
Each benchmark scaled 0–100% (its declared range, else the field’s range); Δ is Qwen4-Max minus GPT-6 Astra.
| Terminal-Bench-Science 0.1 | Science › Multidisciplinary | 54.8 | 23.3 | −31.4 |
| EnterpriseBench: CoreCraft | Tool & computer use › Customer service & operations | 42.6 | 68.7 | +26.1 |
| Medical Long Context Reasoning (MLCR-AA, October 2026 methodology) | Health & medicine | 41.7 | 19.4 | −22.2 |
| Code Migration v1.1 (Vals Index v2.2 subset) | Software › Software engineering | 78.0 | 57.3 | −20.8 |
| DAYJOB: Law (November 2026 release) | Professional › Legal | 36.6 | 17.5 | −19.1 |
| Humanity's Last Exam Diamond | Knowledge & reasoning › General knowledge | 63.8 | 44.9 | −18.9 |
| CritPt v2 (agentic, avg@5) | Science › Physical sciences | 83.4 | 66.0 | −17.4 |
| sudo L7 (October 2026 rescoring) | Software › Software engineering | 31.1 | 15.6 | −15.5 |
| FrontierCode 2.0 (Artificial Analysis) | Software › Software engineering | 41.4 | 26.5 | −14.9 |
| LMArena Agent Arena Net Improvement (Steering Burden) | Tool & computer use › General agents | 14.6 | 7.3 | −14.2 |
| HLAB-Vals-1.1 | Professional › Legal | 7.1 | 21.3 | +14.2 |
| Artificial Analysis Intelligence Index v5.0.1 | Composite indexes | 56.9 | 42.9 | −14.0 |
| Chartography (November 2026 rescoring) | Perception & media › Documents & charts | 88.6 | 75.3 | −13.3 |
| DAYJOB: Finance (October 2026 rescoring) | Professional › Finance, accounting & tax | 37.3 | 25.3 | −12.0 |
| ComplexConstraints (November 2026 rescoring) | Language & writing › Instruction following | 70.8 | 59.1 | −11.7 |
| LiveBench 2.0 (2026-11-06 release) | Composite indexes | 84.3 | 73.1 | −11.2 |
| Terminal-Bench 4.0 (Artificial Analysis) | Software › Software engineering | 59.6 | 48.5 | −11.1 |
| Terminal-Bench 4.0 | Software › Software engineering | 59.6 | 48.5 | −11.1 |
| GDPval-AA v2.1 | Professional › General knowledge work | 1572 | 1809 | +10.4 |
| LLM Debate Benchmark | Language & writing › Language & wordplay | 1607 | 1679 | +10.3 |
| LMArena Agent Arena Praise vs Complaint | Tool & computer use › General agents | 32.3 | 13.0 | −9.6 |
| AA-Omniscience v1.1 Index | Knowledge & reasoning › General knowledge | 44.6 | 27.7 | −8.4 |
| HANDBOOK.md Agents v1.1 | Tool & computer use › Customer service & operations | 31.4 | 39.4 | +8.0 |
| AA-Briefcase v1.1 Elo | Professional › General knowledge work | 1544 | 1686 | +7.8 |
| DAYJOB: Accounting | Professional › Finance, accounting & tax | 30.0 | 22.4 | −7.6 |
| GDP.pdf (November 2026 rescoring) | Professional › General knowledge work | 50.4 | 43.6 | −6.8 |
| Tax Agent Bench | Professional › Finance, accounting & tax | 63.3 | 70.0 | +6.7 |
| Agents' Last Exam v1.1 (ALE v1.1) | Professional › General knowledge work | 40.2 | 46.7 | +6.6 |
| Vals Finance Index | Professional › Finance, accounting & tax | 55.6 | 62.0 | +6.4 |
| Finance Agent v2.1 | Professional › Finance, accounting & tax | 60.4 | 66.7 | +6.3 |
| GDP.pdf (Artificial Analysis, All-pass) | Professional › General knowledge work | 32.2 | 26.2 | −6.0 |
| AA-AnalystAgent (pass^5) | Professional › General knowledge work | 51.3 | 46.3 | −5.0 |
| AutomationBench-AA 1.0.6 | Tool & computer use › Customer service & operations | 68.5 | 72.6 | +4.1 |
| DAYJOB: Tax | Professional › Finance, accounting & tax | 4.8 | 8.8 | +4.0 |
| DAYJOB: Healthcare (October 2026 rescoring) | Health & medicine | 28.4 | 24.4 | −4.0 |
| LMArena Agent Arena Confirmed Success | Tool & computer use › General agents | 14.9 | 8.8 | −3.0 |
| LMArena Agent Arena Steering Burden | Tool & computer use › General agents | 13.9 | 8.0 | −3.0 |
| FrontierCUA v1 pass@1 | Tool & computer use › Computer & browser use | 20.0 | 17.5 | −2.5 |
| Vals Legal Index | Professional › Legal | 68.4 | 70.7 | +2.3 |
| DualEntry Accounting AI Benchmark | Professional › Finance, accounting & tax | 81.2 | 83.2 | +2.0 |
| Legal Research Bench | Professional › Legal | 39.4 | 41.3 | +1.9 |
| Excel Modeling Benchmark v1.1 | Professional › Finance, accounting & tax | 72.7 | 70.8 | −1.9 |
| LMArena Agent Arena Bash Reliability | Tool & computer use › General agents | 6.5 | 3.4 | −1.6 |
| GDP.xlsx | Professional › General knowledge work | 22.9 | 23.7 | +0.8 |
| LMArena Agent Arena Tool Hallucination | Tool & computer use › Tool calling | 1.2 | 1.2 | 0.0 |
Data: Artificial Analysis, Surge AI, Vals AI and 6 othersatlas.village.dev