GPT-6.2 Sol vs Qwen4-Max
GPT-6.2 Sol leads by 3.3 capability points (≈95% interval +0.6 to +5.9): a clear lead over Qwen4-Max · P(higher) ≈ 99%
Wins 38 of 53 shared benchmarks (15 lost)
Capability vs. relative cost
GPT-6.2 SolQwen4-MaxClosed weightsOpen weights
Benchmark wins38 – 15 · 53 shared
Comparing matching setups only (3 benchmarks excluded) · suites counted once
Area← GPT-6.2 SolQwen4-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-6.2 Sol.
| KradleBench | Games | 67.9 | 11.0 | −56.9 |
| Terminal-Bench-Science 0.1 | Science › Multidisciplinary | 66.7 | 23.3 | −43.3 |
| EnterpriseBench: CoreCraft | Tool & computer use › Customer service & operations | 36.4 | 68.7 | +32.3 |
| Code Migration v1.1 (Vals Index v2.2 subset) | Software › Software engineering | 85.3 | 57.3 | −28.1 |
| EnterpriseOps-Gym-AA | Tool & computer use › Customer service & operations | 26.3 | 48.5 | +22.2 |
| sudo L7 (October 2026 rescoring) | Software › Software engineering | 36.1 | 15.6 | −20.5 |
| Humanity's Last Exam Diamond | Knowledge & reasoning › General knowledge | 64.0 | 44.9 | −19.1 |
| Medical Long Context Reasoning (MLCR-AA, October 2026 methodology) | Health & medicine | 37.2 | 19.4 | −17.8 |
| FrontierCode 2.0 (Artificial Analysis) | Software › Software engineering | 42.8 | 26.5 | −16.3 |
| DAYJOB: Law (November 2026 release) | Professional › Legal | 32.7 | 17.5 | −15.2 |
| Artificial Analysis Intelligence Index v5.0.1 | Composite indexes | 57.3 | 42.9 | −14.4 |
| Chartography (November 2026 rescoring) | Perception & media › Documents & charts | 87.7 | 75.3 | −12.4 |
| CritPt v2 (agentic, avg@5) | Science › Physical sciences | 78.3 | 66.0 | −12.3 |
| Terminal-Bench 4.0 | Software › Software engineering | 60.6 | 48.5 | −12.1 |
| Artificial Analysis Engineering Index | Science › Engineering | 61.2 | 50.1 | −11.1 |
| ComplexConstraints (November 2026 rescoring) | Language & writing › Instruction following | 69.5 | 59.1 | −10.4 |
| HLAB-Vals-1.1 | Professional › Legal | 12.1 | 21.3 | +9.2 |
| LMArena Agent Arena Net Improvement (Steering Burden) | Tool & computer use › General agents | 11.3 | 7.3 | −7.9 |
| Finance Agent v2.1 | Professional › Finance, accounting & tax | 58.9 | 66.7 | +7.8 |
| Terminal-Bench 4.0 (Artificial Analysis) | Software › Software engineering | 56.1 | 48.5 | −7.6 |
| AA-AnalystAgent (pass^5) | Professional › General knowledge work | 53.8 | 46.3 | −7.5 |
| FrontierCUA v1 pass@1 | Tool & computer use › Computer & browser use | 25.0 | 17.5 | −7.5 |
| DAYJOB: Finance (October 2026 rescoring) | Professional › Finance, accounting & tax | 32.8 | 25.3 | −7.5 |
| LiveBench 2.0 (2026-11-06 release) | Composite indexes | 80.3 | 73.1 | −7.2 |
| DAYJOB: Healthcare (October 2026 rescoring) | Health & medicine | 17.2 | 24.4 | +7.2 |
| Tax Agent Bench | Professional › Finance, accounting & tax | 62.9 | 70.0 | +7.1 |
| AA-Omniscience v1.1 Index | Knowledge & reasoning › General knowledge | 40.4 | 27.7 | −6.3 |
| Artificial Analysis Economics Index | Composite indexes | 57.4 | 51.3 | −6.0 |
| AA-Briefcase v1.1 Elo | Professional › General knowledge work | 1580 | 1686 | +5.8 |
| Artificial Analysis Legal Index | Professional › Legal | 55.0 | 49.6 | −5.5 |
| Vals Finance Index | Professional › Finance, accounting & tax | 56.7 | 62.0 | +5.3 |
| DAYJOB: Accounting | Professional › Finance, accounting & tax | 27.6 | 22.4 | −5.2 |
| GDP.pdf (November 2026 rescoring) | Professional › General knowledge work | 48.8 | 43.6 | −5.2 |
| LMArena Agent Arena Praise vs Complaint | Tool & computer use › General agents | 23.3 | 13.0 | −5.1 |
| Artificial Analysis Healthcare & Medical Index | Health & medicine | 53.3 | 48.2 | −5.1 |
| Agents' Last Exam v1.1 (ALE v1.1) | Professional › General knowledge work | 41.8 | 46.7 | +4.9 |
| HANDBOOK.md Agents v1.1 | Tool & computer use › Customer service & operations | 34.5 | 39.4 | +4.9 |
| Legal Research Bench | Professional › Legal | 37.0 | 41.3 | +4.3 |
| Vals Legal Index | Professional › Legal | 66.7 | 70.7 | +4.0 |
| DAYJOB: Tax | Professional › Finance, accounting & tax | 4.8 | 8.8 | +4.0 |
| GDP.pdf (Artificial Analysis, All-pass) | Professional › General knowledge work | 30.0 | 26.2 | −3.8 |
| Excel Modeling Benchmark v1.1 | Professional › Finance, accounting & tax | 74.3 | 70.8 | −3.5 |
| Artificial Analysis Finance & Accounting Index | Professional › Finance, accounting & tax | 57.2 | 54.1 | −3.1 |
| Vals Index v2.2 | Composite indexes | 66.1 | 63.2 | −2.9 |
| LMArena Agent Arena Steering Burden | Tool & computer use › General agents | 13.4 | 8.0 | −2.7 |
| Artificial Analysis Strategy & Ops Index | Professional › General knowledge work | 59.4 | 56.9 | −2.6 |
| GDP.xlsx | Professional › General knowledge work | 22.3 | 23.7 | +1.4 |
| AutomationBench-AA 1.0.6 | Tool & computer use › Customer service & operations | 71.3 | 72.6 | +1.3 |
| LMArena Agent Arena Confirmed Success | Tool & computer use › General agents | 10.9 | 8.8 | −1.0 |
| DualEntry Accounting AI Benchmark | Professional › Finance, accounting & tax | 84.2 | 83.2 | −1.0 |
| Vibe Code Bench v1.1 | Software › Frontend & design | 87.6 | 86.7 | −1.0 |
| LMArena Agent Arena Bash Reliability | Tool & computer use › General agents | 4.3 | 3.4 | −0.5 |
| 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