Claude Opus 5.5 vs GPT-6.2 Sol
Claude Opus 5.5 leads by 0.7 capability points (≈95% interval −2.1 to +3.4): statistically tied · P(higher) ≈ 68%
Wins 35 of 55 shared benchmarks (18 lost, 2 tied)
Capability vs. relative cost
Claude Opus 5.5GPT-6.2 SolClosed weightsOpen weights
Benchmark wins35 – 18 · 55 shared, 2 tied
Comparing matching setups only (51 benchmarks excluded) · suites counted once
Area← Claude Opus 5.5GPT-6.2 Sol →
Data: Artificial Analysis, Surge AI, Arena and 15 othersatlas.village.dev
Margins
Each benchmark scaled 0–100% (its declared range, else the field’s range); Δ is GPT-6.2 Sol minus Claude Opus 5.5.
| AA-PersonalityBench Informativeness index | Language & writing › Style & personality | 90.5 | 37.7 | −53.3 |
| TxBench Preclinical Pharmacology V1 Clean Reruns | Science › Life sciences | 26.3 | 65.3 | +39.0 |
| EnterpriseBench: CoreCraft | Tool & computer use › Customer service & operations | 74.4 | 36.4 | −38.0 |
| AA-PersonalityBench Expressiveness index | Language & writing › Style & personality | 90.5 | 55.3 | −35.5 |
| AA-PersonalityBench Imagination index | Language & writing › Style & personality | 94.3 | 60.1 | −34.6 |
| AA-PersonalityBench Transparency index | Language & writing › Style & personality | 90.5 | 56.9 | −33.9 |
| AA-PersonalityBench Organization index | Language & writing › Style & personality | 79.1 | 45.7 | −33.7 |
| DAYJOB: Healthcare (October 2026 rescoring) | Health & medicine | 48.3 | 17.2 | −31.1 |
| AA-PersonalityBench Warmth index | Language & writing › Style & personality | 84.8 | 60.1 | −24.9 |
| DeepsecBench — Revalidated V1 (233 issues) | Software › Cybersecurity | 26.6 | 47.3 | +20.8 |
| SimpleBench | Knowledge & reasoning › General knowledge | 88.4 | 69.9 | −18.5 |
| HANDBOOK.md Agents v1.1 | Tool & computer use › Customer service & operations | 52.3 | 34.5 | −17.8 |
| SWE Atlas v1.1 - Overall | Software › Software engineering | 77.5 | 60.5 | −17.0 |
| LMArena Agent Arena Net Improvement (Steering Burden) | Tool & computer use › General agents | 18.6 | 11.3 | −14.3 |
| Humanity's Sixth Sense | Perception & media › Spatial & visual reasoning | 44.6 | 56.8 | +12.2 |
| AA-Briefcase v1.1 Elo | Professional › General knowledge work | 1800 | 1612 | −10.3 |
| sudo L7 (October 2026 rescoring) | Software › Software engineering | 46.1 | 36.1 | −10.0 |
| TaxCalcBench TY25 | Professional › Finance, accounting & tax | 42.0 | 32.0 | −10.0 |
| AA-PersonalityBench Conviction index | Language & writing › Style & personality | 69.5 | 79.2 | +9.8 |
| DAYJOB: Finance (October 2026 rescoring) | Professional › Finance, accounting & tax | 42.5 | 32.8 | −9.7 |
| Medical Long Context Reasoning (MLCR-AA, October 2026 methodology) | Health & medicine | 27.8 | 37.2 | +9.4 |
| Humanity's Last Exam Diamond | Knowledge & reasoning › General knowledge | 54.6 | 64.0 | +9.4 |
| DAYJOB: Law (November 2026 release) | Professional › Legal | 23.7 | 32.7 | +9.0 |
| GDP.xlsx | Professional › General knowledge work | 30.3 | 22.3 | −8.0 |
| AA-3D v1.0 Elo | Software › Frontend & design | 1202 | 1259 | +7.7 |
| LMArena Agent Arena Praise vs Complaint | Tool & computer use › General agents | 38.6 | 23.3 | −7.7 |
| ARC-AGI-2 | Knowledge & reasoning › Abstract reasoning | 93.3 | 85.8 | −7.5 |
| DAYJOB: Accounting | Professional › Finance, accounting & tax | 34.4 | 27.6 | −6.8 |
| Blueprint-Bench 2 | Perception & media › Spatial & visual reasoning | 0.5 | 0.6 | +5.8 |
| ComplexConstraints (November 2026 rescoring) | Language & writing › Instruction following | 64.4 | 69.5 | +5.1 |
| LMArena Agent Arena Bash Reliability | Tool & computer use › General agents | 14.0 | 4.3 | −4.9 |
| Terminal-Bench-Science 0.1 | Science › Multidisciplinary | 61.9 | 66.7 | +4.8 |
| AA-PersonalityBench Slop index | Language & writing › Style & personality | 20.0 | 15.4 | −4.7 |
| DAYJOB: Tax | Professional › Finance, accounting & tax | 9.2 | 4.8 | −4.4 |
| Professional Reasoning Benchmark - Legal | Professional › Legal | 47.6 | 43.3 | −4.2 |
| LMArena Agent Arena Confirmed Success | Tool & computer use › General agents | 19.2 | 10.9 | −4.2 |
| Dual-Arm Sim (task completion) | Tool & computer use › Robotics | 0.0 | 3.8 | +3.8 |
| Terminal-Bench 4.0 (Artificial Analysis) | Software › Software engineering | 59.6 | 56.1 | −3.5 |
| GDPval v2 (OpenAI internal) | Professional › General knowledge work | 43.5 | 46.9 | +3.4 |
| CritPt v2 (agentic, avg@5) | Science › Physical sciences | 81.7 | 78.6 | −3.1 |
| LiveBench 2.0 (2026-11-06 release) | Composite indexes | 83.4 | 80.3 | −3.1 |
| HLAB-Vals-1.1 | Professional › Legal | 9.2 | 12.1 | +2.9 |
| AA-AnalystAgent (pass^5) | Professional › General knowledge work | 56.3 | 53.8 | −2.5 |
| LMArena Agent Arena Steering Burden | Tool & computer use › General agents | 18.0 | 13.4 | −2.3 |
| FrontierCode 2.0 (Artificial Analysis) | Software › Software engineering | 46.4 | 44.4 | −2.1 |
| DualEntry Accounting AI Benchmark | Professional › Finance, accounting & tax | 82.2 | 84.2 | +2.0 |
| Chartography (November 2026 rescoring) | Perception & media › Documents & charts | 89.6 | 87.7 | −1.9 |
| Excel Modeling Benchmark v1.1 | Professional › Finance, accounting & tax | 75.8 | 74.3 | −1.5 |
| Gray Swan IPI Attack Success (k=15) | Safety & alignment | 1.0 | 2.3 | −1.3 |
| Ramp SWE-Bench v2 (Bash harness) | Software › Software engineering | 71.2 | 72.4 | +1.2 |
| GDP.pdf (Artificial Analysis, All-pass) | Professional › General knowledge work | 28.8 | 30.0 | +1.2 |
| ARC-AGI-1 Semi-Private | Knowledge & reasoning › Abstract reasoning | 98.5 | 97.5 | −1.0 |
| LMArena Agent Arena Tool Hallucination | Tool & computer use › Tool calling | 1.0 | 1.2 | +0.1 |
| GDP.pdf (November 2026 rescoring) | Professional › General knowledge work | 48.8 | 48.8 | 0.0 |
| RiemannBench (November 2026 rescoring) | Math | 80.0 | 80.0 | 0.0 |
Data: Artificial Analysis, Surge AI, Arena and 15 othersatlas.village.dev