Model comparison
Claude Opus 4 vs GPT-6 Sol
GPT-6 Sol is the stronger model overall, scoring 49.2 to 42.9 on the Noometry Index.
Last verified . 15 shared benchmarks.
Summary
- They share 15 benchmarks with published results for both. Claude Opus 4 scores higher in 4 categories and GPT-6 Sol in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6 Sol leads 49.3 to 27.4.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 12% for Claude Opus 4 and 6.5% for GPT-6 Sol.
- GPT-6 Sol is cheaper at $2 / $10 per million input/output tokens, against $15 / $75 for Claude Opus 4.
- GPT-6 Sol accepts more context: 1.05M tokens versus 200K.
Side by side
| Claude Opus 4 | GPT-6 Sol | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 42.9 | 49.2 |
| Released | 2025-05-22 | 2026-09-22 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1.05M |
| Max output | 32K | 128K |
| Input $ / M tokens | $15 | $2 |
| Output $ / M tokens | $75 | $10 |
| Results tracked | 56 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
Claude Opus 4: 47.8 (#55), GPT-6 Sol: 59.6 (#11)
| Benchmark | Claude Opus 4 | GPT-6 Sol |
|---|---|---|
| LMArena Coding | 1442 | 1453 |
| SWE-bench Verified | 70.7% | — |
| DeepSWE | — | 68.8% |
| FrontierCode | — | 49.3% |
| SWE-bench Verified (bash only) | 67.6% | — |
| Aider Polyglot | 72% | — |
| LMArena WebDev | — | 1692 |
| GSO | 6.9% | — |
| WeirdML | 43.7% | — |
| AlgoTune | 1.33 | — |
Agentic & Tool Use Too close to call
Claude Opus 4: 34.5 (#39), GPT-6 Sol: 33.5 (#49)
| Benchmark | Claude Opus 4 | GPT-6 Sol |
|---|---|---|
| Cybench | 38% | — |
| DeepResearch Bench | 46.8% | — |
| GDP.pdf | — | 28% |
| LMArena Search | 1127 | — |
| METR Time Horizons | 63.9% | — |
Reasoning GPT-6 Sol leads
Claude Opus 4: 27.4 (#104), GPT-6 Sol: 49.3 (#34)
| Benchmark | Claude Opus 4 | GPT-6 Sol |
|---|---|---|
| LMArena Hard Prompts | 1399 | 1420 |
| ARC-AGI-2 | 8.6% | — |
| SimpleBench | 58.8% | — |
| Kagi LLM Benchmark | 74.3% | — |
| NYT Connections (extended) | — | 90.1% |
| ARC-AGI-1 | 35.7% | — |
| CritPt | 0.3% | — |
| EnigmaEval | 5.6% | — |
| EBR-Bench | — | 53.3% |
| DTBench | 81.6% | — |
| LMCA | 37.4% | — |
| Epoch Capabilities Index | 142.67 | — |
| ForecastBench | 61.1 | — |
Math Claude Opus 4 leads
Claude Opus 4: 40.2 (#80), GPT-6 Sol: 35.8 (#135)
| Benchmark | Claude Opus 4 | GPT-6 Sol |
|---|---|---|
| LMArena Math | 1391 | 1404 |
| OTIS Mock AIME 2024-2025 | 64.4% | — |
| Omni-MATH | 61.6% | — |
| MATH Level 5 | 85% | — |
| FrontierMath (Feb 2025 set) | 4.5% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Too close to call
Claude Opus 4: 43.9 (#82), GPT-6 Sol: 43.0 (#87)
| Benchmark | Claude Opus 4 | GPT-6 Sol |
|---|---|---|
| Vectara Hallucination Rate | 12% | 6.5% |
| LMArena Expert | 1384 | 1449 |
| GPQA Diamond | 76.3% | — |
| Humanity's Last Exam | 10.7% | — |
| MMLU-Pro | 87.5% | — |
| Confabulations | 15.9% | — |
| GPQA (HELM) | 70.8% | — |
Multimodal GPT-6 Sol leads
Claude Opus 4: 30.9 (#101), GPT-6 Sol: 47.6 (#9)
| Benchmark | Claude Opus 4 | GPT-6 Sol |
|---|---|---|
| LMArena Vision | 1192 | — |
| GeoBench | 49% | — |
| VPCT | 38% | — |
| Furniture Assembly | — | 58.3% |
Multilingual GPT-6 Sol leads
Claude Opus 4: 49.0 (#133), GPT-6 Sol: 51.0 (#113)
| Benchmark | Claude Opus 4 | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 1362 | 1389 |
| LMArena Chinese | 1386 | 1416 |
| LMArena Russian | 1392 | 1407 |
| LMArena Spanish | 1388 | 1377 |
| LMArena French | 1370 | — |
| LMArena German | 1391 | — |
| LMArena Japanese | 1332 | — |
| LMArena Korean | 1318 | — |
Instruction Following Claude Opus 4 leads
Claude Opus 4: 77.3 (#26), GPT-6 Sol: 74.4 (#97)
| Benchmark | Claude Opus 4 | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 1406 | 1406 |
| IFEval | 91.8% | — |
Long Context GPT-6 Sol leads
Claude Opus 4: 39.5 (#167), GPT-6 Sol: 43.2 (#100)
| Benchmark | Claude Opus 4 | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | 1422 | 1415 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference GPT-6 Sol leads
Claude Opus 4: 61.4 (#85), GPT-6 Sol: 72.3 (#15)
| Benchmark | Claude Opus 4 | GPT-6 Sol |
|---|---|---|
| LMArena Text | 1377 | 1396 |
| LMArena Creative Writing | 1386 | 1392 |
| EQ-Bench Creative Writing | 1580 | 2125 |
| LMArena Multi-Turn | 1396 | 1405 |
| Short-Story Creative Writing | 83.6% | — |
| WildBench | 85.2% | — |
Frequently asked questions
Is Claude Opus 4 better than GPT-6 Sol?
GPT-6 Sol is the stronger model overall, scoring 49.2 to 42.9 on the Noometry Index.
Which is cheaper, Claude Opus 4 or GPT-6 Sol?
GPT-6 Sol is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; Claude Opus 4 lists at $15 and $75.
Is Claude Opus 4 or GPT-6 Sol better for coding?
GPT-6 Sol scores higher on coding benchmarks: 59.6 versus 47.8 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Sol does, with 1.05M tokens against 200K.
How many benchmarks do Claude Opus 4 and GPT-6 Sol share?
15 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and GPT-6 Sol has 22.