Model comparison
Claude Opus 4.1 vs GPT-6 Sol
GPT-6 Sol is the stronger model overall, scoring 49.2 to 40.8 on the Noometry Index.
Last verified . 16 shared benchmarks.
Summary
- They share 16 benchmarks with published results for both. Claude Opus 4.1 scores higher in 4 categories and GPT-6 Sol in 6 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in multimodal, where GPT-6 Sol leads 47.6 to 26.2.
- The biggest single-benchmark swing is EBR-Bench: 7.9% for Claude Opus 4.1 and 53.3% for GPT-6 Sol.
- GPT-6 Sol is cheaper at $2 / $10 per million input/output tokens, against $15 / $75 for Claude Opus 4.1.
- GPT-6 Sol accepts more context: 1.05M tokens versus 200K.
Side by side
| Claude Opus 4.1 | GPT-6 Sol | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 40.8 | 49.2 |
| Released | 2025-08-05 | 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 | 48 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
Claude Opus 4.1: 44.3 (#69), GPT-6 Sol: 59.6 (#11)
| Benchmark | Claude Opus 4.1 | GPT-6 Sol |
|---|---|---|
| LMArena WebDev | 1390 | 1692 |
| LMArena Coding | 1479 | 1453 |
| SWE-bench Verified | 73.3% | — |
| DeepSWE | — | 68.8% |
| FrontierCode | — | 49.3% |
| WeirdML | 45.9% | — |
| ALE-Bench | 674.77 | — |
| AlgoTune | 1.34 | — |
Agentic & Tool Use Claude Opus 4.1 leads
Claude Opus 4.1: 34.8 (#38), GPT-6 Sol: 33.5 (#49)
| Benchmark | Claude Opus 4.1 | GPT-6 Sol |
|---|---|---|
| Terminal-Bench | 38% | — |
| GDPval | 43.6% | — |
| Cybench | 42% | — |
| DeepResearch Bench | 48.3% | — |
| GDP.pdf | — | 28% |
| LMArena Search | 1148 | — |
| METR Time Horizons | 66.8% | — |
Reasoning GPT-6 Sol leads
Claude Opus 4.1: 31.6 (#70), GPT-6 Sol: 49.3 (#34)
| Benchmark | Claude Opus 4.1 | GPT-6 Sol |
|---|---|---|
| EBR-Bench | 7.9% | 53.3% |
| LMArena Hard Prompts | 1443 | 1420 |
| SimpleBench | 60% | — |
| NYT Connections (extended) | — | 90.1% |
| Chess Puzzles | 7% | — |
| EnigmaEval | 7.2% | — |
| Mystery Game Puzzles | 21% | — |
| DTBench | 80% | — |
| LMCA | 37.1% | — |
| Epoch Capabilities Index | 144.11 | — |
| ForecastBench | 62 | — |
Math GPT-6 Sol leads
Claude Opus 4.1: 22.0 (#267), GPT-6 Sol: 35.8 (#135)
| Benchmark | Claude Opus 4.1 | GPT-6 Sol |
|---|---|---|
| LMArena Math | 1430 | 1404 |
| FrontierMath (Tiers 1-3) | 12.6% | — |
| FrontierMath Tier 4 | 2.4% | — |
| OTIS Mock AIME 2024-2025 | 68.9% | — |
| FrontierMath (Feb 2025 set) | 7.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge GPT-6 Sol leads
Claude Opus 4.1: 41.9 (#93), GPT-6 Sol: 43.0 (#87)
| Benchmark | Claude Opus 4.1 | GPT-6 Sol |
|---|---|---|
| Vectara Hallucination Rate | 11.8% | 6.5% |
| LMArena Expert | 1439 | 1449 |
| GPQA Diamond | 77.3% | — |
| Humanity's Last Exam | 11.5% | — |
| Confabulations | 17.1% | — |
Multimodal GPT-6 Sol leads
Claude Opus 4.1: 26.2 (#114), GPT-6 Sol: 47.6 (#9)
| Benchmark | Claude Opus 4.1 | GPT-6 Sol |
|---|---|---|
| VPCT | 35% | — |
| Furniture Assembly | — | 58.3% |
Multilingual Claude Opus 4.1 leads
Claude Opus 4.1: 52.1 (#90), GPT-6 Sol: 51.0 (#113)
| Benchmark | Claude Opus 4.1 | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 1405 | 1389 |
| LMArena Chinese | 1427 | 1416 |
| LMArena Russian | 1421 | 1407 |
| LMArena Spanish | 1448 | 1377 |
| LMArena French | 1432 | — |
| LMArena German | 1412 | — |
| LMArena Japanese | 1378 | — |
| LMArena Korean | 1381 | — |
Instruction Following Claude Opus 4.1 leads
Claude Opus 4.1: 75.8 (#53), GPT-6 Sol: 74.4 (#97)
| Benchmark | Claude Opus 4.1 | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 1436 | 1406 |
Long Context Claude Opus 4.1 leads
Claude Opus 4.1: 44.5 (#60), GPT-6 Sol: 43.2 (#100)
| Benchmark | Claude Opus 4.1 | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | 1455 | 1415 |
Writing & Preference GPT-6 Sol leads
Claude Opus 4.1: 62.6 (#70), GPT-6 Sol: 72.3 (#15)
| Benchmark | Claude Opus 4.1 | GPT-6 Sol |
|---|---|---|
| LMArena Text | 1419 | 1396 |
| LMArena Creative Writing | 1412 | 1392 |
| LMArena Multi-Turn | 1444 | 1405 |
| Short-Story Creative Writing | 84.7% | — |
| EQ-Bench Creative Writing | — | 2125 |
Frequently asked questions
Is Claude Opus 4.1 better than GPT-6 Sol?
GPT-6 Sol is the stronger model overall, scoring 49.2 to 40.8 on the Noometry Index.
Which is cheaper, Claude Opus 4.1 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 4.1 lists at $15 and $75.
Is Claude Opus 4.1 or GPT-6 Sol better for coding?
GPT-6 Sol scores higher on coding benchmarks: 59.6 versus 44.3 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 4.1 and GPT-6 Sol share?
16 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and GPT-6 Sol has 22.