Model comparison
Claude Opus 4.1 vs GPT-6 Sol
GPT-6 Sol is the stronger model overall, scoring 61.8 to 41.0 on the Noometry Index.
Last verified . 29 shared benchmarks.
Summary
- They share 29 benchmarks with published results for both. Claude Opus 4.1 scores higher in 3 categories and GPT-6 Sol in 7 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Sol leads 87.2 to 22.3.
- The biggest single-benchmark swing is FrontierMath Tier 4: 2.4% for Claude Opus 4.1 and 90% 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 | 41.0 | 61.8 |
| 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 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
Claude Opus 4.1: 44.4 (#73), GPT-6 Sol: 60.1 (#11)
| Benchmark | Claude Opus 4.1 | GPT-6 Sol |
|---|---|---|
| LMArena WebDev | 1390 | 1688 |
| LMArena Coding | 1479 | 1447 |
| ALE-Bench | 674.77 | 2,462 |
| SWE-bench Verified | 73.3% | — |
| DeepSWE | — | 68.8% |
| FrontierCode | — | 49.3% |
| SciCode | — | 57.6% |
| WeirdML | 45.9% | — |
| AlgoTune | 1.34 | — |
Agentic & Tool Use GPT-6 Sol leads
Claude Opus 4.1: 35.0 (#41), GPT-6 Sol: 37.2 (#36)
| Benchmark | Claude Opus 4.1 | GPT-6 Sol |
|---|---|---|
| Terminal-Bench | 38% | — |
| APEX-Agents | — | 54.3% |
| GDPval | 43.6% | — |
| Cybench | 42% | — |
| DeepResearch Bench | 48.3% | — |
| GDP.pdf | — | 26.4% |
| LMArena Search | 1148 | — |
| METR Time Horizons | 66.8% | — |
| Vending-Bench 2 | — | 14,428 |
Reasoning GPT-6 Sol leads
Claude Opus 4.1: 32.2 (#76), GPT-6 Sol: 74.0 (#9)
| Benchmark | Claude Opus 4.1 | GPT-6 Sol |
|---|---|---|
| EBR-Bench | 7.9% | 53.3% |
| LMArena Hard Prompts | 1443 | 1418 |
| Mystery Game Puzzles | 21% | 56% |
| DTBench | 80% | 97.3% |
| LMCA | 37.1% | 59.1% |
| Epoch Capabilities Index | 144.12 | 162.72 |
| ARC-AGI-2 | — | 89.6% |
| SimpleBench | 60% | — |
| NYT Connections (extended) | — | 90.1% |
| ARC-AGI-1 | — | 95.5% |
| CritPt | — | 30.9% |
| Chess Puzzles | 7% | — |
| EnigmaEval | 7.2% | — |
| ForecastBench | 62 | — |
Math GPT-6 Sol leads
Claude Opus 4.1: 22.3 (#277), GPT-6 Sol: 87.2 (#7)
| Benchmark | Claude Opus 4.1 | GPT-6 Sol |
|---|---|---|
| FrontierMath (Tiers 1-3) | 12.6% | 89.8% |
| FrontierMath Tier 4 | 2.4% | 90% |
| OTIS Mock AIME 2024-2025 | 68.9% | 100% |
| LMArena Math | 1431 | 1402 |
| ProofBench | — | 83% |
| FrontierMath (Feb 2025 set) | 7.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge GPT-6 Sol leads
Claude Opus 4.1: 42.0 (#101), GPT-6 Sol: 64.8 (#15)
| Benchmark | Claude Opus 4.1 | GPT-6 Sol |
|---|---|---|
| GPQA Diamond | 77.3% | 94.3% |
| Vectara Hallucination Rate | 11.8% | 6.5% |
| LMArena Expert | 1439 | 1439 |
| Humanity's Last Exam | 11.5% | — |
| SimpleQA Verified | — | 60.7% |
| Confabulations | 17.1% | — |
Multimodal GPT-6 Sol leads
Claude Opus 4.1: 26.8 (#119), GPT-6 Sol: 47.6 (#10)
| Benchmark | Claude Opus 4.1 | GPT-6 Sol |
|---|---|---|
| LMArena Vision | — | 1245 |
| VPCT | 35% | — |
| Blueprint-Bench 2 | — | 36.9% |
| Furniture Assembly | — | 58.3% |
Multilingual Claude Opus 4.1 leads
Claude Opus 4.1: 52.0 (#95), GPT-6 Sol: 50.5 (#118)
| Benchmark | Claude Opus 4.1 | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 1405 | 1385 |
| LMArena Chinese | 1427 | 1405 |
| LMArena French | 1431 | 1410 |
| LMArena German | 1413 | 1390 |
| LMArena Japanese | 1378 | 1385 |
| LMArena Korean | 1380 | 1341 |
| LMArena Russian | 1422 | 1401 |
| LMArena Spanish | 1448 | 1384 |
Instruction Following Claude Opus 4.1 leads
Claude Opus 4.1: 75.6 (#58), GPT-6 Sol: 74.5 (#94)
| Benchmark | Claude Opus 4.1 | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 1435 | 1412 |
Long Context Claude Opus 4.1 leads
Claude Opus 4.1: 44.5 (#63), GPT-6 Sol: 43.1 (#108)
| Benchmark | Claude Opus 4.1 | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | 1455 | 1411 |
Writing & Preference GPT-6 Sol leads
Claude Opus 4.1: 62.4 (#74), GPT-6 Sol: 71.9 (#18)
| Benchmark | Claude Opus 4.1 | GPT-6 Sol |
|---|---|---|
| LMArena Text | 1419 | 1395 |
| LMArena Creative Writing | 1412 | 1378 |
| LMArena Multi-Turn | 1444 | 1412 |
| 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 61.8 to 41.0 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: 60.1 versus 44.4 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?
29 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and GPT-6 Sol has 45.