Model comparison
Claude Opus 4 vs GPT-5.1
GPT-5.1 is the stronger model overall, scoring 49.0 to 43.1 on the Noometry Index.
Last verified . 45 shared benchmarks.
Summary
- They share 45 benchmarks with published results for both. Claude Opus 4 scores higher in 2 categories and GPT-5.1 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in multimodal, where GPT-5.1 leads 44.8 to 31.5.
- The biggest single-benchmark swing is ARC-AGI-1: 35.7% for Claude Opus 4 and 72.8% for GPT-5.1.
- GPT-5.1 is cheaper at $1.25 / $10 per million input/output tokens, against $15 / $75 for Claude Opus 4.
- GPT-5.1 accepts more context: 400K tokens versus 200K.
Side by side
| Claude Opus 4 | GPT-5.1 | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 43.1 | 49.0 |
| Released | 2025-05-22 | 2025-11-13 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 400K |
| Max output | 32K | 128K |
| Input $ / M tokens | $15 | $1.25 |
| Output $ / M tokens | $75 | $10 |
| Results tracked | 56 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude Opus 4: 47.2 (#62), GPT-5.1: 46.4 (#66)
| Benchmark | Claude Opus 4 | GPT-5.1 |
|---|---|---|
| SWE-bench Verified | 70.7% | 68% |
| SWE-bench Verified (bash only) | 67.6% | 66% |
| GSO | 6.9% | 13.7% |
| WeirdML | 43.7% | 60.8% |
| LMArena Coding | 1442 | 1454 |
| Aider Polyglot | 72% | — |
| LMArena WebDev | — | 1395 |
| SciCode | — | 43.3% |
| LiveBench Coding | — | 72.5% |
| ALE-Bench | — | 1,192 |
| AlgoTune | 1.33 | — |
Agentic & Tool Use Claude Opus 4 leads
Claude Opus 4: 34.8 (#42), GPT-5.1: 32.7 (#60)
| Benchmark | Claude Opus 4 | GPT-5.1 |
|---|---|---|
| DeepResearch Bench | 46.8% | 42.8% |
| LMArena Search | 1127 | 1199 |
| Terminal-Bench | — | 47.6% |
| Cybench | 38% | — |
| METR Time Horizons | 63.9% | — |
| Vending-Bench 2 | — | 1,473 |
Reasoning GPT-5.1 leads
Claude Opus 4: 27.3 (#121), GPT-5.1: 39.8 (#58)
| Benchmark | Claude Opus 4 | GPT-5.1 |
|---|---|---|
| ARC-AGI-2 | 8.6% | 17.6% |
| SimpleBench | 58.8% | 53.2% |
| ARC-AGI-1 | 35.7% | 72.8% |
| CritPt | 0.3% | 4.9% |
| EnigmaEval | 5.6% | 11.2% |
| LMArena Hard Prompts | 1399 | 1457 |
| DTBench | 81.6% | 90.1% |
| LMCA | 37.4% | 43.9% |
| Epoch Capabilities Index | 142.67 | 149.64 |
| ForecastBench | 61.1 | 58.1 |
| Kagi LLM Benchmark | 74.3% | — |
| Chess Puzzles | — | 32% |
| LiveBench Reasoning | — | 95.8% |
| Mystery Game Puzzles | — | 19% |
| LiveBench Data Analysis | — | 72.1% |
| LiveBench | — | 78.8% |
Math GPT-5.1 leads
Claude Opus 4: 42.0 (#86), GPT-5.1: 52.2 (#51)
| Benchmark | Claude Opus 4 | GPT-5.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 64.4% | 88.6% |
| Omni-MATH | 61.6% | 46.4% |
| LMArena Math | 1390 | 1447 |
| FrontierMath (Feb 2025 set) | 4.5% | 31% |
| FrontierMath Tier 4 (v1) | 4.2% | 12.5% |
| LiveBench Math | — | 94.5% |
| MATH Level 5 | 85% | — |
Knowledge GPT-5.1 leads
Claude Opus 4: 44.0 (#88), GPT-5.1: 50.6 (#71)
| Benchmark | Claude Opus 4 | GPT-5.1 |
|---|---|---|
| GPQA Diamond | 76.3% | 87.6% |
| Humanity's Last Exam | 10.7% | 23.7% |
| MMLU-Pro | 87.5% | 57.9% |
| Vectara Hallucination Rate | 12% | 10.9% |
| GPQA (HELM) | 70.8% | 44.2% |
| LMArena Expert | 1386 | 1470 |
| SimpleQA Verified | — | 48% |
| Confabulations | 15.9% | — |
Multimodal GPT-5.1 leads
Claude Opus 4: 31.5 (#106), GPT-5.1: 44.8 (#19)
| Benchmark | Claude Opus 4 | GPT-5.1 |
|---|---|---|
| LMArena Vision | 1192 | 1250 |
| VPCT | 38% | 58.7% |
| GeoBench | 49% | — |
| LMArena Document | — | 1403 |
Multilingual GPT-5.1 leads
Claude Opus 4: 48.8 (#138), GPT-5.1: 53.8 (#56)
| Benchmark | Claude Opus 4 | GPT-5.1 |
|---|---|---|
| LMArena Non-English | 1362 | 1431 |
| LMArena Chinese | 1386 | 1495 |
| LMArena French | 1372 | 1450 |
| LMArena German | 1391 | 1438 |
| LMArena Japanese | 1331 | 1453 |
| LMArena Korean | 1321 | 1401 |
| LMArena Russian | 1392 | 1435 |
| LMArena Spanish | 1389 | 1433 |
Instruction Following GPT-5.1 leads
Claude Opus 4: 77.1 (#28), GPT-5.1: 83.9 (#1)
| Benchmark | Claude Opus 4 | GPT-5.1 |
|---|---|---|
| IFEval | 91.8% | 93.5% |
| LMArena Instruction Following | 1406 | 1443 |
| LiveBench Instruction Following | — | 93.3% |
Long Context GPT-5.1 leads
Claude Opus 4: 39.6 (#172), GPT-5.1: 47.6 (#14)
| Benchmark | Claude Opus 4 | GPT-5.1 |
|---|---|---|
| LMArena Longer Query | 1422 | 1447 |
| Fiction.LiveBench | 61.1% | — |
| CL-bench | — | 23.7% |
| CL-bench Life | — | 17.3% |
Writing & Preference GPT-5.1 leads
Claude Opus 4: 61.2 (#89), GPT-5.1: 64.5 (#55)
| Benchmark | Claude Opus 4 | GPT-5.1 |
|---|---|---|
| LMArena Text | 1377 | 1443 |
| LMArena Creative Writing | 1387 | 1427 |
| WildBench | 85.2% | 86.3% |
| LMArena Multi-Turn | 1396 | 1450 |
| Short-Story Creative Writing | 83.6% | — |
| EQ-Bench Creative Writing | 1580 | — |
| LiveBench Language | — | 80.2% |
Frequently asked questions
Is Claude Opus 4 better than GPT-5.1?
GPT-5.1 is the stronger model overall, scoring 49.0 to 43.1 on the Noometry Index.
Which is cheaper, Claude Opus 4 or GPT-5.1?
GPT-5.1 is cheaper. It lists at $1.25 per million input tokens and $10 per million output tokens; Claude Opus 4 lists at $15 and $75.
Is Claude Opus 4 or GPT-5.1 better for coding?
They score almost the same on coding (47.2 vs 46.4); test both on your own repository before choosing.
Which has the bigger context window?
GPT-5.1 does, with 400K tokens against 200K.
How many benchmarks do Claude Opus 4 and GPT-5.1 share?
45 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and GPT-5.1 has 63.