Model comparison
Claude 3 Opus vs GPT-5.1
GPT-5.1 is the stronger model overall, scoring 48.8 to 29.3 on the Noometry Index.
Last verified . 36 shared benchmarks.
Summary
- They share 36 benchmarks with published results for both. Claude 3 Opus scores higher in 0 categories and GPT-5.1 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.1 leads 50.3 to 13.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.7% for Claude 3 Opus and 88.6% for GPT-5.1.
Side by side
| Claude 3 Opus | GPT-5.1 | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 29.3 | 48.8 |
| Released | 2024-02-29 | 2025-11-13 |
| Weights | Proprietary | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $1.25 |
| Output $ / M tokens | — | $10 |
| Results tracked | 46 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.1 leads
Claude 3 Opus: 32.4 (#261), GPT-5.1: 46.9 (#59)
| Benchmark | Claude 3 Opus | GPT-5.1 |
|---|---|---|
| WeirdML | 19.2% | 60.8% |
| LiveBench Coding | 38.6% | 72.5% |
| LMArena Coding | 1264 | 1454 |
| SWE-bench Verified | — | 68% |
| SWE-bench Verified (bash only) | — | 66% |
| LMArena WebDev | — | 1395 |
| SciCode | — | 43.3% |
| GSO | — | 13.7% |
| BigCodeBench Instruct | 45.5% | — |
| BigCodeBench Complete | 57.4% | — |
| ALE-Bench | — | 1,192 |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use GPT-5.1 leads
Claude 3 Opus: 24.3 (#110), GPT-5.1: 32.5 (#55)
| Benchmark | Claude 3 Opus | GPT-5.1 |
|---|---|---|
| Terminal-Bench | — | 47.6% |
| Cybench | 10% | — |
| DeepResearch Bench | — | 42.8% |
| LMArena Search | — | 1199 |
| METR Time Horizons | 29.5% | — |
| Vending-Bench 2 | — | 1,473 |
Reasoning GPT-5.1 leads
Claude 3 Opus: 14.2 (#318), GPT-5.1: 39.9 (#50)
| Benchmark | Claude 3 Opus | GPT-5.1 |
|---|---|---|
| SimpleBench | 23.5% | 53.2% |
| Chess Puzzles | 5% | 32% |
| EnigmaEval | 0.8% | 11.2% |
| LiveBench Reasoning | 40.6% | 95.8% |
| LMArena Hard Prompts | 1246 | 1457 |
| DTBench | 61.6% | 90.1% |
| LiveBench Data Analysis | 57.9% | 72.1% |
| LMCA | 17% | 43.9% |
| Epoch Capabilities Index | 126.91 | 149.66 |
| ForecastBench | 58.4 | 58.1 |
| LiveBench | 49.2% | 78.8% |
| ARC-AGI-2 | — | 17.6% |
| ARC-AGI-1 | — | 72.8% |
| CritPt | — | 4.9% |
| Mystery Game Puzzles | — | 19% |
| WinoGrande | 88.5% | — |
Math GPT-5.1 leads
Claude 3 Opus: 13.9 (#293), GPT-5.1: 50.3 (#45)
| Benchmark | Claude 3 Opus | GPT-5.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 88.6% |
| LiveBench Math | 43.6% | 94.5% |
| LMArena Math | 1273 | 1446 |
| Omni-MATH | — | 46.4% |
| MATH Level 5 | 37.5% | — |
| FrontierMath (Feb 2025 set) | — | 31% |
| FrontierMath Tier 4 (v1) | — | 12.5% |
Knowledge GPT-5.1 leads
Claude 3 Opus: 24.5 (#262), GPT-5.1: 50.5 (#65)
| Benchmark | Claude 3 Opus | GPT-5.1 |
|---|---|---|
| GPQA Diamond | 47.2% | 87.6% |
| SimpleQA Verified | 12.6% | 48% |
| LMArena Expert | 1223 | 1470 |
| Humanity's Last Exam | — | 23.7% |
| MMLU-Pro | — | 57.9% |
| Confabulations | 22.7% | — |
| Vectara Hallucination Rate | — | 10.9% |
| GPQA (HELM) | — | 44.2% |
| MMLU | 84.6% | — |
Multimodal GPT-5.1 leads
Claude 3 Opus: 26.6 (#112), GPT-5.1: 44.0 (#17)
| Benchmark | Claude 3 Opus | GPT-5.1 |
|---|---|---|
| LMArena Vision | 1023 | 1250 |
| VPCT | — | 58.7% |
| LMArena Document | — | 1403 |
Multilingual GPT-5.1 leads
Claude 3 Opus: 41.6 (#202), GPT-5.1: 54.0 (#51)
| Benchmark | Claude 3 Opus | GPT-5.1 |
|---|---|---|
| LMArena Non-English | 1258 | 1431 |
| LMArena Chinese | 1248 | 1495 |
| LMArena French | 1274 | 1451 |
| LMArena German | 1258 | 1439 |
| LMArena Japanese | 1204 | 1453 |
| LMArena Korean | 1187 | 1401 |
| LMArena Russian | 1280 | 1435 |
| LMArena Spanish | 1246 | 1430 |
Instruction Following GPT-5.1 leads
Claude 3 Opus: 64.3 (#223), GPT-5.1: 84.0 (#1)
| Benchmark | Claude 3 Opus | GPT-5.1 |
|---|---|---|
| LiveBench Instruction Following | 63.9% | 93.3% |
| LMArena Instruction Following | 1248 | 1442 |
| IFEval | — | 93.5% |
Long Context GPT-5.1 leads
Claude 3 Opus: 38.2 (#197), GPT-5.1: 47.6 (#14)
| Benchmark | Claude 3 Opus | GPT-5.1 |
|---|---|---|
| LMArena Longer Query | 1259 | 1448 |
| CL-bench | — | 23.7% |
| CL-bench Life | — | 17.3% |
Writing & Preference GPT-5.1 leads
Claude 3 Opus: 47.4 (#208), GPT-5.1: 64.7 (#53)
| Benchmark | Claude 3 Opus | GPT-5.1 |
|---|---|---|
| LMArena Text | 1262 | 1443 |
| LMArena Creative Writing | 1235 | 1427 |
| LMArena Multi-Turn | 1275 | 1449 |
| LiveBench Language | 50.4% | 80.2% |
| WildBench | — | 86.3% |
Frequently asked questions
Is Claude 3 Opus better than GPT-5.1?
GPT-5.1 is the stronger model overall, scoring 48.8 to 29.3 on the Noometry Index.
Is Claude 3 Opus or GPT-5.1 better for coding?
GPT-5.1 scores higher on coding benchmarks: 46.9 versus 32.4 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and GPT-5.1 share?
36 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and GPT-5.1 has 63.