Model comparison
Claude 3 Opus vs GPT-4.1
GPT-4.1 is the stronger model overall, scoring 35.9 to 29.5 on the Noometry Index.
Last verified . 30 shared benchmarks.
Summary
- They share 30 benchmarks with published results for both. Claude 3 Opus scores higher in 1 category and GPT-4.1 in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-4.1 leads 37.1 to 24.5.
- The biggest single-benchmark swing is MATH Level 5: 37.5% for Claude 3 Opus and 83% for GPT-4.1.
Side by side
| Claude 3 Opus | GPT-4.1 | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 29.5 | 35.9 |
| Released | 2024-02-29 | 2025-04-14 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 33K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $8 |
| Results tracked | 46 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4.1 leads
Claude 3 Opus: 32.9 (#267), GPT-4.1: 34.4 (#238)
| Benchmark | Claude 3 Opus | GPT-4.1 |
|---|---|---|
| WeirdML | 19.2% | 39% |
| LMArena Coding | 1264 | 1391 |
| SWE-bench Verified | — | 48.5% |
| SWE-bench Verified (bash only) | — | 39.6% |
| Aider Polyglot | — | 52.4% |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 38.6% | — |
| BigCodeBench Complete | 57.4% | — |
| CadEval | — | 42% |
| ALE-Bench | — | 558.1 |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use GPT-4.1 leads
Claude 3 Opus: 24.6 (#116), GPT-4.1: 34.7 (#43)
| Benchmark | Claude 3 Opus | GPT-4.1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 54% |
| Cybench | 10% | — |
| METR Time Horizons | 29.5% | — |
Reasoning Claude 3 Opus leads
Claude 3 Opus: 14.6 (#324), GPT-4.1: 11.7 (#339)
| Benchmark | Claude 3 Opus | GPT-4.1 |
|---|---|---|
| SimpleBench | 23.5% | 27% |
| Chess Puzzles | 5% | 6% |
| EnigmaEval | 0.8% | 2.2% |
| LMArena Hard Prompts | 1245 | 1384 |
| DTBench | 61.6% | 68.3% |
| LMCA | 17% | 25.6% |
| Epoch Capabilities Index | 126.91 | 136.78 |
| ForecastBench | 58.4 | 61.5 |
| ARC-AGI-2 | — | 0.4% |
| Kagi LLM Benchmark | — | 52.3% |
| ARC-AGI-1 | — | 5.5% |
| LiveBench Reasoning | 40.6% | — |
| LiveBench Data Analysis | 57.9% | — |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |
Math GPT-4.1 leads
Claude 3 Opus: 14.8 (#299), GPT-4.1: 22.3 (#280)
| Benchmark | Claude 3 Opus | GPT-4.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 38.3% |
| LMArena Math | 1273 | 1370 |
| MATH Level 5 | 37.5% | 83% |
| FrontierMath (Tiers 1-3) | — | 6% |
| Omni-MATH | — | 47.1% |
| LiveBench Math | 43.6% | — |
| FrontierMath (Feb 2025 set) | — | 5.5% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge GPT-4.1 leads
Claude 3 Opus: 24.5 (#267), GPT-4.1: 37.1 (#160)
| Benchmark | Claude 3 Opus | GPT-4.1 |
|---|---|---|
| GPQA Diamond | 47.2% | 66.9% |
| SimpleQA Verified | 12.6% | 31.1% |
| LMArena Expert | 1223 | 1364 |
| Humanity's Last Exam | — | 5.4% |
| MMLU-Pro | — | 81.1% |
| Confabulations | 22.7% | — |
| Vectara Hallucination Rate | — | 5.6% |
| GPQA (HELM) | — | 65.9% |
| MMLU | 84.6% | — |
Multimodal GPT-4.1 leads
Claude 3 Opus: 27.1 (#116), GPT-4.1: 38.2 (#67)
| Benchmark | Claude 3 Opus | GPT-4.1 |
|---|---|---|
| LMArena Vision | 1023 | 1211 |
| GeoBench | — | 72% |
Multilingual GPT-4.1 leads
Claude 3 Opus: 41.4 (#207), GPT-4.1: 49.4 (#133)
| Benchmark | Claude 3 Opus | GPT-4.1 |
|---|---|---|
| LMArena Non-English | 1258 | 1370 |
| LMArena Chinese | 1248 | 1382 |
| LMArena French | 1275 | 1382 |
| LMArena German | 1258 | 1381 |
| LMArena Japanese | 1204 | 1319 |
| LMArena Korean | 1187 | 1339 |
| LMArena Russian | 1280 | 1377 |
| LMArena Spanish | 1246 | 1376 |
Instruction Following GPT-4.1 leads
Claude 3 Opus: 64.1 (#228), GPT-4.1: 71.3 (#153)
| Benchmark | Claude 3 Opus | GPT-4.1 |
|---|---|---|
| LMArena Instruction Following | 1248 | 1367 |
| LiveBench Instruction Following | 63.9% | — |
| IFEval | — | 83.8% |
Long Context GPT-4.1 leads
Claude 3 Opus: 38.2 (#202), GPT-4.1: 40.0 (#163)
| Benchmark | Claude 3 Opus | GPT-4.1 |
|---|---|---|
| LMArena Longer Query | 1259 | 1385 |
| Fiction.LiveBench | — | 63.9% |
Writing & Preference GPT-4.1 leads
Claude 3 Opus: 47.2 (#213), GPT-4.1: 57.6 (#125)
| Benchmark | Claude 3 Opus | GPT-4.1 |
|---|---|---|
| LMArena Text | 1262 | 1383 |
| LMArena Creative Writing | 1235 | 1363 |
| LMArena Multi-Turn | 1275 | 1398 |
| EQ-Bench Creative Writing | — | 1420 |
| WildBench | — | 85.4% |
| LiveBench Language | 50.4% | — |
Frequently asked questions
Is Claude 3 Opus better than GPT-4.1?
GPT-4.1 is the stronger model overall, scoring 35.9 to 29.5 on the Noometry Index.
Is Claude 3 Opus or GPT-4.1 better for coding?
GPT-4.1 scores higher on coding benchmarks: 34.4 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and GPT-4.1 share?
30 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and GPT-4.1 has 52.