Model comparison
Claude 3.5 Sonnet vs GPT-4.1
GPT-4.1 is the stronger model overall, scoring 35.9 to 34.6 on the Noometry Index.
Last verified . 39 shared benchmarks.
Summary
- They share 39 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 2 categories and GPT-4.1 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in multimodal, where GPT-4.1 leads 38.2 to 26.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Claude 3.5 Sonnet and 38.3% for GPT-4.1.
Side by side
| Claude 3.5 Sonnet | GPT-4.1 | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 34.6 | 35.9 |
| Released | 2024-06-20 | 2025-04-14 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 33K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $8 |
| Results tracked | 60 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 39.0 (#165), GPT-4.1: 34.4 (#238)
| Benchmark | Claude 3.5 Sonnet | GPT-4.1 |
|---|---|---|
| Aider Polyglot | 51.6% | 52.4% |
| WeirdML | 40% | 39% |
| LMArena Coding | 1342 | 1391 |
| CadEval | 48% | 42% |
| SWE-bench Verified | — | 48.5% |
| SWE-bench Verified (bash only) | — | 39.6% |
| GSO | 4.6% | — |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| BigCodeBench Complete | 58.6% | — |
| ALE-Bench | — | 558.1 |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use GPT-4.1 leads
Claude 3.5 Sonnet: 32.3 (#67), GPT-4.1: 34.7 (#43)
| Benchmark | Claude 3.5 Sonnet | GPT-4.1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 54% |
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| METR Time Horizons | 45.2% | — |
Reasoning Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 23.1 (#183), GPT-4.1: 11.7 (#339)
| Benchmark | Claude 3.5 Sonnet | GPT-4.1 |
|---|---|---|
| SimpleBench | 41.4% | 27% |
| EnigmaEval | 0.9% | 2.2% |
| LMArena Hard Prompts | 1305 | 1384 |
| DTBench | 67.8% | 68.3% |
| Epoch Capabilities Index | 133.55 | 136.78 |
| ForecastBench | 60.7 | 61.5 |
| ARC-AGI-2 | — | 0.4% |
| Kagi LLM Benchmark | — | 52.3% |
| ARC-AGI-1 | — | 5.5% |
| Chess Puzzles | — | 6% |
| LiveBench Reasoning | 56.7% | — |
| LiveBench Data Analysis | 55% | — |
| LMCA | — | 25.6% |
| LiveBench | 59% | — |
Math GPT-4.1 leads
Claude 3.5 Sonnet: 19.2 (#288), GPT-4.1: 22.3 (#280)
| Benchmark | Claude 3.5 Sonnet | GPT-4.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 38.3% |
| Omni-MATH | 27.6% | 47.1% |
| LMArena Math | 1307 | 1370 |
| MATH Level 5 | 56.9% | 83% |
| FrontierMath (Feb 2025 set) | 2.1% | 5.5% |
| FrontierMath Tier 4 (v1) | 0% | 0% |
| FrontierMath (Tiers 1-3) | — | 6% |
| LiveBench Math | 52.3% | — |
Knowledge GPT-4.1 leads
Claude 3.5 Sonnet: 28.6 (#245), GPT-4.1: 37.1 (#160)
| Benchmark | Claude 3.5 Sonnet | GPT-4.1 |
|---|---|---|
| GPQA Diamond | 55.3% | 66.9% |
| Humanity's Last Exam | 4.1% | 5.4% |
| MMLU-Pro | 77.7% | 81.1% |
| GPQA (HELM) | 56.5% | 65.9% |
| LMArena Expert | 1265 | 1364 |
| SimpleQA Verified | — | 31.1% |
| Confabulations | 19.9% | — |
| Vectara Hallucination Rate | — | 5.6% |
| MMLU | 87.3% | — |
Multimodal GPT-4.1 leads
Claude 3.5 Sonnet: 26.5 (#120), GPT-4.1: 38.2 (#67)
| Benchmark | Claude 3.5 Sonnet | GPT-4.1 |
|---|---|---|
| LMArena Vision | 1125 | 1211 |
| GeoBench | 62% | 72% |
| Video-MME | 60% | — |
| VPCT | 33% | — |
Multilingual GPT-4.1 leads
Claude 3.5 Sonnet: 43.2 (#185), GPT-4.1: 49.4 (#133)
| Benchmark | Claude 3.5 Sonnet | GPT-4.1 |
|---|---|---|
| LMArena Non-English | 1283 | 1370 |
| LMArena Chinese | 1272 | 1382 |
| LMArena French | 1305 | 1382 |
| LMArena German | 1297 | 1381 |
| LMArena Japanese | 1234 | 1319 |
| LMArena Korean | 1200 | 1339 |
| LMArena Russian | 1306 | 1377 |
| LMArena Spanish | 1290 | 1376 |
Instruction Following GPT-4.1 leads
Claude 3.5 Sonnet: 68.8 (#182), GPT-4.1: 71.3 (#153)
| Benchmark | Claude 3.5 Sonnet | GPT-4.1 |
|---|---|---|
| IFEval | 85.5% | 83.8% |
| LMArena Instruction Following | 1297 | 1367 |
| LiveBench Instruction Following | 69.3% | — |
Long Context Too close to call
Claude 3.5 Sonnet: 39.9 (#167), GPT-4.1: 40.0 (#163)
| Benchmark | Claude 3.5 Sonnet | GPT-4.1 |
|---|---|---|
| LMArena Longer Query | 1311 | 1385 |
| Fiction.LiveBench | — | 63.9% |
Writing & Preference GPT-4.1 leads
Claude 3.5 Sonnet: 52.9 (#164), GPT-4.1: 57.6 (#125)
| Benchmark | Claude 3.5 Sonnet | GPT-4.1 |
|---|---|---|
| LMArena Text | 1298 | 1383 |
| LMArena Creative Writing | 1292 | 1363 |
| EQ-Bench Creative Writing | 1451 | 1420 |
| WildBench | 79.2% | 85.4% |
| LMArena Multi-Turn | 1326 | 1398 |
| Short-Story Creative Writing | 80.3% | — |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than GPT-4.1?
GPT-4.1 is the stronger model overall, scoring 35.9 to 34.6 on the Noometry Index.
Is Claude 3.5 Sonnet or GPT-4.1 better for coding?
Claude 3.5 Sonnet scores higher on coding benchmarks: 39.0 versus 34.4 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and GPT-4.1 share?
39 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and GPT-4.1 has 52.