Model comparison
Claude Sonnet 4 vs GPT-4.1
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 35.9 on the Noometry Index. GPT-4.1 costs 1.7× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.
Last verified . 46 shared benchmarks.
Summary
- They share 46 benchmarks with published results for both. Claude Sonnet 4 scores higher in 6 categories and GPT-4.1 in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 4 leads 43.3 to 22.3.
- The biggest single-benchmark swing is GeoBench: 37% for Claude Sonnet 4 and 72% for GPT-4.1.
- GPT-4.1 is cheaper at $2 / $8 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
- GPT-4.1 accepts more context: 1.05M tokens versus 200K.
Side by side
| Claude Sonnet 4 | GPT-4.1 | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 40.8 | 35.9 |
| Released | 2025-05-22 | 2025-04-14 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1.05M |
| Max output | 64K | 33K |
| Input $ / M tokens | $3 | $2 |
| Output $ / M tokens | $15 | $8 |
| Results tracked | 58 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4 leads
Claude Sonnet 4: 43.5 (#88), GPT-4.1: 34.4 (#238)
| Benchmark | Claude Sonnet 4 | GPT-4.1 |
|---|---|---|
| SWE-bench Verified (bash only) | 64.9% | 39.6% |
| Aider Polyglot | 61.3% | 52.4% |
| WeirdML | 46.1% | 39% |
| LMArena Coding | 1414 | 1391 |
| ALE-Bench | 655.35 | 558.1 |
| SWE-bench Verified | — | 48.5% |
| SciCode | 40% | — |
| GSO | 4.9% | — |
| CadEval | — | 42% |
Agentic & Tool Use Claude Sonnet 4 leads
Claude Sonnet 4: 38.5 (#31), GPT-4.1: 34.7 (#43)
| Benchmark | Claude Sonnet 4 | GPT-4.1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 54% |
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |
Reasoning Claude Sonnet 4 leads
Claude Sonnet 4: 22.9 (#187), GPT-4.1: 11.7 (#339)
| Benchmark | Claude Sonnet 4 | GPT-4.1 |
|---|---|---|
| ARC-AGI-2 | 5.9% | 0.4% |
| SimpleBench | 45.5% | 27% |
| Kagi LLM Benchmark | 73% | 52.3% |
| ARC-AGI-1 | 40% | 5.5% |
| EnigmaEval | 3.1% | 2.2% |
| LMArena Hard Prompts | 1372 | 1384 |
| DTBench | 77.1% | 68.3% |
| LMCA | 29% | 25.6% |
| Epoch Capabilities Index | 141.69 | 136.78 |
| ForecastBench | 60.2 | 61.5 |
| CritPt | 0.3% | — |
| Chess Puzzles | — | 6% |
Math Claude Sonnet 4 leads
Claude Sonnet 4: 43.3 (#80), GPT-4.1: 22.3 (#280)
| Benchmark | Claude Sonnet 4 | GPT-4.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 38.3% |
| Omni-MATH | 60.2% | 47.1% |
| LMArena Math | 1375 | 1370 |
| MATH Level 5 | 84.4% | 83% |
| FrontierMath (Feb 2025 set) | 4.1% | 5.5% |
| FrontierMath Tier 4 (v1) | 0% | 0% |
| FrontierMath (Tiers 1-3) | — | 6% |
Knowledge Claude Sonnet 4 leads
Claude Sonnet 4: 41.8 (#108), GPT-4.1: 37.1 (#160)
| Benchmark | Claude Sonnet 4 | GPT-4.1 |
|---|---|---|
| GPQA Diamond | 79.2% | 66.9% |
| Humanity's Last Exam | 7.8% | 5.4% |
| MMLU-Pro | 84.3% | 81.1% |
| Vectara Hallucination Rate | 10.3% | 5.6% |
| GPQA (HELM) | 70.6% | 65.9% |
| LMArena Expert | 1372 | 1364 |
| SimpleQA Verified | — | 31.1% |
| Confabulations | 13.2% | — |
Multimodal GPT-4.1 leads
Claude Sonnet 4: 26.2 (#121), GPT-4.1: 38.2 (#67)
| Benchmark | Claude Sonnet 4 | GPT-4.1 |
|---|---|---|
| LMArena Vision | 1191 | 1211 |
| GeoBench | 37% | 72% |
| VPCT | 34% | — |
| MindCube | 44.8% | — |
Multilingual GPT-4.1 leads
Claude Sonnet 4: 46.7 (#156), GPT-4.1: 49.4 (#133)
| Benchmark | Claude Sonnet 4 | GPT-4.1 |
|---|---|---|
| LMArena Non-English | 1333 | 1370 |
| LMArena Chinese | 1350 | 1382 |
| LMArena French | 1363 | 1382 |
| LMArena German | 1331 | 1381 |
| LMArena Japanese | 1302 | 1319 |
| LMArena Korean | 1291 | 1339 |
| LMArena Russian | 1355 | 1377 |
| LMArena Spanish | 1357 | 1376 |
Instruction Following Too close to call
Claude Sonnet 4: 71.7 (#145), GPT-4.1: 71.3 (#153)
| Benchmark | Claude Sonnet 4 | GPT-4.1 |
|---|---|---|
| IFEval | 84% | 83.8% |
| LMArena Instruction Following | 1376 | 1367 |
Long Context GPT-4.1 leads
Claude Sonnet 4: 33.7 (#259), GPT-4.1: 40.0 (#163)
| Benchmark | Claude Sonnet 4 | GPT-4.1 |
|---|---|---|
| Fiction.LiveBench | 46.9% | 63.9% |
| LMArena Longer Query | 1398 | 1385 |
Writing & Preference Too close to call
Claude Sonnet 4: 57.1 (#132), GPT-4.1: 57.6 (#125)
| Benchmark | Claude Sonnet 4 | GPT-4.1 |
|---|---|---|
| LMArena Text | 1351 | 1383 |
| LMArena Creative Writing | 1345 | 1363 |
| EQ-Bench Creative Writing | 1483 | 1420 |
| WildBench | 83.8% | 85.4% |
| LMArena Multi-Turn | 1376 | 1398 |
| Short-Story Creative Writing | 81.4% | — |
Frequently asked questions
Is Claude Sonnet 4 better than GPT-4.1?
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 35.9 on the Noometry Index. GPT-4.1 costs 1.7× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 4 or GPT-4.1?
GPT-4.1 is cheaper. It lists at $2 per million input tokens and $8 per million output tokens; Claude Sonnet 4 lists at $3 and $15.
Is Claude Sonnet 4 or GPT-4.1 better for coding?
Claude Sonnet 4 scores higher on coding benchmarks: 43.5 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 does, with 1.05M tokens against 200K.
How many benchmarks do Claude Sonnet 4 and GPT-4.1 share?
46 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and GPT-4.1 has 52.