Model comparison
Claude Sonnet 4.6 vs GPT-4.1
Claude Sonnet 4.6 is the stronger model overall, scoring 50.1 to 35.7 on the Noometry Index. GPT-4.1 costs 1.7× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.
Last verified . 35 shared benchmarks.
Summary
- They share 35 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 10 categories and GPT-4.1 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Sonnet 4.6 leads 46.1 to 11.7.
- The biggest single-benchmark swing is ARC-AGI-1: 86.5% for Claude Sonnet 4.6 and 5.5% for GPT-4.1.
- GPT-4.1 is cheaper at $2 / $8 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.6.
- GPT-4.1 accepts more context: 1.05M tokens versus 1M.
Side by side
| Claude Sonnet 4.6 | GPT-4.1 | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 50.1 | 35.7 |
| Released | 2026-02-17 | 2025-04-14 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 128K | 33K |
| Input $ / M tokens | $3 | $2 |
| Output $ / M tokens | $15 | $8 |
| Results tracked | 57 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 46.0 (#62), GPT-4.1: 34.2 (#228)
| Benchmark | Claude Sonnet 4.6 | GPT-4.1 |
|---|---|---|
| SWE-bench Verified | 75.2% | 48.5% |
| WeirdML | 66.1% | 39% |
| LMArena Coding | 1504 | 1391 |
| ALE-Bench | 1,327 | 558.1 |
| DeepSWE | 29.9% | — |
| FrontierCode | 24.3% | — |
| SWE-bench Verified (bash only) | — | 39.6% |
| Aider Polyglot | — | 52.4% |
| LMArena WebDev | 1521 | — |
| SciCode | 46.8% | — |
| CadEval | — | 42% |
Agentic & Tool Use Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 39.1 (#26), GPT-4.1: 34.4 (#40)
| Benchmark | Claude Sonnet 4.6 | GPT-4.1 |
|---|---|---|
| Terminal-Bench | 53.4% | — |
| APEX-Agents | 43% | — |
| Berkeley Function Calling Leaderboard | — | 54% |
| OSWorld 2.0 | 9.3% | — |
| DeepResearch Bench | 54.9% | — |
| OSWorld | 72.1% | — |
| ExploitBench | 23.6% | — |
| GBAEval | 48.8% | — |
| GDP.pdf | 18% | — |
| LMArena Search | 1221 | — |
| Vending-Bench 2 | 7,204 | — |
Reasoning Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 46.1 (#40), GPT-4.1: 11.7 (#334)
| Benchmark | Claude Sonnet 4.6 | GPT-4.1 |
|---|---|---|
| ARC-AGI-2 | 60.4% | 0.4% |
| ARC-AGI-1 | 86.5% | 5.5% |
| Chess Puzzles | 13% | 6% |
| LMArena Hard Prompts | 1485 | 1384 |
| DTBench | 89.9% | 68.3% |
| LMCA | 46.5% | 25.6% |
| Epoch Capabilities Index | 152.25 | 136.79 |
| ForecastBench | 62 | 61.5 |
| SimpleBench | — | 27% |
| Kagi LLM Benchmark | — | 52.3% |
| NYT Connections (extended) | 80.9% | — |
| CritPt | 3.1% | — |
| EnigmaEval | — | 2.2% |
| Thematic Generalization | 76.3% | — |
| Mystery Game Puzzles | 16% | — |
Math Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 51.9 (#41), GPT-4.1: 21.4 (#269)
| Benchmark | Claude Sonnet 4.6 | GPT-4.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 85.8% | 38.3% |
| LMArena Math | 1463 | 1369 |
| FrontierMath (Feb 2025 set) | 32.4% | 5.5% |
| FrontierMath Tier 4 (v1) | 8.3% | 0% |
| FrontierMath (Tiers 1-3) | — | 6% |
| ProofBench | 45% | — |
| Omni-MATH | — | 47.1% |
| MATH Level 5 | — | 83% |
Knowledge Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 51.6 (#60), GPT-4.1: 37.0 (#152)
| Benchmark | Claude Sonnet 4.6 | GPT-4.1 |
|---|---|---|
| GPQA Diamond | 87.4% | 66.9% |
| SimpleQA Verified | 35.5% | 31.1% |
| Vectara Hallucination Rate | 10.6% | 5.6% |
| LMArena Expert | 1500 | 1364 |
| Humanity's Last Exam | — | 5.4% |
| MMLU-Pro | — | 81.1% |
| GPQA (HELM) | — | 65.9% |
Multimodal Too close to call
Claude Sonnet 4.6: 38.0 (#61), GPT-4.1: 37.5 (#66)
| Benchmark | Claude Sonnet 4.6 | GPT-4.1 |
|---|---|---|
| LMArena Vision | 1283 | 1210 |
| GeoBench | — | 72% |
| Blueprint-Bench 2 | 6.7% | — |
| LMArena Document | 1482 | — |
Multilingual Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 54.6 (#39), GPT-4.1: 49.6 (#128)
| Benchmark | Claude Sonnet 4.6 | GPT-4.1 |
|---|---|---|
| LMArena Non-English | 1440 | 1370 |
| LMArena Chinese | 1491 | 1382 |
| LMArena French | 1465 | 1383 |
| LMArena German | 1428 | 1380 |
| LMArena Japanese | 1419 | 1320 |
| LMArena Korean | 1411 | 1339 |
| LMArena Russian | 1440 | 1377 |
| LMArena Spanish | 1465 | 1375 |
Instruction Following Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 77.6 (#23), GPT-4.1: 71.5 (#148)
| Benchmark | Claude Sonnet 4.6 | GPT-4.1 |
|---|---|---|
| LMArena Instruction Following | 1476 | 1367 |
| IFEval | — | 83.8% |
Long Context Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 45.3 (#40), GPT-4.1: 40.0 (#158)
| Benchmark | Claude Sonnet 4.6 | GPT-4.1 |
|---|---|---|
| LMArena Longer Query | 1479 | 1385 |
| Fiction.LiveBench | — | 63.9% |
Writing & Preference Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 70.4 (#22), GPT-4.1: 57.8 (#120)
| Benchmark | Claude Sonnet 4.6 | GPT-4.1 |
|---|---|---|
| LMArena Text | 1458 | 1383 |
| LMArena Creative Writing | 1435 | 1363 |
| EQ-Bench Creative Writing | 1810 | 1420 |
| LMArena Multi-Turn | 1464 | 1398 |
| WildBench | — | 85.4% |
| EQ-Bench 4 | 1207 | — |
Frequently asked questions
Is Claude Sonnet 4.6 better than GPT-4.1?
Claude Sonnet 4.6 is the stronger model overall, scoring 50.1 to 35.7 on the Noometry Index. GPT-4.1 costs 1.7× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 4.6 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 4.6 lists at $3 and $15.
Is Claude Sonnet 4.6 or GPT-4.1 better for coding?
Claude Sonnet 4.6 scores higher on coding benchmarks: 46.0 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 does, with 1.05M tokens against 1M.
How many benchmarks do Claude Sonnet 4.6 and GPT-4.1 share?
35 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and GPT-4.1 has 52.