Model comparison
Claude 3.7 Sonnet vs GPT-5.4 mini
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 39.5 on the Noometry Index.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 2 categories and GPT-5.4 mini in 8 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.4 mini leads 30.4 to 18.6.
- The biggest single-benchmark swing is ARC-AGI-1: 28.6% for Claude 3.7 Sonnet and 63.7% for GPT-5.4 mini.
Side by side
| Claude 3.7 Sonnet | GPT-5.4 mini | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 39.5 | 45.0 |
| Released | 2025-02-24 | 2026-03-17 |
| Weights | Proprietary | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.75 |
| Output $ / M tokens | — | $4.50 |
| Results tracked | 58 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 mini leads
Claude 3.7 Sonnet: 40.6 (#136), GPT-5.4 mini: 45.2 (#72)
| Benchmark | Claude 3.7 Sonnet | GPT-5.4 mini |
|---|---|---|
| LMArena Coding | 1361 | 1438 |
| SWE-bench Verified | 61% | — |
| FrontierCode | — | 27% |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| LMArena WebDev | — | 1397 |
| SciCode | — | 49.9% |
| GSO | 3.8% | — |
| WeirdML | — | 60.3% |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
| ALE-Bench | — | 1,189 |
Agentic & Tool Use Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 34.1 (#50), GPT-5.4 mini: 29.9 (#81)
| Benchmark | Claude 3.7 Sonnet | GPT-5.4 mini |
|---|---|---|
| DeepResearch Bench | 43.6% | 36.3% |
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| OSWorld | 35.8% | — |
| METR Time Horizons | 60% | — |
Reasoning GPT-5.4 mini leads
Claude 3.7 Sonnet: 18.6 (#277), GPT-5.4 mini: 30.4 (#85)
| Benchmark | Claude 3.7 Sonnet | GPT-5.4 mini |
|---|---|---|
| ARC-AGI-2 | 0.9% | 18.9% |
| ARC-AGI-1 | 28.6% | 63.7% |
| LMArena Hard Prompts | 1333 | 1424 |
| Epoch Capabilities Index | 141.16 | 148.84 |
| ForecastBench | 61.8 | 57 |
| SimpleBench | 46.4% | — |
| Kagi LLM Benchmark | — | 37.9% |
| NYT Connections (extended) | — | 61.8% |
| CritPt | — | 10% |
| Chess Puzzles | — | 24% |
| EnigmaEval | 4.2% | — |
| Thematic Generalization | — | 61.7% |
| LiveBench Reasoning | 87.8% | — |
| Mystery Game Puzzles | — | 11% |
| DTBench | — | 80% |
| LiveBench Data Analysis | 74% | — |
| LMCA | — | 40.8% |
| LiveBench | 76.1% | — |
Math GPT-5.4 mini leads
Claude 3.7 Sonnet: 37.5 (#153), GPT-5.4 mini: 45.5 (#75)
| Benchmark | Claude 3.7 Sonnet | GPT-5.4 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 88.9% |
| LMArena Math | 1337 | 1419 |
| FrontierMath (Feb 2025 set) | 4.1% | 28.3% |
| FrontierMath (Tiers 1-3) | — | 51.2% |
| FrontierMath Tier 4 | — | 9.8% |
| ProofBench | — | 21% |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| MATH Level 5 | 91.2% | — |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge GPT-5.4 mini leads
Claude 3.7 Sonnet: 39.8 (#130), GPT-5.4 mini: 51.5 (#67)
| Benchmark | Claude 3.7 Sonnet | GPT-5.4 mini |
|---|---|---|
| GPQA Diamond | 79.7% | 86.9% |
| LMArena Expert | 1321 | 1435 |
| Humanity's Last Exam | 8% | — |
| SimpleQA Verified | — | 29.4% |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| Vectara Hallucination Rate | — | 5.5% |
| GPQA (HELM) | 60.8% | — |
Multimodal GPT-5.4 mini leads
Claude 3.7 Sonnet: 33.7 (#95), GPT-5.4 mini: 39.7 (#56)
| Benchmark | Claude 3.7 Sonnet | GPT-5.4 mini |
|---|---|---|
| LMArena Vision | 1169 | 1245 |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |
Multilingual GPT-5.4 mini leads
Claude 3.7 Sonnet: 44.1 (#179), GPT-5.4 mini: 51.9 (#96)
| Benchmark | Claude 3.7 Sonnet | GPT-5.4 mini |
|---|---|---|
| LMArena Non-English | 1296 | 1405 |
| LMArena Chinese | 1299 | 1446 |
| LMArena French | 1303 | 1440 |
| LMArena German | 1301 | 1409 |
| LMArena Japanese | 1267 | 1374 |
| LMArena Korean | 1249 | 1368 |
| LMArena Russian | 1311 | 1417 |
| LMArena Spanish | 1298 | 1405 |
Instruction Following GPT-5.4 mini leads
Claude 3.7 Sonnet: 72.9 (#125), GPT-5.4 mini: 74.1 (#102)
| Benchmark | Claude 3.7 Sonnet | GPT-5.4 mini |
|---|---|---|
| LMArena Instruction Following | 1352 | 1405 |
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.3 (#10), GPT-5.4 mini: 43.0 (#112)
| Benchmark | Claude 3.7 Sonnet | GPT-5.4 mini |
|---|---|---|
| LMArena Longer Query | 1373 | 1407 |
| Fiction.LiveBench | 83.3% | — |
Writing & Preference GPT-5.4 mini leads
Claude 3.7 Sonnet: 54.4 (#150), GPT-5.4 mini: 64.0 (#58)
| Benchmark | Claude 3.7 Sonnet | GPT-5.4 mini |
|---|---|---|
| LMArena Text | 1314 | 1412 |
| LMArena Creative Writing | 1332 | 1370 |
| EQ-Bench Creative Writing | 1412 | 1665 |
| LMArena Multi-Turn | 1339 | 1429 |
| Short-Story Creative Writing | 81.1% | — |
| WildBench | 81.4% | — |
| LiveBench Language | 59.9% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than GPT-5.4 mini?
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 39.5 on the Noometry Index.
Is Claude 3.7 Sonnet or GPT-5.4 mini better for coding?
GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 40.6 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and GPT-5.4 mini share?
27 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and GPT-5.4 mini has 46.