Model comparison
Claude Sonnet 4 vs GPT-4
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 29.1 on the Noometry Index.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. Claude Sonnet 4 scores higher in 7 categories and GPT-4 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 4 leads 43.3 to 10.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 71.1% for Claude Sonnet 4 and 1.1% for GPT-4.
- Claude Sonnet 4 is cheaper at $3 / $15 per million input/output tokens, against $30 / $60 for GPT-4.
- Claude Sonnet 4 accepts more context: 200K tokens versus 8K.
Side by side
| Claude Sonnet 4 | GPT-4 | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 40.8 | 29.1 |
| Released | 2025-05-22 | 2023-03-14 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 8K |
| Max output | 64K | 8K |
| Input $ / M tokens | $3 | $30 |
| Output $ / M tokens | $15 | $60 |
| Results tracked | 58 | 38 |
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: 31.6 (#283)
| Benchmark | Claude Sonnet 4 | GPT-4 |
|---|---|---|
| WeirdML | 46.1% | 12.4% |
| LMArena Coding | 1414 | 1254 |
| SWE-bench Verified (bash only) | 64.9% | — |
| Aider Polyglot | 61.3% | — |
| SciCode | 40% | — |
| GSO | 4.9% | — |
| BigCodeBench Instruct | — | 46% |
| BigCodeBench Complete | — | 57.2% |
| ALE-Bench | 655.35 | — |
| HumanEval+ | — | 79.3% |
Agentic & Tool Use Not comparable
Claude Sonnet 4: 38.5 (#31), GPT-4: —
| Benchmark | Claude Sonnet 4 | GPT-4 |
|---|---|---|
| METR Time Horizons | 62% | 36.1% |
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
Reasoning Claude Sonnet 4 leads
Claude Sonnet 4: 22.9 (#187), GPT-4: 17.8 (#289)
| Benchmark | Claude Sonnet 4 | GPT-4 |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1241 |
| DTBench | 77.1% | 62.7% |
| LMCA | 29% | 17.1% |
| Epoch Capabilities Index | 141.69 | 125.89 |
| ForecastBench | 60.2 | 57.8 |
| ARC-AGI-2 | 5.9% | — |
| SimpleBench | 45.5% | — |
| Kagi LLM Benchmark | 73% | — |
| ARC-AGI-1 | 40% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | — | 4% |
| EnigmaEval | 3.1% | — |
| Mystery Game Puzzles | — | 12% |
| BIG-Bench Hard | — | 75.1% |
| HellaSwag | — | 95.3% |
| WinoGrande | — | 87.5% |
Math Claude Sonnet 4 leads
Claude Sonnet 4: 43.3 (#80), GPT-4: 10.8 (#309)
| Benchmark | Claude Sonnet 4 | GPT-4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 1.1% |
| LMArena Math | 1375 | 1269 |
| MATH Level 5 | 84.4% | 23% |
| Omni-MATH | 60.2% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
| GSM8K | — | 92% |
Knowledge Claude Sonnet 4 leads
Claude Sonnet 4: 41.8 (#108), GPT-4: 18.4 (#282)
| Benchmark | Claude Sonnet 4 | GPT-4 |
|---|---|---|
| GPQA Diamond | 79.2% | 35.7% |
| LMArena Expert | 1372 | 1211 |
| Humanity's Last Exam | 7.8% | — |
| MMLU-Pro | 84.3% | — |
| Confabulations | 13.2% | — |
| Vectara Hallucination Rate | 10.3% | — |
| GPQA (HELM) | 70.6% | — |
| MMLU | — | 86.4% |
| TriviaQA | — | 84.8% |
Multimodal Not comparable
Claude Sonnet 4: 26.2 (#121), GPT-4: —
| Benchmark | Claude Sonnet 4 | GPT-4 |
|---|---|---|
| LMArena Vision | 1191 | — |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |
Multilingual Claude Sonnet 4 leads
Claude Sonnet 4: 46.7 (#156), GPT-4: 40.6 (#215)
| Benchmark | Claude Sonnet 4 | GPT-4 |
|---|---|---|
| LMArena Non-English | 1333 | 1246 |
| LMArena Chinese | 1350 | 1242 |
| LMArena French | 1363 | 1283 |
| LMArena German | 1331 | 1251 |
| LMArena Japanese | 1302 | 1209 |
| LMArena Korean | 1291 | 1184 |
| LMArena Russian | 1355 | 1251 |
| LMArena Spanish | 1357 | 1261 |
Instruction Following Claude Sonnet 4 leads
Claude Sonnet 4: 71.7 (#145), GPT-4: 65.3 (#222)
| Benchmark | Claude Sonnet 4 | GPT-4 |
|---|---|---|
| LMArena Instruction Following | 1376 | 1241 |
| IFEval | 84% | — |
Long Context GPT-4 leads
Claude Sonnet 4: 33.7 (#259), GPT-4: 37.7 (#212)
| Benchmark | Claude Sonnet 4 | GPT-4 |
|---|---|---|
| LMArena Longer Query | 1398 | 1244 |
| Fiction.LiveBench | 46.9% | — |
Writing & Preference Claude Sonnet 4 leads
Claude Sonnet 4: 57.1 (#132), GPT-4: 34.9 (#268)
| Benchmark | Claude Sonnet 4 | GPT-4 |
|---|---|---|
| LMArena Text | 1351 | 1263 |
| LMArena Creative Writing | 1345 | 1244 |
| EQ-Bench Creative Writing | 1483 | 752 |
| LMArena Multi-Turn | 1376 | 1257 |
| Short-Story Creative Writing | 81.4% | — |
| WildBench | 83.8% | — |
Frequently asked questions
Is Claude Sonnet 4 better than GPT-4?
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 29.1 on the Noometry Index.
Which is cheaper, Claude Sonnet 4 or GPT-4?
Claude Sonnet 4 is cheaper. It lists at $3 per million input tokens and $15 per million output tokens; GPT-4 lists at $30 and $60.
Is Claude Sonnet 4 or GPT-4 better for coding?
Claude Sonnet 4 scores higher on coding benchmarks: 43.5 versus 31.6 in the Noometry coding category.
Which has the bigger context window?
Claude Sonnet 4 does, with 200K tokens against 8K.
How many benchmarks do Claude Sonnet 4 and GPT-4 share?
27 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and GPT-4 has 38.