Model comparison
Claude Sonnet 5 vs GPT-4 Turbo
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 30.5 on the Noometry Index.
Last verified . 28 shared benchmarks.
Summary
- They share 28 benchmarks with published results for both. Claude Sonnet 5 scores higher in 9 categories and GPT-4 Turbo in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5 leads 66.2 to 9.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 94.7% for Claude Sonnet 5 and 6.7% for GPT-4 Turbo.
- Claude Sonnet 5 is cheaper at $2 / $10 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
- Claude Sonnet 5 accepts more context: 1M tokens versus 128K.
Side by side
| Claude Sonnet 5 | GPT-4 Turbo | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 54.6 | 30.5 |
| Released | 2026-06-29 | 2023-11-06 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 128K |
| Max output | 128K | 4K |
| Input $ / M tokens | $2 | $10 |
| Output $ / M tokens | $10 | $30 |
| Results tracked | 51 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 5 leads
Claude Sonnet 5: 55.5 (#26), GPT-4 Turbo: 33.8 (#249)
| Benchmark | Claude Sonnet 5 | GPT-4 Turbo |
|---|---|---|
| WeirdML | 68.8% | 18% |
| LMArena Coding | 1483 | 1268 |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.7% | — |
| CursorBench | 34.1% | — |
| LMArena WebDev | 1541 | — |
| SciCode | 54.3% | — |
| GSO | 37.3% | — |
| BigCodeBench Instruct | — | 48.2% |
| BigCodeBench Complete | — | 58.2% |
| ALE-Bench | 1,463 | — |
| HumanEval+ | — | 86.6% |
| MBPP+ | — | 73.3% |
Agentic & Tool Use Not comparable
Claude Sonnet 5: 42.8 (#18), GPT-4 Turbo: —
| Benchmark | Claude Sonnet 5 | GPT-4 Turbo |
|---|---|---|
| APEX-Agents | 54.5% | — |
| GBAEval | 65.3% | — |
| LMArena Search | 1194 | — |
| METR Time Horizons | — | 36.7% |
| Vending-Bench 2 | 6,378 | — |
Reasoning Claude Sonnet 5 leads
Claude Sonnet 5: 49.1 (#39), GPT-4 Turbo: 15.3 (#317)
| Benchmark | Claude Sonnet 5 | GPT-4 Turbo |
|---|---|---|
| SimpleBench | 60.6% | 25.1% |
| Chess Puzzles | 35% | 6% |
| LMArena Hard Prompts | 1461 | 1251 |
| DTBench | 92.5% | 61.6% |
| LMCA | 50% | 9.8% |
| Epoch Capabilities Index | 156.21 | 127.25 |
| ForecastBench | 61.1 | 59.4 |
| NYT Connections (extended) | 75.1% | — |
| CritPt | 16.9% | — |
| Mystery Game Puzzles | 35% | — |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |
Math Claude Sonnet 5 leads
Claude Sonnet 5: 66.2 (#27), GPT-4 Turbo: 9.0 (#322)
| Benchmark | Claude Sonnet 5 | GPT-4 Turbo |
|---|---|---|
| FrontierMath (Tiers 1-3) | 65.6% | 0.7% |
| OTIS Mock AIME 2024-2025 | 94.7% | 6.7% |
| LMArena Math | 1467 | 1272 |
| FrontierMath Tier 4 | 29.3% | — |
| ProofBench | 77% | — |
| MATH Level 5 | — | 46.7% |
Knowledge Claude Sonnet 5 leads
Claude Sonnet 5: 55.6 (#47), GPT-4 Turbo: 24.3 (#268)
| Benchmark | Claude Sonnet 5 | GPT-4 Turbo |
|---|---|---|
| GPQA Diamond | 90.5% | 46.6% |
| LMArena Expert | 1490 | 1223 |
| SimpleQA Verified | 33.7% | — |
| Confabulations | — | 28.4% |
| MMLU | — | 81.3% |
Multimodal Claude Sonnet 5 leads
Claude Sonnet 5: 42.4 (#31), GPT-4 Turbo: 30.6 (#110)
| Benchmark | Claude Sonnet 5 | GPT-4 Turbo |
|---|---|---|
| LMArena Vision | 1274 | 1090 |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |
Multilingual Claude Sonnet 5 leads
Claude Sonnet 5: 53.8 (#55), GPT-4 Turbo: 40.5 (#216)
| Benchmark | Claude Sonnet 5 | GPT-4 Turbo |
|---|---|---|
| LMArena Non-English | 1431 | 1245 |
| LMArena Chinese | 1477 | 1242 |
| LMArena French | 1460 | 1276 |
| LMArena German | 1440 | 1259 |
| LMArena Japanese | 1422 | 1194 |
| LMArena Korean | 1411 | 1187 |
| LMArena Russian | 1451 | 1259 |
| LMArena Spanish | 1437 | 1260 |
Instruction Following Claude Sonnet 5 leads
Claude Sonnet 5: 76.3 (#41), GPT-4 Turbo: 65.8 (#216)
| Benchmark | Claude Sonnet 5 | GPT-4 Turbo |
|---|---|---|
| LMArena Instruction Following | 1452 | 1249 |
Long Context Claude Sonnet 5 leads
Claude Sonnet 5: 44.8 (#55), GPT-4 Turbo: 38.0 (#206)
| Benchmark | Claude Sonnet 5 | GPT-4 Turbo |
|---|---|---|
| LMArena Longer Query | 1463 | 1254 |
Writing & Preference Claude Sonnet 5 leads
Claude Sonnet 5: 69.2 (#25), GPT-4 Turbo: 47.7 (#206)
| Benchmark | Claude Sonnet 5 | GPT-4 Turbo |
|---|---|---|
| LMArena Text | 1442 | 1272 |
| LMArena Creative Writing | 1416 | 1269 |
| LMArena Multi-Turn | 1454 | 1267 |
| EQ-Bench Creative Writing | 1794 | — |
| EQ-Bench 4 | 1236 | — |
Frequently asked questions
Is Claude Sonnet 5 better than GPT-4 Turbo?
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 30.5 on the Noometry Index.
Which is cheaper, Claude Sonnet 5 or GPT-4 Turbo?
Claude Sonnet 5 is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; GPT-4 Turbo lists at $10 and $30.
Is Claude Sonnet 5 or GPT-4 Turbo better for coding?
Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
Claude Sonnet 5 does, with 1M tokens against 128K.
How many benchmarks do Claude Sonnet 5 and GPT-4 Turbo share?
28 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and GPT-4 Turbo has 36.