Model comparison
Claude 3.5 Sonnet vs GPT-4.5
GPT-4.5 is the stronger model overall, scoring 36.9 to 34.4 on the Noometry Index.
Last verified . 39 shared benchmarks.
Summary
- They share 39 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 2 categories and GPT-4.5 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-4.5 leads 31.0 to 18.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Claude 3.5 Sonnet and 37.8% for GPT-4.5.
Side by side
| Claude 3.5 Sonnet | GPT-4.5 | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 34.4 | 36.9 |
| Released | 2024-06-20 | 2025-02-27 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 60 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4.5 leads
Claude 3.5 Sonnet: 39.5 (#145), GPT-4.5: 41.8 (#102)
| Benchmark | Claude 3.5 Sonnet | GPT-4.5 |
|---|---|---|
| Aider Polyglot | 51.6% | 44.9% |
| WeirdML | 40% | 39.4% |
| LiveBench Coding | 67.1% | 75.2% |
| LMArena Coding | 1343 | 1397 |
| GSO | 4.6% | — |
| BigCodeBench Instruct | 46.8% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 32.1 (#61), GPT-4.5: 27.6 (#92)
| Benchmark | Claude 3.5 Sonnet | GPT-4.5 |
|---|---|---|
| Cybench | 17.5% | 17.5% |
| TheAgentCompany | 24% | — |
| BALROG | 32.6% | — |
| METR Time Horizons | 45.2% | — |
Reasoning Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 22.5 (#176), GPT-4.5: 14.1 (#320)
| Benchmark | Claude 3.5 Sonnet | GPT-4.5 |
|---|---|---|
| SimpleBench | 41.4% | 34.5% |
| EnigmaEval | 0.9% | 3.2% |
| LiveBench Reasoning | 56.7% | 71.1% |
| LMArena Hard Prompts | 1305 | 1404 |
| LiveBench Data Analysis | 55% | 64.3% |
| Epoch Capabilities Index | 133.55 | 136.74 |
| ForecastBench | 60.7 | 61.7 |
| LiveBench | 59% | 69% |
| ARC-AGI-2 | — | 0.8% |
| ARC-AGI-1 | — | 10.3% |
| DTBench | 67.8% | — |
Math GPT-4.5 leads
Claude 3.5 Sonnet: 18.0 (#282), GPT-4.5: 31.0 (#200)
| Benchmark | Claude 3.5 Sonnet | GPT-4.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 37.8% |
| LiveBench Math | 52.3% | 69.3% |
| LMArena Math | 1306 | 1412 |
| MATH Level 5 | 56.9% | 78.6% |
| Omni-MATH | 27.6% | — |
| FrontierMath (Feb 2025 set) | 2.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge GPT-4.5 leads
Claude 3.5 Sonnet: 28.5 (#236), GPT-4.5: 32.4 (#205)
| Benchmark | Claude 3.5 Sonnet | GPT-4.5 |
|---|---|---|
| GPQA Diamond | 55.3% | 68.7% |
| Humanity's Last Exam | 4.1% | 5.4% |
| Confabulations | 19.9% | 13.6% |
| LMArena Expert | 1264 | 1394 |
| MMLU-Pro | 77.7% | — |
| GPQA (HELM) | 56.5% | — |
| MMLU | 87.3% | — |
Multimodal GPT-4.5 leads
Claude 3.5 Sonnet: 26.0 (#115), GPT-4.5: 37.0 (#68)
| Benchmark | Claude 3.5 Sonnet | GPT-4.5 |
|---|---|---|
| LMArena Vision | 1125 | 1195 |
| VPCT | 33% | 45% |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
Multilingual GPT-4.5 leads
Claude 3.5 Sonnet: 43.4 (#180), GPT-4.5: 52.7 (#78)
| Benchmark | Claude 3.5 Sonnet | GPT-4.5 |
|---|---|---|
| LMArena Non-English | 1283 | 1413 |
| LMArena Chinese | 1271 | 1421 |
| LMArena French | 1304 | 1417 |
| LMArena German | 1297 | 1457 |
| LMArena Japanese | 1234 | 1416 |
| LMArena Korean | 1200 | 1392 |
| LMArena Russian | 1305 | 1419 |
| LMArena Spanish | 1289 | — |
Instruction Following GPT-4.5 leads
Claude 3.5 Sonnet: 69.0 (#177), GPT-4.5: 72.8 (#129)
| Benchmark | Claude 3.5 Sonnet | GPT-4.5 |
|---|---|---|
| LiveBench Instruction Following | 69.3% | 72.3% |
| LMArena Instruction Following | 1297 | 1404 |
| IFEval | 85.5% | — |
Long Context Too close to call
Claude 3.5 Sonnet: 39.9 (#162), GPT-4.5: 40.4 (#150)
| Benchmark | Claude 3.5 Sonnet | GPT-4.5 |
|---|---|---|
| LMArena Longer Query | 1311 | 1406 |
| Fiction.LiveBench | — | 63.9% |
Writing & Preference GPT-4.5 leads
Claude 3.5 Sonnet: 53.0 (#159), GPT-4.5: 57.1 (#129)
| Benchmark | Claude 3.5 Sonnet | GPT-4.5 |
|---|---|---|
| LMArena Text | 1298 | 1417 |
| LMArena Creative Writing | 1292 | 1394 |
| Short-Story Creative Writing | 80.3% | 75.6% |
| EQ-Bench Creative Writing | 1451 | 1258 |
| LMArena Multi-Turn | 1326 | 1444 |
| LiveBench Language | 53.8% | 61.5% |
| WildBench | 79.2% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than GPT-4.5?
GPT-4.5 is the stronger model overall, scoring 36.9 to 34.4 on the Noometry Index.
Is Claude 3.5 Sonnet or GPT-4.5 better for coding?
GPT-4.5 scores higher on coding benchmarks: 41.8 versus 39.5 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and GPT-4.5 share?
39 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and GPT-4.5 has 42.