Model comparison
Claude Sonnet 5 vs GPT-4.5
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 37.2 on the Noometry Index.
Last verified . 24 shared benchmarks.
Summary
- They share 24 benchmarks with published results for both. Claude Sonnet 5 scores higher in 10 categories and GPT-4.5 in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Sonnet 5 leads 49.1 to 13.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 94.7% for Claude Sonnet 5 and 37.8% for GPT-4.5.
Side by side
| Claude Sonnet 5 | GPT-4.5 | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 54.6 | 37.2 |
| Released | 2026-06-29 | 2025-02-27 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | — |
| Max output | 128K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 51 | 42 |
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-4.5: 42.2 (#109)
| Benchmark | Claude Sonnet 5 | GPT-4.5 |
|---|---|---|
| WeirdML | 68.8% | 39.4% |
| LMArena Coding | 1483 | 1396 |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.7% | — |
| Aider Polyglot | — | 44.9% |
| CursorBench | 34.1% | — |
| LMArena WebDev | 1541 | — |
| SciCode | 54.3% | — |
| GSO | 37.3% | — |
| LiveBench Coding | — | 75.2% |
| ALE-Bench | 1,463 | — |
Agentic & Tool Use Claude Sonnet 5 leads
Claude Sonnet 5: 42.8 (#18), GPT-4.5: 27.9 (#97)
| Benchmark | Claude Sonnet 5 | GPT-4.5 |
|---|---|---|
| APEX-Agents | 54.5% | — |
| Cybench | — | 17.5% |
| GBAEval | 65.3% | — |
| LMArena Search | 1194 | — |
| Vending-Bench 2 | 6,378 | — |
Reasoning Claude Sonnet 5 leads
Claude Sonnet 5: 49.1 (#39), GPT-4.5: 13.9 (#330)
| Benchmark | Claude Sonnet 5 | GPT-4.5 |
|---|---|---|
| SimpleBench | 60.6% | 34.5% |
| LMArena Hard Prompts | 1461 | 1403 |
| Epoch Capabilities Index | 156.21 | 136.74 |
| ForecastBench | 61.1 | 61.7 |
| ARC-AGI-2 | — | 0.8% |
| NYT Connections (extended) | 75.1% | — |
| ARC-AGI-1 | — | 10.3% |
| CritPt | 16.9% | — |
| Chess Puzzles | 35% | — |
| EnigmaEval | — | 3.2% |
| LiveBench Reasoning | — | 71.1% |
| Mystery Game Puzzles | 35% | — |
| DTBench | 92.5% | — |
| LiveBench Data Analysis | — | 64.3% |
| LMCA | 50% | — |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |
| LiveBench | — | 69% |
Math Claude Sonnet 5 leads
Claude Sonnet 5: 66.2 (#27), GPT-4.5: 32.6 (#211)
| Benchmark | Claude Sonnet 5 | GPT-4.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 94.7% | 37.8% |
| LMArena Math | 1467 | 1412 |
| FrontierMath (Tiers 1-3) | 65.6% | — |
| FrontierMath Tier 4 | 29.3% | — |
| ProofBench | 77% | — |
| LiveBench Math | — | 69.3% |
| MATH Level 5 | — | 78.6% |
Knowledge Claude Sonnet 5 leads
Claude Sonnet 5: 55.6 (#47), GPT-4.5: 32.5 (#211)
| Benchmark | Claude Sonnet 5 | GPT-4.5 |
|---|---|---|
| GPQA Diamond | 90.5% | 68.7% |
| LMArena Expert | 1490 | 1394 |
| Humanity's Last Exam | — | 5.4% |
| SimpleQA Verified | 33.7% | — |
| Confabulations | — | 13.6% |
Multimodal Claude Sonnet 5 leads
Claude Sonnet 5: 42.4 (#31), GPT-4.5: 37.6 (#71)
| Benchmark | Claude Sonnet 5 | GPT-4.5 |
|---|---|---|
| LMArena Vision | 1274 | 1195 |
| VPCT | — | 45% |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |
Multilingual Claude Sonnet 5 leads
Claude Sonnet 5: 53.8 (#55), GPT-4.5: 52.5 (#83)
| Benchmark | Claude Sonnet 5 | GPT-4.5 |
|---|---|---|
| LMArena Non-English | 1431 | 1413 |
| LMArena Chinese | 1477 | 1421 |
| LMArena French | 1460 | 1418 |
| LMArena German | 1440 | 1457 |
| LMArena Japanese | 1422 | 1416 |
| LMArena Korean | 1411 | 1392 |
| LMArena Russian | 1451 | 1419 |
| LMArena Spanish | 1437 | — |
Instruction Following Claude Sonnet 5 leads
Claude Sonnet 5: 76.3 (#41), GPT-4.5: 72.6 (#134)
| Benchmark | Claude Sonnet 5 | GPT-4.5 |
|---|---|---|
| LMArena Instruction Following | 1452 | 1404 |
| LiveBench Instruction Following | — | 72.3% |
Long Context Claude Sonnet 5 leads
Claude Sonnet 5: 44.8 (#55), GPT-4.5: 40.4 (#155)
| Benchmark | Claude Sonnet 5 | GPT-4.5 |
|---|---|---|
| LMArena Longer Query | 1463 | 1406 |
| Fiction.LiveBench | — | 63.9% |
Writing & Preference Claude Sonnet 5 leads
Claude Sonnet 5: 69.2 (#25), GPT-4.5: 56.9 (#134)
| Benchmark | Claude Sonnet 5 | GPT-4.5 |
|---|---|---|
| LMArena Text | 1442 | 1417 |
| LMArena Creative Writing | 1416 | 1394 |
| EQ-Bench Creative Writing | 1794 | 1258 |
| LMArena Multi-Turn | 1454 | 1444 |
| Short-Story Creative Writing | — | 75.6% |
| EQ-Bench 4 | 1236 | — |
| LiveBench Language | — | 61.5% |
Frequently asked questions
Is Claude Sonnet 5 better than GPT-4.5?
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 37.2 on the Noometry Index.
Is Claude Sonnet 5 or GPT-4.5 better for coding?
Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 42.2 in the Noometry coding category.
How many benchmarks do Claude Sonnet 5 and GPT-4.5 share?
24 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and GPT-4.5 has 42.