Model comparison
Claude Sonnet 5 vs o3
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 47.5 on the Noometry Index.
Last verified . 35 shared benchmarks.
Summary
- They share 35 benchmarks with published results for both. Claude Sonnet 5 scores higher in 9 categories and o3 in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Sonnet 5 leads 49.1 to 32.0.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 65.6% for Claude Sonnet 5 and 33.3% for o3.
- o3 is cheaper at $2 / $8 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.
- Claude Sonnet 5 accepts more context: 1M tokens versus 200K.
Side by side
| Claude Sonnet 5 | o3 | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 54.6 | 47.5 |
| Released | 2026-06-29 | 2025-04-16 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 200K |
| Max output | 128K | 100K |
| Input $ / M tokens | $2 | $2 |
| Output $ / M tokens | $10 | $8 |
| Results tracked | 51 | 63 |
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), o3: 46.8 (#64)
| Benchmark | Claude Sonnet 5 | o3 |
|---|---|---|
| GSO | 37.3% | 8.8% |
| WeirdML | 68.8% | 52.4% |
| LMArena Coding | 1483 | 1408 |
| ALE-Bench | 1,463 | 933.55 |
| SWE-bench Verified | — | 62.3% |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.7% | — |
| SWE-bench Verified (bash only) | — | 58.4% |
| Aider Polyglot | — | 81.3% |
| CursorBench | 34.1% | — |
| LMArena WebDev | 1541 | — |
| SciCode | 54.3% | — |
| CadEval | — | 74% |
Agentic & Tool Use Claude Sonnet 5 leads
Claude Sonnet 5: 42.8 (#18), o3: 34.5 (#44)
| Benchmark | Claude Sonnet 5 | o3 |
|---|---|---|
| LMArena Search | 1194 | 1144 |
| APEX-Agents | 54.5% | — |
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 30.8% |
| DeepResearch Bench | — | 45.2% |
| OSWorld | — | 23% |
| GBAEval | 65.3% | — |
| METR Time Horizons | — | 65.4% |
| Vending-Bench 2 | 6,378 | — |
Reasoning Claude Sonnet 5 leads
Claude Sonnet 5: 49.1 (#39), o3: 32.0 (#78)
| Benchmark | Claude Sonnet 5 | o3 |
|---|---|---|
| SimpleBench | 60.6% | 53.1% |
| CritPt | 16.9% | 1.4% |
| Chess Puzzles | 35% | 38% |
| LMArena Hard Prompts | 1461 | 1402 |
| Mystery Game Puzzles | 35% | 29% |
| DTBench | 92.5% | 84.8% |
| LMCA | 50% | 39.7% |
| Epoch Capabilities Index | 156.21 | 146.86 |
| ForecastBench | 61.1 | 62.5 |
| ARC-AGI-2 | — | 6.5% |
| Kagi LLM Benchmark | — | 67.6% |
| NYT Connections (extended) | 75.1% | — |
| ARC-AGI-1 | — | 60.8% |
| EnigmaEval | — | 13.1% |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |
Math Claude Sonnet 5 leads
Claude Sonnet 5: 66.2 (#27), o3: 50.2 (#58)
| Benchmark | Claude Sonnet 5 | o3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 65.6% | 33.3% |
| OTIS Mock AIME 2024-2025 | 94.7% | 84.4% |
| LMArena Math | 1467 | 1426 |
| FrontierMath Tier 4 | 29.3% | — |
| ProofBench | 77% | — |
| Omni-MATH | — | 71.4% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 18.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge Claude Sonnet 5 leads
Claude Sonnet 5: 55.6 (#47), o3: 54.6 (#52)
| Benchmark | Claude Sonnet 5 | o3 |
|---|---|---|
| GPQA Diamond | 90.5% | 81.8% |
| SimpleQA Verified | 33.7% | 49.4% |
| LMArena Expert | 1490 | 1402 |
| Humanity's Last Exam | — | 20.3% |
| MMLU-Pro | — | 85.9% |
| Confabulations | — | 14.4% |
| GPQA (HELM) | — | 75.3% |
Multimodal Too close to call
Claude Sonnet 5: 42.4 (#31), o3: 41.4 (#36)
| Benchmark | Claude Sonnet 5 | o3 |
|---|---|---|
| LMArena Vision | 1274 | 1214 |
| GeoBench | — | 74% |
| VPCT | — | 52% |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |
Multilingual Claude Sonnet 5 leads
Claude Sonnet 5: 53.8 (#55), o3: 51.7 (#105)
| Benchmark | Claude Sonnet 5 | o3 |
|---|---|---|
| LMArena Non-English | 1431 | 1401 |
| LMArena Chinese | 1477 | 1437 |
| LMArena French | 1460 | 1430 |
| LMArena German | 1440 | 1420 |
| LMArena Japanese | 1422 | 1403 |
| LMArena Korean | 1411 | 1370 |
| LMArena Russian | 1451 | 1406 |
| LMArena Spanish | 1437 | 1395 |
Instruction Following Claude Sonnet 5 leads
Claude Sonnet 5: 76.3 (#41), o3: 72.8 (#127)
| Benchmark | Claude Sonnet 5 | o3 |
|---|---|---|
| LMArena Instruction Following | 1452 | 1368 |
| IFEval | — | 86.9% |
Long Context o3 leads
Claude Sonnet 5: 44.8 (#55), o3: 53.3 (#6)
| Benchmark | Claude Sonnet 5 | o3 |
|---|---|---|
| LMArena Longer Query | 1463 | 1372 |
| Fiction.LiveBench | — | 88.9% |
| CL-bench | — | 17.8% |
Writing & Preference Claude Sonnet 5 leads
Claude Sonnet 5: 69.2 (#25), o3: 63.5 (#64)
| Benchmark | Claude Sonnet 5 | o3 |
|---|---|---|
| LMArena Text | 1442 | 1410 |
| LMArena Creative Writing | 1416 | 1359 |
| EQ-Bench Creative Writing | 1794 | 1676 |
| LMArena Multi-Turn | 1454 | 1405 |
| Short-Story Creative Writing | — | 83.9% |
| WildBench | — | 86.1% |
| EQ-Bench 4 | 1236 | — |
Frequently asked questions
Is Claude Sonnet 5 better than o3?
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 47.5 on the Noometry Index.
Which is cheaper, Claude Sonnet 5 or o3?
o3 is cheaper. It lists at $2 per million input tokens and $8 per million output tokens; Claude Sonnet 5 lists at $2 and $10.
Is Claude Sonnet 5 or o3 better for coding?
Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 46.8 in the Noometry coding category.
Which has the bigger context window?
Claude Sonnet 5 does, with 1M tokens against 200K.
How many benchmarks do Claude Sonnet 5 and o3 share?
35 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and o3 has 63.