# Claude Sonnet 5 vs o3

> Claude Sonnet 5 is the stronger model overall, scoring 54.5 to 47.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-sonnet-5-vs-o3
- Last updated: 2026-10-10
- Shared benchmarks: 35

## Summary

- They share 35 benchmarks with published results for both. Claude Sonnet 5 scores higher in 9 categories and o3 in 1 category; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5 leads 66.1 to 48.9.
- 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.

## Snapshot

| | Claude Sonnet 5 | o3 |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 54.5 | 47.4 |
| Rank | 26 | 53 |
| Context | 1M | 200K |
| Input $/M | $2 | $2 |
| Output $/M | $10 | $8 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Sonnet 5: 55.5 (#20)
- o3: 47.3 (#57)

| 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 | 1540 | — |
| SciCode | 53.6% | — |
| CadEval | — | 74% |

## Agentic & Tool Use

- Claude Sonnet 5: 42.7 (#16)
- o3: 34.3 (#42)

| 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: 48.2 (#37)
- o3: 32.1 (#66)

| 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 | 156.34 | 146.88 |
| 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: 66.1 (#21)
- o3: 48.9 (#49)

| 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: 55.7 (#42)
- o3: 54.5 (#47)

| Benchmark | Claude Sonnet 5 | o3 |
|---|---|---|
| GPQA Diamond | 90.5% | 81.8% |
| SimpleQA Verified | 33.7% | 49.4% |
| LMArena Expert | 1491 | 1403 |
| Humanity's Last Exam | — | 20.3% |
| MMLU-Pro | — | 85.9% |
| Confabulations | — | 14.4% |
| GPQA (HELM) | — | 75.3% |

## Multimodal

- Claude Sonnet 5: 42.4 (#26)
- o3: 40.7 (#35)

| Benchmark | Claude Sonnet 5 | o3 |
|---|---|---|
| LMArena Vision | 1275 | 1214 |
| GeoBench | — | 74% |
| VPCT | — | 52% |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |

## Multilingual

- Claude Sonnet 5: 54.0 (#55)
- o3: 51.9 (#99)

| Benchmark | Claude Sonnet 5 | o3 |
|---|---|---|
| LMArena Non-English | 1431 | 1402 |
| LMArena Chinese | 1475 | 1438 |
| LMArena French | 1457 | 1430 |
| LMArena German | 1448 | 1420 |
| LMArena Japanese | 1422 | 1404 |
| LMArena Korean | 1411 | 1371 |
| LMArena Russian | 1452 | 1407 |
| LMArena Spanish | 1436 | 1395 |

## Instruction Following

- Claude Sonnet 5: 76.6 (#39)
- o3: 73.0 (#122)

| Benchmark | Claude Sonnet 5 | o3 |
|---|---|---|
| LMArena Instruction Following | 1453 | 1368 |
| IFEval | — | 86.9% |

## Long Context

- Claude Sonnet 5: 44.8 (#53)
- o3: 53.2 (#6)

| Benchmark | Claude Sonnet 5 | o3 |
|---|---|---|
| LMArena Longer Query | 1464 | 1372 |
| Fiction.LiveBench | — | 88.9% |
| CL-bench | — | 17.8% |

## Writing & Preference

- Claude Sonnet 5: 69.4 (#24)
- o3: 63.7 (#62)

| Benchmark | Claude Sonnet 5 | o3 |
|---|---|---|
| LMArena Text | 1443 | 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 | — |

## FAQ

### Is Claude Sonnet 5 better than o3?

Claude Sonnet 5 is the stronger model overall, scoring 54.5 to 47.4 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 47.3 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.