# Claude 3 Opus vs o3-mini

> o3-mini is the stronger model overall, scoring 36.7 to 29.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-opus-vs-o3-mini
- Last updated: 2026-10-11
- Shared benchmarks: 37

## Summary

- They share 37 benchmarks with published results for both. Claude 3 Opus scores higher in 1 category and o3-mini in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3-mini leads 38.3 to 24.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.7% for Claude 3 Opus and 76.9% for o3-mini.

## Snapshot

| | Claude 3 Opus | o3-mini |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 29.5 | 36.7 |
| Rank | 310 | 212 |
| Context | — | 200K |
| Input $/M | — | $1.10 |
| Output $/M | — | $4.40 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3 Opus: 32.9 (#267)
- o3-mini: 40.8 (#132)

| Benchmark | Claude 3 Opus | o3-mini |
|---|---|---|
| WeirdML | 19.2% | 43.7% |
| LiveBench Coding | 38.6% | 82.7% |
| LMArena Coding | 1264 | 1378 |
| Aider Polyglot | — | 60.4% |
| SciCode | — | 39.8% |
| GSO | — | 1.3% |
| BigCodeBench Instruct | 45.5% | — |
| BigCodeBench Complete | 57.4% | — |
| CadEval | — | 54% |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |

## Agentic & Tool Use

- Claude 3 Opus: 24.6 (#116)
- o3-mini: 29.6 (#84)

| Benchmark | Claude 3 Opus | o3-mini |
|---|---|---|
| Cybench | 10% | 22.5% |
| METR Time Horizons | 29.5% | — |

## Reasoning

- Claude 3 Opus: 14.6 (#324)
- o3-mini: 16.3 (#305)

| Benchmark | Claude 3 Opus | o3-mini |
|---|---|---|
| SimpleBench | 23.5% | 22.8% |
| Chess Puzzles | 5% | 17% |
| LiveBench Reasoning | 40.6% | 89.6% |
| LMArena Hard Prompts | 1245 | 1366 |
| DTBench | 61.6% | 68.8% |
| LiveBench Data Analysis | 57.9% | 70.6% |
| LMCA | 17% | 19% |
| Epoch Capabilities Index | 126.91 | 140.34 |
| ForecastBench | 58.4 | 59.6 |
| LiveBench | 49.2% | 75.9% |
| ARC-AGI-2 | — | 3% |
| ARC-AGI-1 | — | 34.5% |
| CritPt | — | 0.3% |
| EnigmaEval | 0.8% | — |
| Mystery Game Puzzles | — | 7% |
| WinoGrande | 88.5% | — |

## Math

- Claude 3 Opus: 14.8 (#299)
- o3-mini: 28.1 (#244)

| Benchmark | Claude 3 Opus | o3-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 76.9% |
| LiveBench Math | 43.6% | 77.3% |
| LMArena Math | 1273 | 1396 |
| MATH Level 5 | 37.5% | 96.5% |
| FrontierMath (Tiers 1-3) | — | 18.6% |
| FrontierMath Tier 4 | — | 0% |
| FrontierMath (Feb 2025 set) | — | 12.4% |
| FrontierMath Tier 4 (v1) | — | 4.2% |

## Knowledge

- Claude 3 Opus: 24.5 (#267)
- o3-mini: 38.3 (#146)

| Benchmark | Claude 3 Opus | o3-mini |
|---|---|---|
| GPQA Diamond | 47.2% | 77% |
| SimpleQA Verified | 12.6% | 15.3% |
| Confabulations | 22.7% | 17.9% |
| LMArena Expert | 1223 | 1364 |
| MMLU | 84.6% | — |

## Multimodal

- Claude 3 Opus: 27.1 (#116)
- o3-mini: —

| Benchmark | Claude 3 Opus | o3-mini |
|---|---|---|
| LMArena Vision | 1023 | — |

## Multilingual

- Claude 3 Opus: 41.4 (#207)
- o3-mini: 45.7 (#164)

| Benchmark | Claude 3 Opus | o3-mini |
|---|---|---|
| LMArena Non-English | 1258 | 1319 |
| LMArena Chinese | 1248 | 1379 |
| LMArena French | 1275 | 1334 |
| LMArena German | 1258 | 1303 |
| LMArena Japanese | 1204 | 1286 |
| LMArena Korean | 1187 | 1314 |
| LMArena Russian | 1280 | 1304 |
| LMArena Spanish | 1246 | 1321 |

## Instruction Following

- Claude 3 Opus: 64.1 (#228)
- o3-mini: 75.1 (#72)

| Benchmark | Claude 3 Opus | o3-mini |
|---|---|---|
| LiveBench Instruction Following | 63.9% | 84.4% |
| LMArena Instruction Following | 1248 | 1337 |

## Long Context

- Claude 3 Opus: 38.2 (#202)
- o3-mini: 33.8 (#256)

| Benchmark | Claude 3 Opus | o3-mini |
|---|---|---|
| LMArena Longer Query | 1259 | 1343 |
| Fiction.LiveBench | — | 50% |

## Writing & Preference

- Claude 3 Opus: 47.2 (#213)
- o3-mini: 50.3 (#182)

| Benchmark | Claude 3 Opus | o3-mini |
|---|---|---|
| LMArena Text | 1262 | 1337 |
| LMArena Creative Writing | 1235 | 1286 |
| LMArena Multi-Turn | 1275 | 1320 |
| LiveBench Language | 50.4% | 50.7% |
| Short-Story Creative Writing | — | 61.7% |

## FAQ

### Is Claude 3 Opus better than o3-mini?

o3-mini is the stronger model overall, scoring 36.7 to 29.5 on the Noometry Index.

### Is Claude 3 Opus or o3-mini better for coding?

o3-mini scores higher on coding benchmarks: 40.8 versus 32.9 in the Noometry coding category.

### How many benchmarks do Claude 3 Opus and o3-mini share?

37 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and o3-mini has 51.