# Claude 3 Haiku vs o3-mini

> o3-mini is the stronger model overall, scoring 36.7 to 25.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-haiku-vs-o3-mini
- Last updated: 2026-10-11
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. Claude 3 Haiku scores higher in 1 category and o3-mini in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3-mini leads 38.3 to 17.3.
- The biggest single-benchmark swing is MATH Level 5: 14.9% for Claude 3 Haiku and 96.5% for o3-mini.

## Snapshot

| | Claude 3 Haiku | o3-mini |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 25.9 | 36.7 |
| Rank | 340 | 212 |
| Context | — | 200K |
| Input $/M | — | $1.10 |
| Output $/M | — | $4.40 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3 Haiku: 26.4 (#325)
- o3-mini: 40.8 (#132)

| Benchmark | Claude 3 Haiku | o3-mini |
|---|---|---|
| WeirdML | 9.8% | 43.7% |
| LMArena Coding | 1199 | 1378 |
| CadEval | 12% | 54% |
| Aider Polyglot | — | 60.4% |
| SciCode | — | 39.8% |
| GSO | — | 1.3% |
| BigCodeBench Instruct | 39.4% | — |
| LiveBench Coding | — | 82.7% |
| BigCodeBench Complete | 50.1% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |

## Agentic & Tool Use

- Claude 3 Haiku: —
- o3-mini: 29.6 (#84)

| Benchmark | Claude 3 Haiku | o3-mini |
|---|---|---|
| Cybench | — | 22.5% |

## Reasoning

- Claude 3 Haiku: 16.3 (#307)
- o3-mini: 16.3 (#305)

| Benchmark | Claude 3 Haiku | o3-mini |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1366 |
| DTBench | 50.1% | 68.8% |
| LMCA | 8.8% | 19% |
| Epoch Capabilities Index | 118.35 | 140.34 |
| ForecastBench | 53.2 | 59.6 |
| ARC-AGI-2 | — | 3% |
| SimpleBench | — | 22.8% |
| Kagi LLM Benchmark | 34.2% | — |
| ARC-AGI-1 | — | 34.5% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 17% |
| LiveBench Reasoning | — | 89.6% |
| Mystery Game Puzzles | — | 7% |
| LiveBench Data Analysis | — | 70.6% |
| LiveBench | — | 75.9% |
| WinoGrande | 74.2% | — |

## Math

- Claude 3 Haiku: 9.8 (#319)
- o3-mini: 28.1 (#244)

| Benchmark | Claude 3 Haiku | o3-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | 76.9% |
| LMArena Math | 1188 | 1396 |
| MATH Level 5 | 14.9% | 96.5% |
| FrontierMath (Tiers 1-3) | — | 18.6% |
| FrontierMath Tier 4 | — | 0% |
| LiveBench Math | — | 77.3% |
| FrontierMath (Feb 2025 set) | — | 12.4% |
| FrontierMath Tier 4 (v1) | — | 4.2% |

## Knowledge

- Claude 3 Haiku: 17.3 (#285)
- o3-mini: 38.3 (#146)

| Benchmark | Claude 3 Haiku | o3-mini |
|---|---|---|
| GPQA Diamond | 36.3% | 77% |
| Confabulations | 34.2% | 17.9% |
| LMArena Expert | 1148 | 1364 |
| SimpleQA Verified | — | 15.3% |
| MMLU | 73.8% | — |

## Multimodal

- Claude 3 Haiku: 23.6 (#128)
- o3-mini: —

| Benchmark | Claude 3 Haiku | o3-mini |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |

## Multilingual

- Claude 3 Haiku: 36.0 (#243)
- o3-mini: 45.7 (#164)

| Benchmark | Claude 3 Haiku | o3-mini |
|---|---|---|
| LMArena Non-English | 1178 | 1319 |
| LMArena Chinese | 1155 | 1379 |
| LMArena French | 1195 | 1334 |
| LMArena German | 1174 | 1303 |
| LMArena Japanese | 1102 | 1286 |
| LMArena Korean | 1109 | 1314 |
| LMArena Russian | 1204 | 1304 |
| LMArena Spanish | 1166 | 1321 |

## Instruction Following

- Claude 3 Haiku: 61.3 (#247)
- o3-mini: 75.1 (#72)

| Benchmark | Claude 3 Haiku | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1173 | 1337 |
| LiveBench Instruction Following | — | 84.4% |

## Long Context

- Claude 3 Haiku: 36.1 (#237)
- o3-mini: 33.8 (#256)

| Benchmark | Claude 3 Haiku | o3-mini |
|---|---|---|
| LMArena Longer Query | 1190 | 1343 |
| Fiction.LiveBench | — | 50% |

## Writing & Preference

- Claude 3 Haiku: 29.7 (#291)
- o3-mini: 50.3 (#182)

| Benchmark | Claude 3 Haiku | o3-mini |
|---|---|---|
| LMArena Text | 1195 | 1337 |
| LMArena Creative Writing | 1157 | 1286 |
| LMArena Multi-Turn | 1190 | 1320 |
| Short-Story Creative Writing | — | 61.7% |
| EQ-Bench Creative Writing | 717 | — |
| LiveBench Language | — | 50.7% |

## FAQ

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

o3-mini is the stronger model overall, scoring 36.7 to 25.9 on the Noometry Index.

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

o3-mini scores higher on coding benchmarks: 40.8 versus 26.4 in the Noometry coding category.

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

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