# Claude 3 Haiku vs o1-mini

> o1-mini is the stronger model overall, scoring 34.0 to 25.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-haiku-vs-o1-mini
- Last updated: 2026-10-10
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. Claude 3 Haiku scores higher in 1 category and o1-mini in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where o1-mini leads 35.4 to 9.8.
- The biggest single-benchmark swing is MATH Level 5: 14.9% for Claude 3 Haiku and 89.2% for o1-mini.

## Snapshot

| | Claude 3 Haiku | o1-mini |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 25.9 | 34.0 |
| Rank | 340 | 235 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3 Haiku: 26.4 (#325)
- o1-mini: 35.5 (#224)

| Benchmark | Claude 3 Haiku | o1-mini |
|---|---|---|
| WeirdML | 9.8% | 36.3% |
| LMArena Coding | 1199 | 1362 |
| HumanEval+ | 68.9% | 89% |
| MBPP+ | 68.8% | 78.8% |
| Aider Polyglot | — | 32.9% |
| BigCodeBench Instruct | 39.4% | — |
| LiveBench Coding | — | 48% |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |

## Agentic & Tool Use

- Claude 3 Haiku: —
- o1-mini: 24.6 (#118)

| Benchmark | Claude 3 Haiku | o1-mini |
|---|---|---|
| Cybench | — | 10% |

## Reasoning

- Claude 3 Haiku: 16.3 (#307)
- o1-mini: 8.8 (#346)

| Benchmark | Claude 3 Haiku | o1-mini |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1333 |
| Epoch Capabilities Index | 118.35 | 135.82 |
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 18.1% |
| Kagi LLM Benchmark | 34.2% | — |
| ARC-AGI-1 | — | 14% |
| LiveBench Reasoning | — | 72.3% |
| DTBench | 50.1% | — |
| LiveBench Data Analysis | — | 57.9% |
| LMCA | 8.8% | — |
| ForecastBench | 53.2 | — |
| LiveBench | — | 57.8% |
| WinoGrande | 74.2% | — |

## Math

- Claude 3 Haiku: 9.8 (#319)
- o1-mini: 35.4 (#186)

| Benchmark | Claude 3 Haiku | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | 46.9% |
| LMArena Math | 1188 | 1358 |
| MATH Level 5 | 14.9% | 89.2% |
| LiveBench Math | — | 62% |
| FrontierMath (Feb 2025 set) | — | 1.7% |

## Knowledge

- Claude 3 Haiku: 17.3 (#285)
- o1-mini: 34.9 (#192)

| Benchmark | Claude 3 Haiku | o1-mini |
|---|---|---|
| GPQA Diamond | 36.3% | 62.4% |
| Confabulations | 34.2% | 18.6% |
| LMArena Expert | 1148 | 1316 |
| MMLU | 73.8% | — |

## Multimodal

- Claude 3 Haiku: 23.6 (#128)
- o1-mini: —

| Benchmark | Claude 3 Haiku | o1-mini |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |

## Multilingual

- Claude 3 Haiku: 36.0 (#243)
- o1-mini: 43.6 (#182)

| Benchmark | Claude 3 Haiku | o1-mini |
|---|---|---|
| LMArena Non-English | 1178 | 1289 |
| LMArena Chinese | 1155 | 1314 |
| LMArena French | 1195 | 1293 |
| LMArena German | 1174 | 1278 |
| LMArena Japanese | 1102 | 1245 |
| LMArena Korean | 1109 | 1223 |
| LMArena Russian | 1204 | 1283 |
| LMArena Spanish | 1166 | 1303 |

## Instruction Following

- Claude 3 Haiku: 61.3 (#247)
- o1-mini: 66.7 (#206)

| Benchmark | Claude 3 Haiku | o1-mini |
|---|---|---|
| LMArena Instruction Following | 1173 | 1304 |
| LiveBench Instruction Following | — | 65.4% |

## Long Context

- Claude 3 Haiku: 36.1 (#237)
- o1-mini: 40.1 (#161)

| Benchmark | Claude 3 Haiku | o1-mini |
|---|---|---|
| LMArena Longer Query | 1190 | 1320 |

## Writing & Preference

- Claude 3 Haiku: 29.7 (#291)
- o1-mini: 48.4 (#202)

| Benchmark | Claude 3 Haiku | o1-mini |
|---|---|---|
| LMArena Text | 1195 | 1317 |
| LMArena Creative Writing | 1157 | 1244 |
| LMArena Multi-Turn | 1190 | 1314 |
| Short-Story Creative Writing | — | 64.9% |
| EQ-Bench Creative Writing | 717 | — |
| LiveBench Language | — | 40.9% |

## FAQ

### Is Claude 3 Haiku better than o1-mini?

o1-mini is the stronger model overall, scoring 34.0 to 25.9 on the Noometry Index.

### Is Claude 3 Haiku or o1-mini better for coding?

o1-mini scores higher on coding benchmarks: 35.5 versus 26.4 in the Noometry coding category.

### How many benchmarks do Claude 3 Haiku and o1-mini share?

25 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and o1-mini has 39.