# Claude 3.5 Haiku vs o1-mini

> o1-mini is the stronger model overall, scoring 33.7 to 28.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-5-haiku-vs-o1-mini
- Last updated: 2026-10-10
- Shared benchmarks: 33

## Summary

- They share 33 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 2 categories and o1-mini in 7 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where o1-mini leads 33.7 to 13.7.
- The biggest single-benchmark swing is LiveBench Reasoning: 28.1% for Claude 3.5 Haiku and 72.3% for o1-mini.

## Snapshot

| | Claude 3.5 Haiku | o1-mini |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 28.9 | 33.7 |
| Rank | 309 | 230 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3.5 Haiku: 32.6 (#258)
- o1-mini: 35.1 (#218)

| Benchmark | Claude 3.5 Haiku | o1-mini |
|---|---|---|
| Aider Polyglot | 28% | 32.9% |
| WeirdML | 30.7% | 36.3% |
| LiveBench Coding | 51.4% | 48% |
| LMArena Coding | 1287 | 1362 |
| SciCode | 27.4% | — |
| BigCodeBench Instruct | 46.1% | — |
| BigCodeBench Complete | 59% | — |
| CadEval | 32% | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |

## Agentic & Tool Use

- Claude 3.5 Haiku: 27.7 (#90)
- o1-mini: 24.3 (#112)

| Benchmark | Claude 3.5 Haiku | o1-mini |
|---|---|---|
| Cybench | — | 10% |
| BALROG | 19.3% | — |

## Reasoning

- Claude 3.5 Haiku: 17.1 (#286)
- o1-mini: 8.9 (#340)

| Benchmark | Claude 3.5 Haiku | o1-mini |
|---|---|---|
| LiveBench Reasoning | 28.1% | 72.3% |
| LMArena Hard Prompts | 1251 | 1333 |
| LiveBench Data Analysis | 48.5% | 57.9% |
| Epoch Capabilities Index | 127.15 | 135.82 |
| LiveBench | 43.5% | 57.8% |
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 18.1% |
| ARC-AGI-1 | — | 14% |
| CritPt | 0% | — |
| DTBench | 56.7% | — |

## Math

- Claude 3.5 Haiku: 13.7 (#294)
- o1-mini: 33.7 (#168)

| Benchmark | Claude 3.5 Haiku | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | 46.9% |
| LiveBench Math | 35.5% | 62% |
| LMArena Math | 1244 | 1358 |
| MATH Level 5 | 46.4% | 89.2% |
| FrontierMath (Feb 2025 set) | 0.3% | 1.7% |
| Omni-MATH | 22.4% | — |

## Knowledge

- Claude 3.5 Haiku: 18.7 (#276)
- o1-mini: 34.8 (#180)

| Benchmark | Claude 3.5 Haiku | o1-mini |
|---|---|---|
| GPQA Diamond | 38.1% | 62.4% |
| Confabulations | 36.7% | 18.6% |
| LMArena Expert | 1208 | 1316 |
| MMLU-Pro | 60.5% | — |
| GPQA (HELM) | 36.3% | — |
| MMLU | 74.3% | — |

## Multimodal

- Claude 3.5 Haiku: 26.3 (#113)
- o1-mini: —

| Benchmark | Claude 3.5 Haiku | o1-mini |
|---|---|---|
| LMArena Vision | 1092 | — |
| GeoBench | 34% | — |

## Multilingual

- Claude 3.5 Haiku: 40.2 (#213)
- o1-mini: 43.8 (#177)

| Benchmark | Claude 3.5 Haiku | o1-mini |
|---|---|---|
| LMArena Non-English | 1238 | 1289 |
| LMArena Chinese | 1229 | 1314 |
| LMArena French | 1262 | 1292 |
| LMArena German | 1237 | 1278 |
| LMArena Japanese | 1175 | 1245 |
| LMArena Korean | 1172 | 1223 |
| LMArena Russian | 1253 | 1283 |
| LMArena Spanish | 1261 | 1302 |

## Instruction Following

- Claude 3.5 Haiku: 63.1 (#229)
- o1-mini: 67.0 (#200)

| Benchmark | Claude 3.5 Haiku | o1-mini |
|---|---|---|
| LiveBench Instruction Following | 61.9% | 65.4% |
| LMArena Instruction Following | 1241 | 1304 |
| IFEval | 79.2% | — |

## Long Context

- Claude 3.5 Haiku: 38.3 (#195)
- o1-mini: 40.1 (#156)

| Benchmark | Claude 3.5 Haiku | o1-mini |
|---|---|---|
| LMArena Longer Query | 1261 | 1321 |

## Writing & Preference

- Claude 3.5 Haiku: 42.9 (#228)
- o1-mini: 48.6 (#196)

| Benchmark | Claude 3.5 Haiku | o1-mini |
|---|---|---|
| LMArena Text | 1255 | 1317 |
| LMArena Creative Writing | 1233 | 1244 |
| Short-Story Creative Writing | 73.5% | 64.9% |
| LMArena Multi-Turn | 1265 | 1314 |
| LiveBench Language | 35.4% | 40.9% |
| EQ-Bench Creative Writing | 1146 | — |
| WildBench | 76% | — |

## FAQ

### Is Claude 3.5 Haiku better than o1-mini?

o1-mini is the stronger model overall, scoring 33.7 to 28.9 on the Noometry Index.

### Is Claude 3.5 Haiku or o1-mini better for coding?

o1-mini scores higher on coding benchmarks: 35.1 versus 32.6 in the Noometry coding category.

### How many benchmarks do Claude 3.5 Haiku and o1-mini share?

33 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and o1-mini has 39.