# Claude 3 Haiku vs o1

> o1 is the stronger model overall, scoring 40.9 to 25.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-haiku-vs-o1
- Last updated: 2026-10-11
- Shared benchmarks: 29

## Summary

- They share 29 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and o1 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where o1 leads 36.1 to 9.8.
- The biggest single-benchmark swing is MATH Level 5: 14.9% for Claude 3 Haiku and 94.7% for o1.

## Snapshot

| | Claude 3 Haiku | o1 |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 25.9 | 40.9 |
| Rank | 340 | 143 |
| Context | — | 200K |
| Input $/M | — | $15 |
| Output $/M | — | $60 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3 Haiku: 26.4 (#325)
- o1: 46.1 (#70)

| Benchmark | Claude 3 Haiku | o1 |
|---|---|---|
| WeirdML | 9.8% | 47.6% |
| LMArena Coding | 1199 | 1367 |
| CadEval | 12% | 56% |
| HumanEval+ | 68.9% | 89% |
| MBPP+ | 68.8% | 80.2% |
| Aider Polyglot | — | 61.7% |
| BigCodeBench Instruct | 39.4% | — |
| LiveBench Coding | — | 69.7% |
| BigCodeBench Complete | 50.1% | — |

## Agentic & Tool Use

- Claude 3 Haiku: —
- o1: 24.6 (#117)

| Benchmark | Claude 3 Haiku | o1 |
|---|---|---|
| Cybench | — | 10% |
| METR Time Horizons | — | 51.1% |

## Reasoning

- Claude 3 Haiku: 16.3 (#307)
- o1: 27.9 (#111)

| Benchmark | Claude 3 Haiku | o1 |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1371 |
| DTBench | 50.1% | 74.7% |
| LMCA | 8.8% | 22.3% |
| Epoch Capabilities Index | 118.35 | 141.91 |
| SimpleBench | — | 41.7% |
| Kagi LLM Benchmark | 34.2% | — |
| ARC-AGI-1 | — | 30.7% |
| Chess Puzzles | — | 15% |
| EnigmaEval | — | 5.7% |
| LiveBench Reasoning | — | 91.6% |
| LiveBench Data Analysis | — | 65.5% |
| ForecastBench | 53.2 | — |
| LiveBench | — | 75.7% |
| WinoGrande | 74.2% | — |

## Math

- Claude 3 Haiku: 9.8 (#319)
- o1: 36.1 (#175)

| Benchmark | Claude 3 Haiku | o1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | 73.3% |
| LMArena Math | 1188 | 1388 |
| MATH Level 5 | 14.9% | 94.7% |
| FrontierMath (Tiers 1-3) | — | 14.7% |
| LiveBench Math | — | 80.3% |
| FrontierMath (Feb 2025 set) | — | 9.3% |

## Knowledge

- Claude 3 Haiku: 17.3 (#285)
- o1: 41.5 (#110)

| Benchmark | Claude 3 Haiku | o1 |
|---|---|---|
| GPQA Diamond | 36.3% | 76.8% |
| Confabulations | 34.2% | 11.7% |
| LMArena Expert | 1148 | 1361 |
| Humanity's Last Exam | — | 8% |
| SimpleQA Verified | — | 41.1% |
| MMLU | 73.8% | — |

## Multimodal

- Claude 3 Haiku: 23.6 (#128)
- o1: 34.2 (#93)

| Benchmark | Claude 3 Haiku | o1 |
|---|---|---|
| LMArena Vision | 950 | 1168 |
| GeoBench | — | 80% |
| VPCT | — | 37% |
| ScienceQA | 72% | — |
| SpatialViz-Bench | — | 41.4% |

## Multilingual

- Claude 3 Haiku: 36.0 (#243)
- o1: 48.6 (#142)

| Benchmark | Claude 3 Haiku | o1 |
|---|---|---|
| LMArena Non-English | 1178 | 1358 |
| LMArena Chinese | 1155 | 1394 |
| LMArena French | 1195 | 1344 |
| LMArena German | 1174 | 1337 |
| LMArena Japanese | 1102 | 1346 |
| LMArena Korean | 1109 | 1396 |
| LMArena Russian | 1204 | 1356 |
| LMArena Spanish | 1166 | 1345 |

## Instruction Following

- Claude 3 Haiku: 61.3 (#247)
- o1: 74.8 (#86)

| Benchmark | Claude 3 Haiku | o1 |
|---|---|---|
| LMArena Instruction Following | 1173 | 1367 |
| LiveBench Instruction Following | — | 81.5% |

## Long Context

- Claude 3 Haiku: 36.1 (#237)
- o1: 50.3 (#9)

| Benchmark | Claude 3 Haiku | o1 |
|---|---|---|
| LMArena Longer Query | 1190 | 1378 |
| Fiction.LiveBench | — | 83.3% |

## Writing & Preference

- Claude 3 Haiku: 29.7 (#291)
- o1: 55.6 (#144)

| Benchmark | Claude 3 Haiku | o1 |
|---|---|---|
| LMArena Text | 1195 | 1366 |
| LMArena Creative Writing | 1157 | 1348 |
| LMArena Multi-Turn | 1190 | 1369 |
| Short-Story Creative Writing | — | 70.2% |
| EQ-Bench Creative Writing | 717 | — |
| LiveBench Language | — | 65.4% |

## FAQ

### Is Claude 3 Haiku better than o1?

o1 is the stronger model overall, scoring 40.9 to 25.9 on the Noometry Index.

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

o1 scores higher on coding benchmarks: 46.1 versus 26.4 in the Noometry coding category.

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

29 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and o1 has 52.