# Claude 3 Haiku vs Mixtral 8x7B

> Mixtral 8x7B is the stronger model overall, scoring 26.8 to 25.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-haiku-vs-mixtral-8x7b
- Last updated: 2026-10-10
- Shared benchmarks: 26

## Summary

- They share 26 benchmarks with published results for both. Claude 3 Haiku scores higher in 4 categories and Mixtral 8x7B in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Claude 3 Haiku leads 61.5 to 51.2.
- The biggest single-benchmark swing is GPQA Diamond: 36.3% for Claude 3 Haiku and 30.6% for Mixtral 8x7B.
- Mixtral 8x7B has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3 Haiku | Mixtral 8x7B |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 25.7 | 26.8 |
| Rank | 333 | 328 |
| Context | — | 32K |
| Input $/M | — | $0.70 |
| Output $/M | — | $0.70 |
| Weights | Proprietary | Open |

## Coding

- Claude 3 Haiku: 26.1 (#320)
- Mixtral 8x7B: 32.2 (#265)

| Benchmark | Claude 3 Haiku | Mixtral 8x7B |
|---|---|---|
| LMArena Coding | 1199 | 1127 |
| HumanEval+ | 68.9% | 39.6% |
| MBPP+ | 68.8% | 49.7% |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |

## Reasoning

- Claude 3 Haiku: 15.7 (#303)
- Mixtral 8x7B: 17.4 (#283)

| Benchmark | Claude 3 Haiku | Mixtral 8x7B |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1115 |
| DTBench | 50.1% | 49.6% |
| Epoch Capabilities Index | 118.3 | 118.38 |
| ForecastBench | 53.2 | 56.3 |
| WinoGrande | 74.2% | 77.2% |
| Kagi LLM Benchmark | 34.2% | — |
| LMCA | 8.8% | — |
| Adversarial NLI | — | 55.2% |
| HellaSwag | — | 86.7% |
| PIQA | — | 83.6% |

## Math

- Claude 3 Haiku: 9.2 (#313)
- Mixtral 8x7B: 17.2 (#284)

| Benchmark | Claude 3 Haiku | Mixtral 8x7B |
|---|---|---|
| LMArena Math | 1188 | 1147 |
| MATH Level 5 | 14.9% | 10% |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| Omni-MATH | — | 10.5% |
| GSM8K | — | 74.4% |

## Knowledge

- Claude 3 Haiku: 17.3 (#280)
- Mixtral 8x7B: 11.0 (#296)

| Benchmark | Claude 3 Haiku | Mixtral 8x7B |
|---|---|---|
| GPQA Diamond | 36.3% | 30.6% |
| LMArena Expert | 1148 | 1088 |
| MMLU | 73.8% | 70.6% |
| MMLU-Pro | — | 33.5% |
| Confabulations | 34.2% | — |
| GPQA (HELM) | — | 29.6% |
| ARC (AI2) Challenge | — | 87.3% |
| OpenBookQA | — | 85.8% |
| TriviaQA | — | 82.2% |

## Multimodal

- Claude 3 Haiku: 23.1 (#123)
- Mixtral 8x7B: —

| Benchmark | Claude 3 Haiku | Mixtral 8x7B |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |

## Multilingual

- Claude 3 Haiku: 36.1 (#238)
- Mixtral 8x7B: 29.8 (#261)

| Benchmark | Claude 3 Haiku | Mixtral 8x7B |
|---|---|---|
| LMArena Non-English | 1178 | 1077 |
| LMArena Chinese | 1155 | 1055 |
| LMArena French | 1194 | 1165 |
| LMArena German | 1174 | 1114 |
| LMArena Japanese | 1102 | 931 |
| LMArena Korean | 1108 | 968 |
| LMArena Russian | 1204 | 1090 |
| LMArena Spanish | 1165 | 1110 |

## Instruction Following

- Claude 3 Haiku: 61.5 (#242)
- Mixtral 8x7B: 51.2 (#292)

| Benchmark | Claude 3 Haiku | Mixtral 8x7B |
|---|---|---|
| LMArena Instruction Following | 1174 | 1110 |
| IFEval | — | 57.5% |

## Long Context

- Claude 3 Haiku: 36.1 (#232)
- Mixtral 8x7B: 33.4 (#255)

| Benchmark | Claude 3 Haiku | Mixtral 8x7B |
|---|---|---|
| LMArena Longer Query | 1191 | 1103 |

## Writing & Preference

- Claude 3 Haiku: 29.8 (#286)
- Mixtral 8x7B: 34.4 (#265)

| Benchmark | Claude 3 Haiku | Mixtral 8x7B |
|---|---|---|
| LMArena Text | 1195 | 1132 |
| LMArena Creative Writing | 1157 | 1109 |
| LMArena Multi-Turn | 1190 | 1115 |
| EQ-Bench Creative Writing | 717 | — |
| WildBench | — | 67.3% |

## FAQ

### Is Claude 3 Haiku better than Mixtral 8x7B?

Mixtral 8x7B is the stronger model overall, scoring 26.8 to 25.7 on the Noometry Index.

### Is Claude 3 Haiku or Mixtral 8x7B better for coding?

Mixtral 8x7B scores higher on coding benchmarks: 32.2 versus 26.1 in the Noometry coding category.

### How many benchmarks do Claude 3 Haiku and Mixtral 8x7B share?

26 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Mixtral 8x7B has 38.