# Claude 3 Haiku vs Magistral Medium

> Magistral Medium is the stronger model overall, scoring 34.8 to 25.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-haiku-vs-magistral-medium
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Claude 3 Haiku scores higher in 1 category and Magistral Medium in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Magistral Medium leads 32.4 to 9.2.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 34.2% for Claude 3 Haiku and 16.2% for Magistral Medium.
- Magistral Medium has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3 Haiku | Magistral Medium |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 25.7 | 34.8 |
| Rank | 333 | 224 |
| Context | — | 128K |
| Input $/M | — | $2 |
| Output $/M | — | $5 |
| Weights | Proprietary | Open |

## Coding

- Claude 3 Haiku: 26.1 (#320)
- Magistral Medium: 38.6 (#161)

| Benchmark | Claude 3 Haiku | Magistral Medium |
|---|---|---|
| LMArena Coding | 1199 | 1319 |
| SciCode | — | 39.2% |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |

## Reasoning

- Claude 3 Haiku: 15.7 (#303)
- Magistral Medium: 8.7 (#342)

| Benchmark | Claude 3 Haiku | Magistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 34.2% | 16.2% |
| LMArena Hard Prompts | 1174 | 1267 |
| ARC-AGI-2 | — | 0% |
| ARC-AGI-1 | — | 6.1% |
| CritPt | — | 0.3% |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.3 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |

## Math

- Claude 3 Haiku: 9.2 (#313)
- Magistral Medium: 32.4 (#187)

| Benchmark | Claude 3 Haiku | Magistral Medium |
|---|---|---|
| LMArena Math | 1188 | 1249 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| MATH Level 5 | 14.9% | — |

## Knowledge

- Claude 3 Haiku: 17.3 (#280)
- Magistral Medium: 32.9 (#199)

| Benchmark | Claude 3 Haiku | Magistral Medium |
|---|---|---|
| LMArena Expert | 1148 | 1222 |
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |

## Multimodal

- Claude 3 Haiku: 23.1 (#123)
- Magistral Medium: —

| Benchmark | Claude 3 Haiku | Magistral Medium |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |

## Multilingual

- Claude 3 Haiku: 36.1 (#238)
- Magistral Medium: 39.8 (#219)

| Benchmark | Claude 3 Haiku | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1178 | 1232 |
| LMArena Chinese | 1155 | 1225 |
| LMArena French | 1194 | 1268 |
| LMArena German | 1174 | 1248 |
| LMArena Japanese | 1102 | 1176 |
| LMArena Korean | 1108 | 1125 |
| LMArena Russian | 1204 | 1224 |
| LMArena Spanish | 1165 | 1269 |

## Instruction Following

- Claude 3 Haiku: 61.5 (#242)
- Magistral Medium: 66.2 (#207)

| Benchmark | Claude 3 Haiku | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1174 | 1254 |

## Long Context

- Claude 3 Haiku: 36.1 (#232)
- Magistral Medium: 39.3 (#178)

| Benchmark | Claude 3 Haiku | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1191 | 1295 |

## Writing & Preference

- Claude 3 Haiku: 29.8 (#286)
- Magistral Medium: 46.5 (#214)

| Benchmark | Claude 3 Haiku | Magistral Medium |
|---|---|---|
| LMArena Text | 1195 | 1255 |
| LMArena Creative Writing | 1157 | 1245 |
| LMArena Multi-Turn | 1190 | 1275 |
| EQ-Bench Creative Writing | 717 | — |

## FAQ

### Is Claude 3 Haiku better than Magistral Medium?

Magistral Medium is the stronger model overall, scoring 34.8 to 25.7 on the Noometry Index.

### Is Claude 3 Haiku or Magistral Medium better for coding?

Magistral Medium scores higher on coding benchmarks: 38.6 versus 26.1 in the Noometry coding category.

### How many benchmarks do Claude 3 Haiku and Magistral Medium share?

18 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Magistral Medium has 22.