# Magistral Medium vs Tulu 3 (Tülu 3) 70B

> Magistral Medium is the stronger model overall, scoring 35.2 to 33.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/magistral-medium-vs-tulu-3-70b
- Last updated: 2026-10-12
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. Magistral Medium scores higher in 6 categories and Tulu 3 (Tülu 3) 70B in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Magistral Medium leads 35.1 to 14.2.

## Snapshot

| | Magistral Medium | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| Provider | Mistral AI | Allen Institute for AI (Ai2) |
| Noometry Index | 35.2 | 33.0 |
| Rank | 227 | 251 |
| Context | 262K | — |
| Input $/M | $2 | — |
| Output $/M | $5 | — |
| Weights | Open | Open |

## Coding

- Magistral Medium: 39.1 (#161)
- Tulu 3 (Tülu 3) 70B: 36.0 (#214)

| Benchmark | Magistral Medium | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1319 | 1235 |
| SciCode | 39.2% | — |

## Reasoning

- Magistral Medium: 8.6 (#348)
- Tulu 3 (Tülu 3) 70B: 23.9 (#169)

| Benchmark | Magistral Medium | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1267 | 1220 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 16.2% | — |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |

## Math

- Magistral Medium: 35.1 (#189)
- Tulu 3 (Tülu 3) 70B: 14.2 (#303)

| Benchmark | Magistral Medium | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Math | 1250 | 1242 |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| MATH Level 5 | — | 42.7% |

## Knowledge

- Magistral Medium: 33.5 (#202)
- Tulu 3 (Tülu 3) 70B: 25.0 (#264)

| Benchmark | Magistral Medium | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
| LMArena Expert | 1223 | — |

## Multilingual

- Magistral Medium: 39.6 (#224)
- Tulu 3 (Tülu 3) 70B: 39.9 (#222)

| Benchmark | Magistral Medium | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1232 | 1236 |
| LMArena Chinese | 1227 | 1249 |
| LMArena Russian | 1224 | 1246 |
| LMArena French | 1267 | — |
| LMArena German | 1248 | — |
| LMArena Japanese | 1175 | — |
| LMArena Korean | 1125 | — |
| LMArena Spanish | 1271 | — |

## Instruction Following

- Magistral Medium: 66.0 (#211)
- Tulu 3 (Tülu 3) 70B: 64.8 (#227)

| Benchmark | Magistral Medium | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1254 | 1233 |

## Long Context

- Magistral Medium: 39.3 (#183)
- Tulu 3 (Tülu 3) 70B: 37.1 (#222)

| Benchmark | Magistral Medium | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1295 | 1224 |

## Writing & Preference

- Magistral Medium: 46.3 (#219)
- Tulu 3 (Tülu 3) 70B: 45.6 (#223)

| Benchmark | Magistral Medium | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1255 | 1256 |
| LMArena Creative Writing | 1245 | 1231 |
| LMArena Multi-Turn | 1275 | 1252 |

## FAQ

### Is Magistral Medium better than Tulu 3 (Tülu 3) 70B?

Magistral Medium is the stronger model overall, scoring 35.2 to 33.0 on the Noometry Index.

### Is Magistral Medium or Tulu 3 (Tülu 3) 70B better for coding?

Magistral Medium scores higher on coding benchmarks: 39.1 versus 36.0 in the Noometry coding category.

### How many benchmarks do Magistral Medium and Tulu 3 (Tülu 3) 70B share?

11 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.