# Inkling-Small vs Magistral Medium

> Inkling-Small is the stronger model overall, scoring 46.5 to 35.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/inkling-small-vs-magistral-medium
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Inkling-Small scores higher in 8 categories and Magistral Medium in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 38.6 to 8.6.
- The biggest single-benchmark swing is ARC-AGI-1: 84% for Inkling-Small and 6.1% for Magistral Medium.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Inkling-Small accepts more context: 524K tokens versus 262K.

## Snapshot

| | Inkling-Small | Magistral Medium |
|---|---|---|
| Provider | Thinking Machines Lab | Mistral AI |
| Noometry Index | 46.5 | 35.2 |
| Rank | 63 | 227 |
| Context | 524K | 262K |
| Input $/M | $0.45 | $2 |
| Output $/M | $1.20 | $5 |
| Weights | Open | Open |

## Coding

- Inkling-Small: 43.6 (#85)
- Magistral Medium: 39.1 (#161)

| Benchmark | Inkling-Small | Magistral Medium |
|---|---|---|
| SciCode | 48.7% | 39.2% |
| LMArena Coding | 1451 | 1319 |
| LMArena WebDev | 1409 | — |

## Reasoning

- Inkling-Small: 38.6 (#63)
- Magistral Medium: 8.6 (#348)

| Benchmark | Inkling-Small | Magistral Medium |
|---|---|---|
| ARC-AGI-2 | 40.1% | 0% |
| ARC-AGI-1 | 84% | 6.1% |
| CritPt | 8.3% | 0.3% |
| LMArena Hard Prompts | 1423 | 1267 |
| Kagi LLM Benchmark | — | 16.2% |
| Chess Puzzles | 18% | — |
| Mystery Game Puzzles | 6% | — |
| Epoch Capabilities Index | 150.15 | — |

## Math

- Inkling-Small: 45.1 (#77)
- Magistral Medium: 35.1 (#189)

| Benchmark | Inkling-Small | Magistral Medium |
|---|---|---|
| LMArena Math | 1459 | 1250 |
| FrontierMath (Tiers 1-3) | 46.3% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 90% | — |
| ProofBench | 6% | — |

## Knowledge

- Inkling-Small: 48.2 (#77)
- Magistral Medium: 33.5 (#202)

| Benchmark | Inkling-Small | Magistral Medium |
|---|---|---|
| LMArena Expert | 1442 | 1223 |
| GPQA Diamond | 88.5% | — |
| SimpleQA Verified | 19.1% | — |

## Multimodal

- Inkling-Small: 39.1 (#62)
- Magistral Medium: —

| Benchmark | Inkling-Small | Magistral Medium |
|---|---|---|
| LMArena Vision | 1235 | — |

## Multilingual

- Inkling-Small: 51.7 (#104)
- Magistral Medium: 39.6 (#224)

| Benchmark | Inkling-Small | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1402 | 1232 |
| LMArena Chinese | 1465 | 1227 |
| LMArena French | 1436 | 1267 |
| LMArena German | 1405 | 1248 |
| LMArena Japanese | 1405 | 1175 |
| LMArena Korean | 1363 | 1125 |
| LMArena Russian | 1391 | 1224 |
| LMArena Spanish | 1428 | 1271 |

## Instruction Following

- Inkling-Small: 73.8 (#114)
- Magistral Medium: 66.0 (#211)

| Benchmark | Inkling-Small | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1399 | 1254 |

## Long Context

- Inkling-Small: 42.7 (#118)
- Magistral Medium: 39.3 (#183)

| Benchmark | Inkling-Small | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1401 | 1295 |

## Writing & Preference

- Inkling-Small: 59.6 (#107)
- Magistral Medium: 46.3 (#219)

| Benchmark | Inkling-Small | Magistral Medium |
|---|---|---|
| LMArena Text | 1414 | 1255 |
| LMArena Creative Writing | 1331 | 1245 |
| LMArena Multi-Turn | 1418 | 1275 |
| EQ-Bench Creative Writing | 1491 | — |

## FAQ

### Is Inkling-Small better than Magistral Medium?

Inkling-Small is the stronger model overall, scoring 46.5 to 35.2 on the Noometry Index.

### Which is cheaper, Inkling-Small or Magistral Medium?

Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Magistral Medium lists at $2 and $5.

### Is Inkling-Small or Magistral Medium better for coding?

Inkling-Small scores higher on coding benchmarks: 43.6 versus 39.1 in the Noometry coding category.

### Which has the bigger context window?

Inkling-Small does, with 524K tokens against 262K.

### How many benchmarks do Inkling-Small and Magistral Medium share?

21 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Magistral Medium has 22.