# Inkling vs Magistral Medium

> Inkling is the stronger model overall, scoring 44.1 to 34.8 on the Noometry Index.

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

## Summary

- They share 21 benchmarks with published results for both. Inkling scores higher in 6 categories and Magistral Medium in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling leads 40.6 to 8.7.
- The biggest single-benchmark swing is ARC-AGI-1: 79.5% for Inkling and 6.1% for Magistral Medium.
- Inkling is cheaper at $1.87 / $4.68 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Magistral Medium accepts more context: 128K tokens versus 66K.

## Snapshot

| | Inkling | Magistral Medium |
|---|---|---|
| Provider | Thinking Machines Lab | Mistral AI |
| Noometry Index | 44.1 | 34.8 |
| Rank | 75 | 224 |
| Context | 66K | 128K |
| Input $/M | $1.87 | $2 |
| Output $/M | $4.68 | $5 |
| Weights | Open | Open |

## Coding

- Inkling: 34.1 (#229)
- Magistral Medium: 38.6 (#161)

| Benchmark | Inkling | Magistral Medium |
|---|---|---|
| SciCode | 47% | 39.2% |
| LMArena Coding | 1463 | 1319 |
| FrontierCode | 14% | — |
| LMArena WebDev | 1412 | — |
| FrontierSWE | 4.1% | — |
| WeirdML | 32.3% | — |
| ALE-Bench | 946 | — |

## Agentic & Tool Use

- Inkling: 29.5 (#76)
- Magistral Medium: —

| Benchmark | Inkling | Magistral Medium |
|---|---|---|
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |

## Reasoning

- Inkling: 40.6 (#48)
- Magistral Medium: 8.7 (#342)

| Benchmark | Inkling | Magistral Medium |
|---|---|---|
| ARC-AGI-2 | 36.5% | 0% |
| ARC-AGI-1 | 79.5% | 6.1% |
| CritPt | 5.4% | 0.3% |
| LMArena Hard Prompts | 1452 | 1267 |
| SimpleBench | 50% | — |
| Kagi LLM Benchmark | — | 16.2% |
| Chess Puzzles | 21% | — |
| DTBench | 87.5% | — |
| LMCA | 37.6% | — |
| Epoch Capabilities Index | 148.6 | — |

## Math

- Inkling: 31.2 (#198)
- Magistral Medium: 32.4 (#187)

| Benchmark | Inkling | Magistral Medium |
|---|---|---|
| LMArena Math | 1482 | 1249 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 0% | — |

## Knowledge

- Inkling: 55.2 (#44)
- Magistral Medium: 32.9 (#199)

| Benchmark | Inkling | Magistral Medium |
|---|---|---|
| LMArena Expert | 1468 | 1222 |
| GPQA Diamond | 88.3% | — |
| SimpleQA Verified | 40.3% | — |

## Multilingual

- Inkling: 54.2 (#49)
- Magistral Medium: 39.8 (#219)

| Benchmark | Inkling | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1434 | 1232 |
| LMArena Chinese | 1495 | 1225 |
| LMArena French | 1453 | 1268 |
| LMArena German | 1456 | 1248 |
| LMArena Japanese | 1428 | 1176 |
| LMArena Korean | 1401 | 1125 |
| LMArena Russian | 1430 | 1224 |
| LMArena Spanish | 1442 | 1269 |

## Instruction Following

- Inkling: 75.3 (#65)
- Magistral Medium: 66.2 (#207)

| Benchmark | Inkling | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1427 | 1254 |

## Long Context

- Inkling: 43.9 (#79)
- Magistral Medium: 39.3 (#178)

| Benchmark | Inkling | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1436 | 1295 |

## Writing & Preference

- Inkling: 65.5 (#48)
- Magistral Medium: 46.5 (#214)

| Benchmark | Inkling | Magistral Medium |
|---|---|---|
| LMArena Text | 1443 | 1255 |
| LMArena Creative Writing | 1390 | 1245 |
| LMArena Multi-Turn | 1436 | 1275 |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |

## FAQ

### Is Inkling better than Magistral Medium?

Inkling is the stronger model overall, scoring 44.1 to 34.8 on the Noometry Index.

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

Inkling is cheaper. It lists at $1.87 per million input tokens and $4.68 per million output tokens; Magistral Medium lists at $2 and $5.

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

Magistral Medium scores higher on coding benchmarks: 38.6 versus 34.1 in the Noometry coding category.

### Which has the bigger context window?

Magistral Medium does, with 128K tokens against 66K.

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

21 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Magistral Medium has 22.