# Inkling vs Mistral Medium

> Inkling is the stronger model overall, scoring 44.1 to 36.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/inkling-vs-mistral-medium
- Last updated: 2026-10-10
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. Inkling scores higher in 9 categories and Mistral Medium in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling leads 55.1 to 25.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.9% for Inkling and 32.2% for Mistral Medium.
- Inkling is cheaper at $1.87 / $4.68 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Mistral Medium accepts more context: 262K tokens versus 66K.

## Snapshot

| | Inkling | Mistral Medium |
|---|---|---|
| Provider | Thinking Machines Lab | Mistral AI |
| Noometry Index | 44.1 | 36.3 |
| Rank | 80 | 218 |
| Context | 66K | 262K |
| Input $/M | $1.87 | $1.50 |
| Output $/M | $4.68 | $7.50 |
| Weights | Open | Open |

## Coding

- Inkling: 34.5 (#234)
- Mistral Medium: 34.2 (#243)

| Benchmark | Inkling | Mistral Medium |
|---|---|---|
| FrontierCode | 14% | 8% |
| SciCode | 47% | 40.2% |
| WeirdML | 32.3% | 43.7% |
| LMArena Coding | 1464 | 1434 |
| ALE-Bench | 946 | 763.98 |
| LMArena WebDev | 1413 | — |
| FrontierSWE | 4.1% | — |

## Agentic & Tool Use

- Inkling: 29.6 (#85)
- Mistral Medium: 28.3 (#90)

| Benchmark | Inkling | Mistral Medium |
|---|---|---|
| APEX-Agents | 33.8% | — |
| Berkeley Function Calling Leaderboard | — | 37.7% |
| τ²-bench Banking | 25% | — |

## Reasoning

- Inkling: 40.4 (#56)
- Mistral Medium: 24.0 (#167)

| Benchmark | Inkling | Mistral Medium |
|---|---|---|
| CritPt | 5.4% | 0% |
| LMArena Hard Prompts | 1451 | 1426 |
| DTBench | 87.5% | 75.5% |
| LMCA | 37.6% | 26.1% |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| Kagi LLM Benchmark | — | 50% |
| ARC-AGI-1 | 79.5% | — |
| Chess Puzzles | 21% | — |
| Surface Evolver Bench | — | 26.9% |
| Epoch Capabilities Index | 148.54 | — |

## Math

- Inkling: 31.3 (#225)
- Mistral Medium: 28.1 (#245)

| Benchmark | Inkling | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 32.2% |
| ProofBench | 0% | 9% |
| LMArena Math | 1479 | 1408 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |

## Knowledge

- Inkling: 55.1 (#49)
- Mistral Medium: 25.0 (#265)

| Benchmark | Inkling | Mistral Medium |
|---|---|---|
| GPQA Diamond | 88.3% | 59.5% |
| LMArena Expert | 1465 | 1408 |
| Humanity's Last Exam | — | 4.5% |
| SimpleQA Verified | 40.3% | — |
| Vectara Hallucination Rate | — | 22.7% |

## Multimodal

- Inkling: —
- Mistral Medium: 35.3 (#88)

| Benchmark | Inkling | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |

## Multilingual

- Inkling: 54.0 (#52)
- Mistral Medium: 52.1 (#91)

| Benchmark | Inkling | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1434 | 1408 |
| LMArena Chinese | 1490 | 1447 |
| LMArena French | 1458 | 1459 |
| LMArena German | 1446 | 1432 |
| LMArena Japanese | 1429 | 1378 |
| LMArena Korean | 1404 | 1380 |
| LMArena Russian | 1429 | 1411 |
| LMArena Spanish | 1448 | 1433 |

## Instruction Following

- Inkling: 75.1 (#71)
- Mistral Medium: 73.7 (#116)

| Benchmark | Inkling | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1426 | 1398 |

## Long Context

- Inkling: 43.8 (#86)
- Mistral Medium: 42.9 (#114)

| Benchmark | Inkling | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1434 | 1406 |

## Writing & Preference

- Inkling: 65.2 (#51)
- Mistral Medium: 60.0 (#103)

| Benchmark | Inkling | Mistral Medium |
|---|---|---|
| LMArena Text | 1441 | 1424 |
| LMArena Creative Writing | 1387 | 1391 |
| LMArena Multi-Turn | 1436 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |

## FAQ

### Is Inkling better than Mistral Medium?

Inkling is the stronger model overall, scoring 44.1 to 36.3 on the Noometry Index.

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

Inkling is cheaper. It lists at $1.87 per million input tokens and $4.68 per million output tokens; Mistral Medium lists at $1.50 and $7.50.

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

They score almost the same on coding (34.5 vs 34.2); test both on your own repository before choosing.

### Which has the bigger context window?

Mistral Medium does, with 262K tokens against 66K.

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

27 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Mistral Medium has 36.