# Inkling-Small vs Mistral Small

> Inkling-Small is the stronger model overall, scoring 46.5 to 33.1 on the Noometry Index. Mistral Small costs 2.4× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/inkling-small-vs-mistral-small
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Inkling-Small scores higher in 9 categories and Mistral Small in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Inkling-Small leads 44.9 to 15.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 90% for Inkling-Small and 5.8% for Mistral Small.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.45 / $1.20 for Inkling-Small.
- Inkling-Small accepts more context: 524K tokens versus 256K.

## Snapshot

| | Inkling-Small | Mistral Small |
|---|---|---|
| Provider | Thinking Machines Lab | Mistral AI |
| Noometry Index | 46.5 | 33.1 |
| Rank | 57 | 238 |
| Context | 524K | 256K |
| Input $/M | $0.45 | $0.15 |
| Output $/M | $1.20 | $0.60 |
| Weights | Open | Open |

## Coding

- Inkling-Small: 43.3 (#80)
- Mistral Small: 33.5 (#242)

| Benchmark | Inkling-Small | Mistral Small |
|---|---|---|
| SciCode | 48.7% | 26.5% |
| LMArena Coding | 1451 | 1363 |
| LMArena WebDev | 1408 | — |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
| ALE-Bench | — | 497.62 |

## Agentic & Tool Use

- Inkling-Small: —
- Mistral Small: 27.9 (#87)

| Benchmark | Inkling-Small | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |

## Reasoning

- Inkling-Small: 39.0 (#53)
- Mistral Small: 19.3 (#238)

| Benchmark | Inkling-Small | Mistral Small |
|---|---|---|
| CritPt | 8.3% | 0% |
| LMArena Hard Prompts | 1424 | 1336 |
| ARC-AGI-2 | 40.1% | — |
| Kagi LLM Benchmark | — | 37.8% |
| ARC-AGI-1 | 84% | — |
| Chess Puzzles | 18% | — |
| LiveBench Reasoning | — | 44.8% |
| Mystery Game Puzzles | 6% | — |
| DTBench | — | 70.9% |
| LiveBench Data Analysis | — | 53.7% |
| LMCA | — | 20.6% |
| Epoch Capabilities Index | 150.13 | — |
| LiveBench | — | 44% |

## Math

- Inkling-Small: 44.9 (#65)
- Mistral Small: 15.4 (#287)

| Benchmark | Inkling-Small | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 90% | 5.8% |
| LMArena Math | 1453 | 1341 |
| FrontierMath (Tiers 1-3) | 46.3% | — |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 6% | — |
| LiveBench Math | — | 39.9% |
| MATH Level 5 | — | 46.8% |

## Knowledge

- Inkling-Small: 48.3 (#71)
- Mistral Small: 30.9 (#214)

| Benchmark | Inkling-Small | Mistral Small |
|---|---|---|
| GPQA Diamond | 88.5% | 47.5% |
| LMArena Expert | 1442 | 1293 |
| SimpleQA Verified | 19.1% | — |
| Vectara Hallucination Rate | — | 5.1% |
| MMLU | — | 68.7% |

## Multimodal

- Inkling-Small: 38.4 (#59)
- Mistral Small: 32.9 (#91)

| Benchmark | Inkling-Small | Mistral Small |
|---|---|---|
| LMArena Vision | 1235 | 1142 |

## Multilingual

- Inkling-Small: 51.7 (#102)
- Mistral Small: 45.7 (#164)

| Benchmark | Inkling-Small | Mistral Small |
|---|---|---|
| LMArena Non-English | 1400 | 1315 |
| LMArena Chinese | 1458 | 1342 |
| LMArena French | 1438 | 1337 |
| LMArena German | 1412 | 1341 |
| LMArena Japanese | 1399 | 1275 |
| LMArena Korean | 1355 | 1260 |
| LMArena Russian | 1392 | 1324 |
| LMArena Spanish | 1426 | 1346 |

## Instruction Following

- Inkling-Small: 73.9 (#112)
- Mistral Small: 66.6 (#204)

| Benchmark | Inkling-Small | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1397 | 1310 |
| LiveBench Instruction Following | — | 63.7% |

## Long Context

- Inkling-Small: 42.7 (#113)
- Mistral Small: 40.4 (#151)

| Benchmark | Inkling-Small | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1401 | 1327 |

## Writing & Preference

- Inkling-Small: 59.8 (#102)
- Mistral Small: 52.6 (#165)

| Benchmark | Inkling-Small | Mistral Small |
|---|---|---|
| LMArena Text | 1413 | 1338 |
| LMArena Creative Writing | 1330 | 1304 |
| LMArena Multi-Turn | 1420 | 1344 |
| EQ-Bench Creative Writing | 1491 | — |
| LiveBench Language | — | 30.5% |

## FAQ

### Is Inkling-Small better than Mistral Small?

Inkling-Small is the stronger model overall, scoring 46.5 to 33.1 on the Noometry Index. Mistral Small costs 2.4× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.

### Which is cheaper, Inkling-Small or Mistral Small?

Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Inkling-Small lists at $0.45 and $1.20.

### Is Inkling-Small or Mistral Small better for coding?

Inkling-Small scores higher on coding benchmarks: 43.3 versus 33.5 in the Noometry coding category.

### Which has the bigger context window?

Inkling-Small does, with 524K tokens against 256K.

### How many benchmarks do Inkling-Small and Mistral Small share?

22 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Mistral Small has 39.