# Inkling vs Mistral Small

> Inkling is the stronger model overall, scoring 44.1 to 33.4 on the Noometry Index. Mistral Small costs 9.8× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/inkling-vs-mistral-small
- Last updated: 2026-10-11
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. Inkling scores higher in 9 categories and Mistral Small in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling leads 55.1 to 31.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.9% for Inkling and 5.8% for Mistral Small.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- Mistral Small accepts more context: 262K tokens versus 66K.

## Snapshot

| | Inkling | Mistral Small |
|---|---|---|
| Provider | Thinking Machines Lab | Mistral AI |
| Noometry Index | 44.1 | 33.4 |
| Rank | 80 | 243 |
| Context | 66K | 262K |
| Input $/M | $1.87 | $0.15 |
| Output $/M | $4.68 | $0.60 |
| Weights | Open | Open |

## Coding

- Inkling: 34.5 (#234)
- Mistral Small: 34.0 (#247)

| Benchmark | Inkling | Mistral Small |
|---|---|---|
| SciCode | 47% | 26.5% |
| LMArena Coding | 1464 | 1362 |
| ALE-Bench | 946 | 497.62 |
| FrontierCode | 14% | — |
| LMArena WebDev | 1413 | — |
| FrontierSWE | 4.1% | — |
| WeirdML | 32.3% | — |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |

## Agentic & Tool Use

- Inkling: 29.6 (#85)
- Mistral Small: 28.1 (#93)

| Benchmark | Inkling | Mistral Small |
|---|---|---|
| APEX-Agents | 33.8% | — |
| Berkeley Function Calling Leaderboard | — | 37.1% |
| τ²-bench Banking | 25% | — |

## Reasoning

- Inkling: 40.4 (#56)
- Mistral Small: 19.8 (#250)

| Benchmark | Inkling | Mistral Small |
|---|---|---|
| CritPt | 5.4% | 0% |
| LMArena Hard Prompts | 1451 | 1335 |
| DTBench | 87.5% | 70.9% |
| LMCA | 37.6% | 20.6% |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| Kagi LLM Benchmark | — | 37.8% |
| ARC-AGI-1 | 79.5% | — |
| Chess Puzzles | 21% | — |
| LiveBench Reasoning | — | 44.8% |
| LiveBench Data Analysis | — | 53.7% |
| Epoch Capabilities Index | 148.54 | — |
| LiveBench | — | 44% |

## Math

- Inkling: 31.3 (#225)
- Mistral Small: 16.4 (#293)

| Benchmark | Inkling | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 5.8% |
| LMArena Math | 1479 | 1341 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| ProofBench | 0% | — |
| LiveBench Math | — | 39.9% |
| MATH Level 5 | — | 46.8% |

## Knowledge

- Inkling: 55.1 (#49)
- Mistral Small: 31.0 (#222)

| Benchmark | Inkling | Mistral Small |
|---|---|---|
| GPQA Diamond | 88.3% | 47.5% |
| LMArena Expert | 1465 | 1291 |
| SimpleQA Verified | 40.3% | — |
| Vectara Hallucination Rate | — | 5.1% |
| MMLU | — | 68.7% |

## Multimodal

- Inkling: —
- Mistral Small: 33.5 (#96)

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

## Multilingual

- Inkling: 54.0 (#52)
- Mistral Small: 45.5 (#169)

| Benchmark | Inkling | Mistral Small |
|---|---|---|
| LMArena Non-English | 1434 | 1315 |
| LMArena Chinese | 1490 | 1340 |
| LMArena French | 1458 | 1337 |
| LMArena German | 1446 | 1340 |
| LMArena Japanese | 1429 | 1275 |
| LMArena Korean | 1404 | 1259 |
| LMArena Russian | 1429 | 1324 |
| LMArena Spanish | 1448 | 1346 |

## Instruction Following

- Inkling: 75.1 (#71)
- Mistral Small: 66.4 (#209)

| Benchmark | Inkling | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1426 | 1310 |
| LiveBench Instruction Following | — | 63.7% |

## Long Context

- Inkling: 43.8 (#86)
- Mistral Small: 40.4 (#156)

| Benchmark | Inkling | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1434 | 1327 |

## Writing & Preference

- Inkling: 65.2 (#51)
- Mistral Small: 52.5 (#171)

| Benchmark | Inkling | Mistral Small |
|---|---|---|
| LMArena Text | 1441 | 1338 |
| LMArena Creative Writing | 1387 | 1305 |
| LMArena Multi-Turn | 1436 | 1344 |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |
| LiveBench Language | — | 30.5% |

## FAQ

### Is Inkling better than Mistral Small?

Inkling is the stronger model overall, scoring 44.1 to 33.4 on the Noometry Index. Mistral Small costs 9.8× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.

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

Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Inkling lists at $1.87 and $4.68.

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

They score almost the same on coding (34.5 vs 34.0); test both on your own repository before choosing.

### Which has the bigger context window?

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

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

24 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Mistral Small has 39.