# Inkling-Small vs Mistral 7B

> Inkling-Small is the stronger model overall, scoring 46.5 to 22.9 on the Noometry Index. Mistral 7B costs 2.5× 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-7b
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. Inkling-Small scores higher in 8 categories and Mistral 7B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling-Small leads 48.3 to 7.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 90% for Inkling-Small and 0.3% for Mistral 7B.
- Mistral 7B is cheaper at $0.25 / $0.25 per million input/output tokens, against $0.45 / $1.20 for Inkling-Small.
- Inkling-Small accepts more context: 524K tokens versus 8K.

## Snapshot

| | Inkling-Small | Mistral 7B |
|---|---|---|
| Provider | Thinking Machines Lab | Mistral AI |
| Noometry Index | 46.5 | 22.9 |
| Rank | 57 | 346 |
| Context | 524K | 8K |
| Input $/M | $0.45 | $0.25 |
| Output $/M | $1.20 | $0.25 |
| Weights | Open | Open |

## Coding

- Inkling-Small: 43.3 (#80)
- Mistral 7B: 25.9 (#321)

| Benchmark | Inkling-Small | Mistral 7B |
|---|---|---|
| LMArena Coding | 1451 | 1082 |
| LMArena WebDev | 1408 | — |
| SciCode | 48.7% | — |
| BigCodeBench Instruct | — | 19.5% |
| BigCodeBench Complete | — | 27.3% |
| HumanEval+ | — | 36% |
| MBPP+ | — | 42.1% |

## Reasoning

- Inkling-Small: 39.0 (#53)
- Mistral 7B: 12.6 (#331)

| Benchmark | Inkling-Small | Mistral 7B |
|---|---|---|
| Chess Puzzles | 18% | 0% |
| LMArena Hard Prompts | 1424 | 1067 |
| Epoch Capabilities Index | 150.13 | 111.97 |
| ARC-AGI-2 | 40.1% | — |
| ARC-AGI-1 | 84% | — |
| CritPt | 8.3% | — |
| Mystery Game Puzzles | 6% | — |
| DTBench | — | 42.5% |
| Adversarial NLI | — | 47.1% |
| BIG-Bench Hard | — | 56.1% |
| HellaSwag | — | 81% |
| PIQA | — | 83% |
| WinoGrande | — | 75.3% |

## Math

- Inkling-Small: 44.9 (#65)
- Mistral 7B: 7.6 (#319)

| Benchmark | Inkling-Small | Mistral 7B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 90% | 0.3% |
| LMArena Math | 1453 | 1085 |
| FrontierMath (Tiers 1-3) | 46.3% | — |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 6% | — |
| MATH Level 5 | — | 3.7% |
| GSM8K | — | 54.4% |

## Knowledge

- Inkling-Small: 48.3 (#71)
- Mistral 7B: 7.3 (#306)

| Benchmark | Inkling-Small | Mistral 7B |
|---|---|---|
| GPQA Diamond | 88.5% | 15.2% |
| LMArena Expert | 1442 | 1036 |
| SimpleQA Verified | 19.1% | — |
| ARC (AI2) Challenge | — | 78.6% |
| BoolQ | — | 87.4% |
| MMLU | — | 62.5% |
| OpenBookQA | — | 79.8% |
| TriviaQA | — | 75.2% |

## Multimodal

- Inkling-Small: 38.4 (#59)
- Mistral 7B: —

| Benchmark | Inkling-Small | Mistral 7B |
|---|---|---|
| LMArena Vision | 1235 | — |

## Multilingual

- Inkling-Small: 51.7 (#102)
- Mistral 7B: 26.0 (#278)

| Benchmark | Inkling-Small | Mistral 7B |
|---|---|---|
| LMArena Non-English | 1400 | 1012 |
| LMArena Chinese | 1458 | 1009 |
| LMArena French | 1438 | 1036 |
| LMArena German | 1412 | 987 |
| LMArena Japanese | 1399 | 878 |
| LMArena Russian | 1392 | 1018 |
| LMArena Spanish | 1426 | 1026 |
| LMArena Korean | 1355 | — |

## Instruction Following

- Inkling-Small: 73.9 (#112)
- Mistral 7B: 54.5 (#275)

| Benchmark | Inkling-Small | Mistral 7B |
|---|---|---|
| LMArena Instruction Following | 1397 | 1060 |

## Long Context

- Inkling-Small: 42.7 (#113)
- Mistral 7B: 32.2 (#266)

| Benchmark | Inkling-Small | Mistral 7B |
|---|---|---|
| LMArena Longer Query | 1401 | 1060 |

## Writing & Preference

- Inkling-Small: 59.8 (#102)
- Mistral 7B: 30.9 (#281)

| Benchmark | Inkling-Small | Mistral 7B |
|---|---|---|
| LMArena Text | 1413 | 1090 |
| LMArena Creative Writing | 1330 | 1068 |
| LMArena Multi-Turn | 1420 | 1062 |
| EQ-Bench Creative Writing | 1491 | — |

## FAQ

### Is Inkling-Small better than Mistral 7B?

Inkling-Small is the stronger model overall, scoring 46.5 to 22.9 on the Noometry Index. Mistral 7B costs 2.5× 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 7B?

Mistral 7B is cheaper. It lists at $0.25 per million input tokens and $0.25 per million output tokens; Inkling-Small lists at $0.45 and $1.20.

### Is Inkling-Small or Mistral 7B better for coding?

Inkling-Small scores higher on coding benchmarks: 43.3 versus 25.9 in the Noometry coding category.

### Which has the bigger context window?

Inkling-Small does, with 524K tokens against 8K.

### How many benchmarks do Inkling-Small and Mistral 7B share?

20 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Mistral 7B has 37.