# Devstral Small 2505 vs Inkling-Small

> Inkling-Small is the stronger model overall, scoring 46.5 to 34.3 on the Noometry Index. Devstral Small 2505 costs 4.2× 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/devstral-small-vs-inkling-small
- Last updated: 2026-10-11
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. Devstral Small 2505 scores higher in 0 categories and Inkling-Small in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 38.6 to 19.7.
- The biggest single-benchmark swing is SciCode: 28.8% for Devstral Small 2505 and 48.7% for Inkling-Small.
- Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.45 / $1.20 for Inkling-Small.
- Inkling-Small accepts more context: 524K tokens versus 128K.

## Snapshot

| | Devstral Small 2505 | Inkling-Small |
|---|---|---|
| Provider | Mistral AI | Thinking Machines Lab |
| Noometry Index | 34.3 | 46.5 |
| Rank | 233 | 63 |
| Context | 128K | 524K |
| Input $/M | $0.10 | $0.45 |
| Output $/M | $0.30 | $1.20 |
| Weights | Open | Open |

## Coding

- Devstral Small 2505: 38.9 (#166)
- Inkling-Small: 43.6 (#85)

| Benchmark | Devstral Small 2505 | Inkling-Small |
|---|---|---|
| SciCode | 28.8% | 48.7% |
| SWE-bench Verified (bash only) | 56.4% | — |
| LMArena WebDev | — | 1409 |
| LMArena Coding | — | 1451 |

## Reasoning

- Devstral Small 2505: 19.7 (#252)
- Inkling-Small: 38.6 (#63)

| Benchmark | Devstral Small 2505 | Inkling-Small |
|---|---|---|
| CritPt | 0% | 8.3% |
| ARC-AGI-2 | — | 40.1% |
| Kagi LLM Benchmark | 37.7% | — |
| ARC-AGI-1 | — | 84% |
| Chess Puzzles | — | 18% |
| LMArena Hard Prompts | — | 1423 |
| Mystery Game Puzzles | — | 6% |
| Epoch Capabilities Index | — | 150.15 |

## Math

- Devstral Small 2505: —
- Inkling-Small: 45.1 (#77)

| Benchmark | Devstral Small 2505 | Inkling-Small |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 46.3% |
| FrontierMath Tier 4 | — | 17.1% |
| OTIS Mock AIME 2024-2025 | — | 90% |
| ProofBench | — | 6% |
| LMArena Math | — | 1459 |

## Knowledge

- Devstral Small 2505: —
- Inkling-Small: 48.2 (#77)

| Benchmark | Devstral Small 2505 | Inkling-Small |
|---|---|---|
| GPQA Diamond | — | 88.5% |
| SimpleQA Verified | — | 19.1% |
| LMArena Expert | — | 1442 |

## Multimodal

- Devstral Small 2505: —
- Inkling-Small: 39.1 (#62)

| Benchmark | Devstral Small 2505 | Inkling-Small |
|---|---|---|
| LMArena Vision | — | 1235 |

## Multilingual

- Devstral Small 2505: —
- Inkling-Small: 51.7 (#104)

| Benchmark | Devstral Small 2505 | Inkling-Small |
|---|---|---|
| LMArena Non-English | — | 1402 |
| LMArena Chinese | — | 1465 |
| LMArena French | — | 1436 |
| LMArena German | — | 1405 |
| LMArena Japanese | — | 1405 |
| LMArena Korean | — | 1363 |
| LMArena Russian | — | 1391 |
| LMArena Spanish | — | 1428 |

## Instruction Following

- Devstral Small 2505: —
- Inkling-Small: 73.8 (#114)

| Benchmark | Devstral Small 2505 | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | — | 1399 |

## Long Context

- Devstral Small 2505: —
- Inkling-Small: 42.7 (#118)

| Benchmark | Devstral Small 2505 | Inkling-Small |
|---|---|---|
| LMArena Longer Query | — | 1401 |

## Writing & Preference

- Devstral Small 2505: —
- Inkling-Small: 59.6 (#107)

| Benchmark | Devstral Small 2505 | Inkling-Small |
|---|---|---|
| LMArena Text | — | 1414 |
| LMArena Creative Writing | — | 1331 |
| EQ-Bench Creative Writing | — | 1491 |
| LMArena Multi-Turn | — | 1418 |

## FAQ

### Is Devstral Small 2505 better than Inkling-Small?

Inkling-Small is the stronger model overall, scoring 46.5 to 34.3 on the Noometry Index. Devstral Small 2505 costs 4.2× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.

### Which is cheaper, Devstral Small 2505 or Inkling-Small?

Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Inkling-Small lists at $0.45 and $1.20.

### Is Devstral Small 2505 or Inkling-Small better for coding?

Inkling-Small scores higher on coding benchmarks: 43.6 versus 38.9 in the Noometry coding category.

### Which has the bigger context window?

Inkling-Small does, with 524K tokens against 128K.

### How many benchmarks do Devstral Small 2505 and Inkling-Small share?

2 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Inkling-Small has 33.