# Devstral Small 2505 vs Step 3.7 Flash

> Step 3.7 Flash is the stronger model overall, scoring 36.5 to 33.9 on the Noometry Index. Devstral Small 2505 costs 2.8× less per token, which makes it the better buy when Step 3.7 Flash's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/devstral-small-vs-step-3-7-flash
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. Devstral Small 2505 scores higher in 0 categories and Step 3.7 Flash in 2 categories; one gap is clear of the uncertainty.
- The biggest single-benchmark swing is SciCode: 28.8% for Devstral Small 2505 and 40% for Step 3.7 Flash.
- Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.18 / $1.11 for Step 3.7 Flash.
- Step 3.7 Flash accepts more context: 256K tokens versus 128K.

## Snapshot

| | Devstral Small 2505 | Step 3.7 Flash |
|---|---|---|
| Provider | Mistral AI | StepFun |
| Noometry Index | 33.9 | 36.5 |
| Rank | 228 | 207 |
| Context | 128K | 256K |
| Input $/M | $0.10 | $0.18 |
| Output $/M | $0.30 | $1.11 |
| Weights | Open | Open |

## Coding

- Devstral Small 2505: 38.6 (#160)
- Step 3.7 Flash: 39.4 (#147)

| Benchmark | Devstral Small 2505 | Step 3.7 Flash |
|---|---|---|
| SciCode | 28.8% | 40% |
| SWE-bench Verified (bash only) | 56.4% | — |
| ALE-Bench | — | 694.12 |

## Reasoning

- Devstral Small 2505: 19.1 (#243)
- Step 3.7 Flash: 20.9 (#211)

| Benchmark | Devstral Small 2505 | Step 3.7 Flash |
|---|---|---|
| CritPt | 0% | 2.3% |
| Kagi LLM Benchmark | 37.7% | — |
| NYT Connections (extended) | — | 39.7% |

## Math

- Devstral Small 2505: —
- Step 3.7 Flash: 40.9 (#74)

| Benchmark | Devstral Small 2505 | Step 3.7 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | — | 68.5% |

## FAQ

### Is Devstral Small 2505 better than Step 3.7 Flash?

Step 3.7 Flash is the stronger model overall, scoring 36.5 to 33.9 on the Noometry Index. Devstral Small 2505 costs 2.8× less per token, which makes it the better buy when Step 3.7 Flash's lead doesn't matter for your workload.

### Which is cheaper, Devstral Small 2505 or Step 3.7 Flash?

Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Step 3.7 Flash lists at $0.18 and $1.11.

### Is Devstral Small 2505 or Step 3.7 Flash better for coding?

They score almost the same on coding (38.6 vs 39.4); test both on your own repository before choosing.

### Which has the bigger context window?

Step 3.7 Flash does, with 256K tokens against 128K.

### How many benchmarks do Devstral Small 2505 and Step 3.7 Flash share?

2 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Step 3.7 Flash has 5.