# Devstral Small 2505 vs Gemini 3.7 Flash

> Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 34.3 on the Noometry Index. Devstral Small 2505 costs 10.0× less per token, which makes it the better buy when Gemini 3.7 Flash's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/devstral-small-vs-gemini-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 Gemini 3.7 Flash in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.7 Flash leads 70.0 to 19.7.
- The biggest single-benchmark swing is SciCode: 28.8% for Devstral Small 2505 and 59.8% for Gemini 3.7 Flash.
- Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.7 Flash.
- Gemini 3.7 Flash accepts more context: 1.05M tokens versus 128K.
- Devstral Small 2505 has downloadable open weights; the other is API-only.

## Snapshot

| | Devstral Small 2505 | Gemini 3.7 Flash |
|---|---|---|
| Provider | Mistral AI | Google |
| Noometry Index | 34.3 | 59.8 |
| Rank | 233 | 14 |
| Context | 128K | 1.05M |
| Input $/M | $0.10 | $0.75 |
| Output $/M | $0.30 | $3.75 |
| Weights | Open | Proprietary |

## Coding

- Devstral Small 2505: 38.9 (#166)
- Gemini 3.7 Flash: 56.2 (#22)

| Benchmark | Devstral Small 2505 | Gemini 3.7 Flash |
|---|---|---|
| SciCode | 28.8% | 59.8% |
| DeepSWE | — | 65.5% |
| FrontierCode | — | 43.6% |
| SWE-bench Verified (bash only) | 56.4% | — |
| LMArena WebDev | — | 1592 |
| FrontierSWE | — | 20.3% |
| LMArena Coding | — | 1497 |
| ALE-Bench | — | 904.3 |

## Agentic & Tool Use

- Devstral Small 2505: —
- Gemini 3.7 Flash: 42.1 (#19)

| Benchmark | Devstral Small 2505 | Gemini 3.7 Flash |
|---|---|---|
| APEX-Agents | — | 67.8% |
| Remote Labor Index | — | 5% |
| GDP.pdf | — | 23.8% |

## Reasoning

- Devstral Small 2505: 19.7 (#252)
- Gemini 3.7 Flash: 70.0 (#15)

| Benchmark | Devstral Small 2505 | Gemini 3.7 Flash |
|---|---|---|
| CritPt | 0% | 14.3% |
| ARC-AGI-2 | — | 84.6% |
| Kagi LLM Benchmark | 37.7% | — |
| NYT Connections (extended) | — | 94% |
| ARC-AGI-1 | — | 95.5% |
| Chess Puzzles | — | 47% |
| LMArena Hard Prompts | — | 1494 |
| Mystery Game Puzzles | — | 37% |
| DTBench | — | 96.8% |
| LMCA | — | 50.4% |
| Epoch Capabilities Index | — | 157.27 |

## Math

- Devstral Small 2505: —
- Gemini 3.7 Flash: 69.6 (#23)

| Benchmark | Devstral Small 2505 | Gemini 3.7 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 71.6% |
| FrontierMath Tier 4 | — | 36.6% |
| OTIS Mock AIME 2024-2025 | — | 97.2% |
| ProofBench | — | 58% |
| LMArena Math | — | 1507 |

## Knowledge

- Devstral Small 2505: —
- Gemini 3.7 Flash: 69.7 (#5)

| Benchmark | Devstral Small 2505 | Gemini 3.7 Flash |
|---|---|---|
| GPQA Diamond | — | 94.8% |
| SimpleQA Verified | — | 69.2% |
| LMArena Expert | — | 1508 |

## Multimodal

- Devstral Small 2505: —
- Gemini 3.7 Flash: 37.3 (#73)

| Benchmark | Devstral Small 2505 | Gemini 3.7 Flash |
|---|---|---|
| LMArena Vision | — | 1316 |
| Furniture Assembly | — | 26.7% |

## Multilingual

- Devstral Small 2505: —
- Gemini 3.7 Flash: 57.6 (#7)

| Benchmark | Devstral Small 2505 | Gemini 3.7 Flash |
|---|---|---|
| LMArena Non-English | — | 1484 |
| LMArena Chinese | — | 1548 |
| LMArena French | — | 1505 |
| LMArena German | — | 1498 |
| LMArena Japanese | — | 1512 |
| LMArena Korean | — | 1483 |
| LMArena Russian | — | 1516 |
| LMArena Spanish | — | 1503 |

## Instruction Following

- Devstral Small 2505: —
- Gemini 3.7 Flash: 77.7 (#15)

| Benchmark | Devstral Small 2505 | Gemini 3.7 Flash |
|---|---|---|
| LMArena Instruction Following | — | 1483 |

## Long Context

- Devstral Small 2505: —
- Gemini 3.7 Flash: 45.7 (#30)

| Benchmark | Devstral Small 2505 | Gemini 3.7 Flash |
|---|---|---|
| LMArena Longer Query | — | 1492 |

## Writing & Preference

- Devstral Small 2505: —
- Gemini 3.7 Flash: 71.2 (#20)

| Benchmark | Devstral Small 2505 | Gemini 3.7 Flash |
|---|---|---|
| LMArena Text | — | 1486 |
| LMArena Creative Writing | — | 1490 |
| EQ-Bench Creative Writing | — | 1723 |
| LMArena Multi-Turn | — | 1489 |

## FAQ

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

Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 34.3 on the Noometry Index. Devstral Small 2505 costs 10.0× less per token, which makes it the better buy when Gemini 3.7 Flash's lead doesn't matter for your workload.

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

Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Gemini 3.7 Flash lists at $0.75 and $3.75.

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

Gemini 3.7 Flash scores higher on coding benchmarks: 56.2 versus 38.9 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.7 Flash does, with 1.05M tokens against 128K.

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

2 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Gemini 3.7 Flash has 44.