# Devstral 2 vs Gemini 3.8 Flash

> Gemini 3.8 Flash has enough public results to be ranked (#13); Devstral 2 does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/devstral-2-vs-gemini-3-8-flash
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. Devstral 2 scores higher in 0 categories and Gemini 3.8 Flash in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where Gemini 3.8 Flash leads 56.4 to 33.0.
- Devstral 2 is cheaper at $0.40 / $2 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.8 Flash.
- Gemini 3.8 Flash accepts more context: 1.05M tokens versus 262K.
- Devstral 2 has downloadable open weights; the other is API-only.

## Snapshot

| | Devstral 2 | Gemini 3.8 Flash |
|---|---|---|
| Provider | Mistral AI | Google |
| Noometry Index | 35.8 | 59.5 |
| Rank | — | 13 |
| Context | 262K | 1.05M |
| Input $/M | $0.40 | $0.75 |
| Output $/M | $2 | $3.75 |
| Weights | Open | Proprietary |

## Coding

- Devstral 2: 33.0 (#253)
- Gemini 3.8 Flash: 56.4 (#17)

| Benchmark | Devstral 2 | Gemini 3.8 Flash |
|---|---|---|
| LMArena WebDev | 1196 | 1581 |
| DeepSWE | — | 73.8% |
| FrontierCode | — | 41.2% |
| SWE-bench Verified (bash only) | 53.8% | — |
| CursorBench | — | 39.6% |
| FrontierSWE | — | 19.6% |
| SciCode | — | 56.6% |
| LMArena Coding | — | 1512 |
| ALE-Bench | — | 1,270 |

## Agentic & Tool Use

- Devstral 2: —
- Gemini 3.8 Flash: 40.3 (#22)

| Benchmark | Devstral 2 | Gemini 3.8 Flash |
|---|---|---|
| APEX-Agents | — | 64.3% |
| GDP.pdf | — | 23.4% |
| Vending-Bench 2 | — | 5,094 |

## Reasoning

- Devstral 2: —
- Gemini 3.8 Flash: 64.7 (#13)

| Benchmark | Devstral 2 | Gemini 3.8 Flash |
|---|---|---|
| NYT Connections (extended) | — | 97.4% |
| CritPt | — | 18.3% |
| Chess Puzzles | — | 61% |
| LMArena Hard Prompts | — | 1506 |
| Mystery Game Puzzles | — | 47% |
| DTBench | — | 95.7% |
| LMCA | — | 52.9% |
| Surface Evolver Bench | — | 76.9% |
| Epoch Capabilities Index | — | 157.13 |

## Math

- Devstral 2: —
- Gemini 3.8 Flash: 65.2 (#22)

| Benchmark | Devstral 2 | Gemini 3.8 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 68.4% |
| FrontierMath Tier 4 | — | 22% |
| OTIS Mock AIME 2024-2025 | — | 98.9% |
| ProofBench | — | 48% |
| LMArena Math | — | 1528 |

## Knowledge

- Devstral 2: —
- Gemini 3.8 Flash: 74.9 (#2)

| Benchmark | Devstral 2 | Gemini 3.8 Flash |
|---|---|---|
| GPQA Diamond | — | 95.4% |
| Humanity's Last Exam | — | 44.5% |
| SimpleQA Verified | — | 69.7% |
| LMArena Expert | — | 1529 |

## Multimodal

- Devstral 2: —
- Gemini 3.8 Flash: 40.9 (#33)

| Benchmark | Devstral 2 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Vision | — | 1312 |
| Blueprint-Bench 2 | — | 38.6% |
| Furniture Assembly | — | 31.7% |

## Multilingual

- Devstral 2: —
- Gemini 3.8 Flash: 57.9 (#5)

| Benchmark | Devstral 2 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Non-English | — | 1486 |
| LMArena Chinese | — | 1547 |
| LMArena French | — | 1502 |
| LMArena German | — | 1470 |
| LMArena Japanese | — | 1505 |
| LMArena Korean | — | 1479 |
| LMArena Russian | — | 1507 |
| LMArena Spanish | — | 1492 |

## Instruction Following

- Devstral 2: —
- Gemini 3.8 Flash: 78.2 (#11)

| Benchmark | Devstral 2 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Instruction Following | — | 1489 |

## Long Context

- Devstral 2: —
- Gemini 3.8 Flash: 46.2 (#23)

| Benchmark | Devstral 2 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Longer Query | — | 1506 |

## Writing & Preference

- Devstral 2: —
- Gemini 3.8 Flash: 72.1 (#16)

| Benchmark | Devstral 2 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Text | — | 1494 |
| LMArena Creative Writing | — | 1485 |
| EQ-Bench Creative Writing | — | 1748 |
| LMArena Multi-Turn | — | 1503 |

## FAQ

### Is Devstral 2 better than Gemini 3.8 Flash?

Gemini 3.8 Flash has enough public results to be ranked (#13); Devstral 2 does not yet, so treat this comparison as directional.

### Which is cheaper, Devstral 2 or Gemini 3.8 Flash?

Devstral 2 is cheaper. It lists at $0.40 per million input tokens and $2 per million output tokens; Gemini 3.8 Flash lists at $0.75 and $3.75.

### Is Devstral 2 or Gemini 3.8 Flash better for coding?

Gemini 3.8 Flash scores higher on coding benchmarks: 56.4 versus 33.0 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.8 Flash does, with 1.05M tokens against 262K.

### How many benchmarks do Devstral 2 and Gemini 3.8 Flash share?

1 benchmark has published results for both models. Devstral 2 has 2 scored results on Noometry and Gemini 3.8 Flash has 46.