# Devstral Medium vs Gemini 3.6 Flash

> Gemini 3.6 Flash has enough public results to be ranked (#33); Devstral Medium does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/devstral-medium-vs-gemini-3-6-flash
- Last updated: 2026-10-11
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. Devstral Medium scores higher in 0 categories and Gemini 3.6 Flash in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.6 Flash leads 58.8 to 21.1.
- Devstral Medium is cheaper at $0.40 / $2 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.6 Flash.
- Gemini 3.6 Flash accepts more context: 1.05M tokens versus 262K.
- Devstral Medium has downloadable open weights; the other is API-only.

## Snapshot

| | Devstral Medium | Gemini 3.6 Flash |
|---|---|---|
| Provider | Mistral AI | Google |
| Noometry Index | 30.1 | 54.1 |
| Rank | — | 33 |
| Context | 262K | 1.05M |
| Input $/M | $0.40 | $0.75 |
| Output $/M | $2 | $3.75 |
| Weights | Open | Proprietary |

## Coding

- Devstral Medium: 24.3
- Gemini 3.6 Flash: 50.0 (#48)

| Benchmark | Devstral Medium | Gemini 3.6 Flash |
|---|---|---|
| LMArena WebDev | 1076 | 1538 |
| DeepSWE | — | 46.7% |
| FrontierCode | — | 34.4% |
| SciCode | — | 52.7% |
| WeirdML | — | 56.1% |
| LMArena Coding | — | 1491 |
| ALE-Bench | — | 715.52 |

## Agentic & Tool Use

- Devstral Medium: —
- Gemini 3.6 Flash: 32.3 (#65)

| Benchmark | Devstral Medium | Gemini 3.6 Flash |
|---|---|---|
| APEX-Agents | — | 46.9% |
| GDP.pdf | — | 14% |

## Reasoning

- Devstral Medium: 21.1
- Gemini 3.6 Flash: 58.8 (#22)

| Benchmark | Devstral Medium | Gemini 3.6 Flash |
|---|---|---|
| ARC-AGI-2 | — | 60.4% |
| Kagi LLM Benchmark | 37.7% | — |
| NYT Connections (extended) | — | 89% |
| ARC-AGI-1 | — | 91.2% |
| CritPt | — | 10.6% |
| Chess Puzzles | — | 43% |
| LMArena Hard Prompts | — | 1485 |
| Mystery Game Puzzles | — | 30% |
| DTBench | — | 95.5% |
| LMCA | — | 44.9% |
| Epoch Capabilities Index | — | 154.25 |

## Math

- Devstral Medium: —
- Gemini 3.6 Flash: 57.3 (#40)

| Benchmark | Devstral Medium | Gemini 3.6 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 58.9% |
| FrontierMath Tier 4 | — | 22% |
| MathArena Final-Answer Competitions | — | 70.8% |
| OTIS Mock AIME 2024-2025 | — | 94.2% |
| ProofBench | — | 36% |
| LMArena Math | — | 1505 |

## Knowledge

- Devstral Medium: —
- Gemini 3.6 Flash: 67.8 (#8)

| Benchmark | Devstral Medium | Gemini 3.6 Flash |
|---|---|---|
| GPQA Diamond | — | 94.1% |
| SimpleQA Verified | — | 66.2% |
| LMArena Expert | — | 1488 |

## Multimodal

- Devstral Medium: —
- Gemini 3.6 Flash: 38.5 (#64)

| Benchmark | Devstral Medium | Gemini 3.6 Flash |
|---|---|---|
| LMArena Vision | — | 1298 |
| Blueprint-Bench 2 | — | 31.2% |
| Furniture Assembly | — | 23.3% |
| LMArena Document | — | 1456 |

## Multilingual

- Devstral Medium: —
- Gemini 3.6 Flash: 56.5 (#19)

| Benchmark | Devstral Medium | Gemini 3.6 Flash |
|---|---|---|
| LMArena Non-English | — | 1469 |
| LMArena Chinese | — | 1531 |
| LMArena French | — | 1504 |
| LMArena German | — | 1478 |
| LMArena Japanese | — | 1476 |
| LMArena Korean | — | 1431 |
| LMArena Russian | — | 1487 |
| LMArena Spanish | — | 1475 |

## Instruction Following

- Devstral Medium: —
- Gemini 3.6 Flash: 77.0 (#33)

| Benchmark | Devstral Medium | Gemini 3.6 Flash |
|---|---|---|
| LMArena Instruction Following | — | 1466 |

## Long Context

- Devstral Medium: —
- Gemini 3.6 Flash: 45.1 (#50)

| Benchmark | Devstral Medium | Gemini 3.6 Flash |
|---|---|---|
| LMArena Longer Query | — | 1474 |

## Writing & Preference

- Devstral Medium: —
- Gemini 3.6 Flash: 68.2 (#27)

| Benchmark | Devstral Medium | Gemini 3.6 Flash |
|---|---|---|
| LMArena Text | — | 1479 |
| LMArena Creative Writing | — | 1465 |
| EQ-Bench Creative Writing | — | 1604 |
| LMArena Multi-Turn | — | 1481 |

## FAQ

### Is Devstral Medium better than Gemini 3.6 Flash?

Gemini 3.6 Flash has enough public results to be ranked (#33); Devstral Medium does not yet, so treat this comparison as directional.

### Which is cheaper, Devstral Medium or Gemini 3.6 Flash?

Devstral Medium is cheaper. It lists at $0.40 per million input tokens and $2 per million output tokens; Gemini 3.6 Flash lists at $0.75 and $3.75.

### Is Devstral Medium or Gemini 3.6 Flash better for coding?

Gemini 3.6 Flash scores higher on coding benchmarks: 50.0 versus 24.3 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.6 Flash does, with 1.05M tokens against 262K.

### How many benchmarks do Devstral Medium and Gemini 3.6 Flash share?

1 benchmark has published results for both models. Devstral Medium has 2 scored results on Noometry and Gemini 3.6 Flash has 46.