# Gemini 2.5 Flash vs Mistral Medium

> Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 36.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-2-5-flash-vs-mistral-medium
- Last updated: 2026-10-12
- Shared benchmarks: 30

## Summary

- They share 30 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 8 categories and Mistral Medium in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 2.5 Flash leads 39.9 to 28.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 73.1% for Gemini 2.5 Flash and 32.2% for Mistral Medium.
- Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 262K.
- Mistral Medium has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 2.5 Flash | Mistral Medium |
|---|---|---|
| Provider | Google | Mistral AI |
| Noometry Index | 39.3 | 36.3 |
| Rank | 170 | 218 |
| Context | 1.05M | 262K |
| Input $/M | $0.30 | $1.50 |
| Output $/M | $2.50 | $7.50 |
| Weights | Proprietary | Open |

## Coding

- Gemini 2.5 Flash: 35.8 (#220)
- Mistral Medium: 34.2 (#243)

| Benchmark | Gemini 2.5 Flash | Mistral Medium |
|---|---|---|
| WeirdML | 41.9% | 43.7% |
| LMArena Coding | 1424 | 1434 |
| ALE-Bench | 661.88 | 763.98 |
| FrontierCode | — | 8% |
| SWE-bench Verified (bash only) | 28.7% | — |
| Aider Polyglot | 55.1% | — |
| SciCode | — | 40.2% |

## Agentic & Tool Use

- Gemini 2.5 Flash: 30.8 (#74)
- Mistral Medium: 28.3 (#90)

| Benchmark | Gemini 2.5 Flash | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | 56.2% | 37.7% |
| Terminal-Bench | 17.1% | — |
| TheAgentCompany | 41.1% | — |
| BALROG | 33.5% | — |
| Vending-Bench 2 | 548.84 | — |

## Reasoning

- Gemini 2.5 Flash: 18.1 (#286)
- Mistral Medium: 24.0 (#167)

| Benchmark | Gemini 2.5 Flash | Mistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 56.8% | 50% |
| CritPt | 1.1% | 0% |
| LMArena Hard Prompts | 1422 | 1426 |
| DTBench | 76.5% | 75.5% |
| LMCA | 27.5% | 26.1% |
| ARC-AGI-2 | 2.5% | — |
| SimpleBench | 41.2% | — |
| ARC-AGI-1 | 33.3% | — |
| EnigmaEval | 2.7% | — |
| Surface Evolver Bench | — | 26.9% |
| Epoch Capabilities Index | 143.03 | — |
| ForecastBench | 60.6 | — |

## Math

- Gemini 2.5 Flash: 39.9 (#98)
- Mistral Medium: 28.1 (#245)

| Benchmark | Gemini 2.5 Flash | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.1% | 32.2% |
| LMArena Math | 1415 | 1408 |
| FrontierMath (Feb 2025 set) | 4.8% | 0.3% |
| ProofBench | — | 9% |
| Omni-MATH | 38.5% | — |
| MATH Level 5 | — | 81.6% |
| FrontierMath Tier 4 (v1) | 4.2% | — |

## Knowledge

- Gemini 2.5 Flash: 36.4 (#168)
- Mistral Medium: 25.0 (#265)

| Benchmark | Gemini 2.5 Flash | Mistral Medium |
|---|---|---|
| Humanity's Last Exam | 12.1% | 4.5% |
| Vectara Hallucination Rate | 7.8% | 22.7% |
| LMArena Expert | 1426 | 1408 |
| GPQA Diamond | — | 59.5% |
| MMLU-Pro | 63.9% | — |
| Confabulations | 16.8% | — |
| GPQA (HELM) | 39% | — |

## Multimodal

- Gemini 2.5 Flash: 41.8 (#32)
- Mistral Medium: 35.3 (#88)

| Benchmark | Gemini 2.5 Flash | Mistral Medium |
|---|---|---|
| LMArena Vision | 1253 | 1172 |
| GeoBench | 76% | — |
| VPCT | 46.2% | — |
| SpatialViz-Bench | 36.9% | — |

## Multilingual

- Gemini 2.5 Flash: 52.3 (#88)
- Mistral Medium: 52.1 (#91)

| Benchmark | Gemini 2.5 Flash | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1409 | 1408 |
| LMArena Chinese | 1450 | 1447 |
| LMArena French | 1433 | 1459 |
| LMArena German | 1418 | 1432 |
| LMArena Japanese | 1405 | 1378 |
| LMArena Korean | 1385 | 1380 |
| LMArena Russian | 1415 | 1411 |
| LMArena Spanish | 1421 | 1433 |

## Instruction Following

- Gemini 2.5 Flash: 75.7 (#54)
- Mistral Medium: 73.7 (#116)

| Benchmark | Gemini 2.5 Flash | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1405 | 1398 |
| IFEval | 89.8% | — |

## Long Context

- Gemini 2.5 Flash: 47.5 (#17)
- Mistral Medium: 42.9 (#114)

| Benchmark | Gemini 2.5 Flash | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1419 | 1406 |
| Fiction.LiveBench | 77.8% | — |

## Writing & Preference

- Gemini 2.5 Flash: 53.8 (#157)
- Mistral Medium: 60.0 (#103)

| Benchmark | Gemini 2.5 Flash | Mistral Medium |
|---|---|---|
| LMArena Text | 1417 | 1424 |
| LMArena Creative Writing | 1400 | 1391 |
| Short-Story Creative Writing | 76.5% | 77.3% |
| LMArena Multi-Turn | 1408 | 1418 |
| EQ-Bench Creative Writing | 1137 | — |
| WildBench | 81.7% | — |

## FAQ

### Is Gemini 2.5 Flash better than Mistral Medium?

Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 36.3 on the Noometry Index.

### Which is cheaper, Gemini 2.5 Flash or Mistral Medium?

Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Mistral Medium lists at $1.50 and $7.50.

### Is Gemini 2.5 Flash or Mistral Medium better for coding?

Gemini 2.5 Flash scores higher on coding benchmarks: 35.8 versus 34.2 in the Noometry coding category.

### Which has the bigger context window?

Gemini 2.5 Flash does, with 1.05M tokens against 262K.

### How many benchmarks do Gemini 2.5 Flash and Mistral Medium share?

30 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Mistral Medium has 36.