# Gemini 3 Flash Preview vs Mistral Medium

> Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 36.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-3-flash-preview-vs-mistral-medium
- Last updated: 2026-10-11
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. Gemini 3 Flash Preview scores higher in 10 categories and Mistral Medium in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 3 Flash Preview leads 58.8 to 25.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 95.6% for Gemini 3 Flash Preview and 32.2% for Mistral Medium.
- Gemini 3 Flash Preview is cheaper at $0.50 / $3 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 262K.
- Mistral Medium has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3 Flash Preview | Mistral Medium |
|---|---|---|
| Provider | Google | Mistral AI |
| Noometry Index | 52.3 | 36.3 |
| Rank | 40 | 218 |
| Context | 1.05M | 262K |
| Input $/M | $0.50 | $1.50 |
| Output $/M | $3 | $7.50 |
| Weights | Proprietary | Open |

## Coding

- Gemini 3 Flash Preview: 50.9 (#42)
- Mistral Medium: 34.2 (#243)

| Benchmark | Gemini 3 Flash Preview | Mistral Medium |
|---|---|---|
| WeirdML | 61.6% | 43.7% |
| LMArena Coding | 1460 | 1434 |
| ALE-Bench | 1,367 | 763.98 |
| SWE-bench Verified | 75.4% | — |
| FrontierCode | — | 8% |
| SWE-bench Verified (bash only) | 75.8% | — |
| LMArena WebDev | 1439 | — |
| SWE-bench Multilingual | 72.7% | — |
| SciCode | — | 40.2% |
| GSO | 9.8% | — |

## Agentic & Tool Use

- Gemini 3 Flash Preview: 38.7 (#29)
- Mistral Medium: 28.3 (#90)

| Benchmark | Gemini 3 Flash Preview | Mistral Medium |
|---|---|---|
| Terminal-Bench | 64.3% | — |
| Berkeley Function Calling Leaderboard | — | 37.7% |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 27.3% | — |
| τ²-bench Retail | 76.8% | — |
| τ²-bench Telecom | 91.2% | — |
| DeepResearch Bench | 49.8% | — |
| BALROG | 48.1% | — |
| GDP.pdf | 10% | — |
| LMArena Search | 1198 | — |
| Vending-Bench 2 | 3,635 | — |

## Reasoning

- Gemini 3 Flash Preview: 49.2 (#37)
- Mistral Medium: 24.0 (#167)

| Benchmark | Gemini 3 Flash Preview | Mistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1465 | 1426 |
| DTBench | 89.1% | 75.5% |
| LMCA | 43.1% | 26.1% |
| ARC-AGI-2 | 33.6% | — |
| SimpleBench | 61.1% | — |
| Kagi LLM Benchmark | — | 50% |
| NYT Connections (extended) | 83.1% | — |
| ARC-AGI-1 | 84.7% | — |
| CritPt | — | 0% |
| Chess Puzzles | 40% | — |
| Mystery Game Puzzles | 26% | — |
| Surface Evolver Bench | — | 26.9% |
| Epoch Capabilities Index | 151.8 | — |
| ForecastBench | 58.5 | — |

## Math

- Gemini 3 Flash Preview: 51.7 (#55)
- Mistral Medium: 28.1 (#245)

| Benchmark | Gemini 3 Flash Preview | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 95.6% | 32.2% |
| ProofBench | 15% | 9% |
| LMArena Math | 1473 | 1408 |
| FrontierMath (Feb 2025 set) | 35.6% | 0.3% |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 17.1% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| MATH Level 5 | — | 81.6% |
| FrontierMath Tier 4 (v1) | 4.2% | — |

## Knowledge

- Gemini 3 Flash Preview: 58.8 (#33)
- Mistral Medium: 25.0 (#265)

| Benchmark | Gemini 3 Flash Preview | Mistral Medium |
|---|---|---|
| GPQA Diamond | 89.4% | 59.5% |
| Vectara Hallucination Rate | 13.5% | 22.7% |
| LMArena Expert | 1462 | 1408 |
| Humanity's Last Exam | — | 4.5% |
| SimpleQA Verified | 66.8% | — |

## Multimodal

- Gemini 3 Flash Preview: 45.5 (#16)
- Mistral Medium: 35.3 (#88)

| Benchmark | Gemini 3 Flash Preview | Mistral Medium |
|---|---|---|
| LMArena Vision | 1285 | 1172 |
| GeoBench | 88% | — |
| VPCT | 72.6% | — |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1413 | — |

## Multilingual

- Gemini 3 Flash Preview: 55.7 (#27)
- Mistral Medium: 52.1 (#91)

| Benchmark | Gemini 3 Flash Preview | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1458 | 1408 |
| LMArena Chinese | 1511 | 1447 |
| LMArena French | 1477 | 1459 |
| LMArena German | 1497 | 1432 |
| LMArena Japanese | 1489 | 1378 |
| LMArena Korean | 1443 | 1380 |
| LMArena Russian | 1480 | 1411 |
| LMArena Spanish | 1469 | 1433 |

## Instruction Following

- Gemini 3 Flash Preview: 75.7 (#56)
- Mistral Medium: 73.7 (#116)

| Benchmark | Gemini 3 Flash Preview | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1437 | 1398 |

## Long Context

- Gemini 3 Flash Preview: 44.4 (#67)
- Mistral Medium: 42.9 (#114)

| Benchmark | Gemini 3 Flash Preview | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1452 | 1406 |

## Writing & Preference

- Gemini 3 Flash Preview: 65.5 (#45)
- Mistral Medium: 60.0 (#103)

| Benchmark | Gemini 3 Flash Preview | Mistral Medium |
|---|---|---|
| LMArena Text | 1466 | 1424 |
| LMArena Creative Writing | 1457 | 1391 |
| LMArena Multi-Turn | 1471 | 1418 |
| Short-Story Creative Writing | — | 77.3% |

## FAQ

### Is Gemini 3 Flash Preview better than Mistral Medium?

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 36.3 on the Noometry Index.

### Which is cheaper, Gemini 3 Flash Preview or Mistral Medium?

Gemini 3 Flash Preview is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; Mistral Medium lists at $1.50 and $7.50.

### Is Gemini 3 Flash Preview or Mistral Medium better for coding?

Gemini 3 Flash Preview scores higher on coding benchmarks: 50.9 versus 34.2 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3 Flash Preview does, with 1.05M tokens against 262K.

### How many benchmarks do Gemini 3 Flash Preview and Mistral Medium share?

27 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and Mistral Medium has 36.