# Gemini 3.8 Flash vs Mistral Large

> Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 31.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-3-8-flash-vs-mistral-large
- Last updated: 2026-10-10
- Shared benchmarks: 26

## Summary

- They share 26 benchmarks with published results for both. Gemini 3.8 Flash scores higher in 9 categories and Mistral Large in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.8 Flash leads 76.9 to 15.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.9% for Gemini 3.8 Flash and 8.5% for Mistral Large.
- Gemini 3.8 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $2 / $6 for Mistral Large.
- Gemini 3.8 Flash accepts more context: 1.05M tokens versus 131K.
- Mistral Large has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3.8 Flash | Mistral Large |
|---|---|---|
| Provider | Google | Mistral AI |
| Noometry Index | 61.8 | 31.9 |
| Rank | 11 | 263 |
| Context | 1.05M | 131K |
| Input $/M | $0.75 | $2 |
| Output $/M | $3.75 | $6 |
| Weights | Proprietary | Open |

## Coding

- Gemini 3.8 Flash: 59.2 (#15)
- Mistral Large: 34.3 (#240)

| Benchmark | Gemini 3.8 Flash | Mistral Large |
|---|---|---|
| SciCode | 56.6% | 36.2% |
| LMArena Coding | 1510 | 1277 |
| ALE-Bench | 1,270 | 264.7 |
| DeepSWE | 73.8% | — |
| FrontierCode | 41.2% | — |
| CursorBench | 39.6% | — |
| LMArena WebDev | 1584 | — |
| FrontierSWE | 19.6% | — |
| WeirdML | 84.8% | — |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |

## Agentic & Tool Use

- Gemini 3.8 Flash: 41.8 (#21)
- Mistral Large: 28.6 (#89)

| Benchmark | Gemini 3.8 Flash | Mistral Large |
|---|---|---|
| APEX-Agents | 64.3% | — |
| Berkeley Function Calling Leaderboard | — | 38.4% |
| Remote Labor Index | 5.8% | — |
| GDP.pdf | 23.4% | — |
| Vending-Bench 2 | 5,094 | — |

## Reasoning

- Gemini 3.8 Flash: 76.9 (#5)
- Mistral Large: 15.8 (#310)

| Benchmark | Gemini 3.8 Flash | Mistral Large |
|---|---|---|
| CritPt | 18.3% | 0% |
| LMArena Hard Prompts | 1508 | 1257 |
| DTBench | 95.7% | 65.1% |
| LMCA | 52.9% | 16.7% |
| Epoch Capabilities Index | 156.71 | 128.52 |
| ARC-AGI-2 | 89.2% | — |
| SimpleBench | — | 22.5% |
| NYT Connections (extended) | 97.4% | — |
| ARC-AGI-1 | 98.5% | — |
| Chess Puzzles | 61% | — |
| LiveBench Reasoning | — | 43.5% |
| Mystery Game Puzzles | 47% | — |
| LiveBench Data Analysis | — | 50.1% |
| Surface Evolver Bench | 76.9% | — |
| ForecastBench | — | 57.1 |
| LiveBench | — | 48.4% |

## Math

- Gemini 3.8 Flash: 65.3 (#28)
- Mistral Large: 18.2 (#291)

| Benchmark | Gemini 3.8 Flash | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.9% | 8.5% |
| LMArena Math | 1528 | 1262 |
| FrontierMath (Tiers 1-3) | 68.4% | — |
| FrontierMath Tier 4 | 22% | — |
| ProofBench | 48% | — |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |

## Knowledge

- Gemini 3.8 Flash: 74.8 (#2)
- Mistral Large: 30.1 (#230)

| Benchmark | Gemini 3.8 Flash | Mistral Large |
|---|---|---|
| GPQA Diamond | 95.4% | 51.3% |
| LMArena Expert | 1524 | 1232 |
| Humanity's Last Exam | 44.5% | — |
| SimpleQA Verified | 69.7% | — |
| MMLU-Pro | — | 59.9% |
| Confabulations | — | 21.4% |
| Vectara Hallucination Rate | — | 4.5% |
| GPQA (HELM) | — | 43.5% |
| MMLU | — | 80% |

## Multimodal

- Gemini 3.8 Flash: 40.7 (#45)
- Mistral Large: —

| Benchmark | Gemini 3.8 Flash | Mistral Large |
|---|---|---|
| LMArena Vision | 1314 | — |
| Blueprint-Bench 2 | 38.6% | — |
| Furniture Assembly | 31.7% | — |

## Multilingual

- Gemini 3.8 Flash: 58.0 (#5)
- Mistral Large: 40.0 (#219)

| Benchmark | Gemini 3.8 Flash | Mistral Large |
|---|---|---|
| LMArena Non-English | 1491 | 1237 |
| LMArena Chinese | 1554 | 1240 |
| LMArena French | 1498 | 1325 |
| LMArena German | 1493 | 1254 |
| LMArena Japanese | 1502 | 1188 |
| LMArena Korean | 1459 | 1202 |
| LMArena Russian | 1515 | 1257 |
| LMArena Spanish | 1485 | 1268 |

## Instruction Following

- Gemini 3.8 Flash: 78.0 (#13)
- Mistral Large: 67.9 (#191)

| Benchmark | Gemini 3.8 Flash | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1490 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |

## Long Context

- Gemini 3.8 Flash: 46.3 (#24)
- Mistral Large: 38.3 (#199)

| Benchmark | Gemini 3.8 Flash | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1508 | 1261 |

## Writing & Preference

- Gemini 3.8 Flash: 72.2 (#15)
- Mistral Large: 40.7 (#242)

| Benchmark | Gemini 3.8 Flash | Mistral Large |
|---|---|---|
| LMArena Text | 1499 | 1266 |
| LMArena Creative Writing | 1492 | 1243 |
| EQ-Bench Creative Writing | 1748 | 985 |
| LMArena Multi-Turn | 1501 | 1260 |
| Short-Story Creative Writing | — | 69% |
| WildBench | — | 80.1% |
| LiveBench Language | — | 39.4% |

## FAQ

### Is Gemini 3.8 Flash better than Mistral Large?

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 31.9 on the Noometry Index.

### Which is cheaper, Gemini 3.8 Flash or Mistral Large?

Gemini 3.8 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; Mistral Large lists at $2 and $6.

### Is Gemini 3.8 Flash or Mistral Large better for coding?

Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 34.3 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.8 Flash does, with 1.05M tokens against 131K.

### How many benchmarks do Gemini 3.8 Flash and Mistral Large share?

26 benchmarks have published results for both models. Gemini 3.8 Flash has 50 scored results on Noometry and Mistral Large has 51.