# Gemini 2.5 Flash-Lite vs Mistral Large 3

> Mistral Large 3 is the stronger model overall, scoring 38.6 to 36.4 on the Noometry Index. Gemini 2.5 Flash-Lite costs 2.1× less per token, which makes it the better buy when Mistral Large 3's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-2-5-flash-lite-vs-mistral-large-3
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. Gemini 2.5 Flash-Lite scores higher in 2 categories and Mistral Large 3 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where Mistral Large 3 leads 43.1 to 33.3.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 3.3% for Gemini 2.5 Flash-Lite and 14.5% for Mistral Large 3.
- Gemini 2.5 Flash-Lite is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.25 / $0.75 for Mistral Large 3.
- Gemini 2.5 Flash-Lite accepts more context: 1.05M tokens versus 262K.
- Mistral Large 3 has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 2.5 Flash-Lite | Mistral Large 3 |
|---|---|---|
| Provider | Google | Mistral AI |
| Noometry Index | 36.4 | 38.6 |
| Rank | 208 | 172 |
| Context | 1.05M | 262K |
| Input $/M | $0.10 | $0.25 |
| Output $/M | $0.40 | $0.75 |
| Weights | Proprietary | Open |

## Coding

- Gemini 2.5 Flash-Lite: 38.0 (#167)
- Mistral Large 3: 34.1 (#230)

| Benchmark | Gemini 2.5 Flash-Lite | Mistral Large 3 |
|---|---|---|
| LMArena Coding | 1373 | 1447 |
| LMArena WebDev | — | 1230 |
| WeirdML | 35.2% | — |
| ALE-Bench | 325.9 | — |

## Agentic & Tool Use

- Gemini 2.5 Flash-Lite: 27.8 (#89)
- Mistral Large 3: —

| Benchmark | Gemini 2.5 Flash-Lite | Mistral Large 3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 36.9% | — |

## Reasoning

- Gemini 2.5 Flash-Lite: 21.5 (#196)
- Mistral Large 3: 14.6 (#314)

| Benchmark | Gemini 2.5 Flash-Lite | Mistral Large 3 |
|---|---|---|
| Kagi LLM Benchmark | 40.5% | 50.9% |
| LMArena Hard Prompts | 1377 | 1429 |
| NYT Connections (extended) | — | 7.5% |
| Thematic Generalization | — | 23% |
| DTBench | 62.8% | — |
| LMCA | 18.1% | — |
| Epoch Capabilities Index | 133.93 | — |

## Math

- Gemini 2.5 Flash-Lite: 35.5 (#144)
- Mistral Large 3: 36.0 (#131)

| Benchmark | Gemini 2.5 Flash-Lite | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1373 | 1415 |
| Omni-MATH | 48% | — |

## Knowledge

- Gemini 2.5 Flash-Lite: 32.1 (#206)
- Mistral Large 3: 35.5 (#173)

| Benchmark | Gemini 2.5 Flash-Lite | Mistral Large 3 |
|---|---|---|
| Vectara Hallucination Rate | 3.3% | 14.5% |
| LMArena Expert | 1373 | 1421 |
| MMLU-Pro | 53.7% | — |
| GPQA (HELM) | 30.9% | — |

## Multimodal

- Gemini 2.5 Flash-Lite: 28.6 (#109)
- Mistral Large 3: 37.6 (#65)

| Benchmark | Gemini 2.5 Flash-Lite | Mistral Large 3 |
|---|---|---|
| LMArena Vision | 1198 | 1222 |
| VPCT | 30% | — |

## Multilingual

- Gemini 2.5 Flash-Lite: 49.5 (#129)
- Mistral Large 3: 52.6 (#79)

| Benchmark | Gemini 2.5 Flash-Lite | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1369 | 1412 |
| LMArena Chinese | 1404 | 1448 |
| LMArena French | 1388 | 1456 |
| LMArena German | 1390 | 1438 |
| LMArena Japanese | 1359 | 1399 |
| LMArena Korean | 1358 | 1384 |
| LMArena Russian | 1373 | 1412 |
| LMArena Spanish | 1396 | 1437 |

## Instruction Following

- Gemini 2.5 Flash-Lite: 70.2 (#163)
- Mistral Large 3: 74.1 (#104)

| Benchmark | Gemini 2.5 Flash-Lite | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1366 | 1402 |
| IFEval | 81% | — |

## Long Context

- Gemini 2.5 Flash-Lite: 33.3 (#257)
- Mistral Large 3: 43.1 (#102)

| Benchmark | Gemini 2.5 Flash-Lite | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1373 | 1413 |
| Fiction.LiveBench | 47.2% | — |

## Writing & Preference

- Gemini 2.5 Flash-Lite: 57.0 (#130)
- Mistral Large 3: 60.2 (#100)

| Benchmark | Gemini 2.5 Flash-Lite | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1379 | 1427 |
| LMArena Creative Writing | 1366 | 1385 |
| LMArena Multi-Turn | 1367 | 1429 |
| EQ-Bench Creative Writing | — | 1412 |
| WildBench | 81.8% | — |

## FAQ

### Is Gemini 2.5 Flash-Lite better than Mistral Large 3?

Mistral Large 3 is the stronger model overall, scoring 38.6 to 36.4 on the Noometry Index. Gemini 2.5 Flash-Lite costs 2.1× less per token, which makes it the better buy when Mistral Large 3's lead doesn't matter for your workload.

### Which is cheaper, Gemini 2.5 Flash-Lite or Mistral Large 3?

Gemini 2.5 Flash-Lite is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Mistral Large 3 lists at $0.25 and $0.75.

### Is Gemini 2.5 Flash-Lite or Mistral Large 3 better for coding?

Gemini 2.5 Flash-Lite scores higher on coding benchmarks: 38.0 versus 34.1 in the Noometry coding category.

### Which has the bigger context window?

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

### How many benchmarks do Gemini 2.5 Flash-Lite and Mistral Large 3 share?

20 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and Mistral Large 3 has 24.