# Gemini 2.5 Flash-Lite vs Mistral Small

> Gemini 2.5 Flash-Lite is the stronger model overall, scoring 37.0 to 33.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-2-5-flash-lite-vs-mistral-small
- Last updated: 2026-10-10
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. Gemini 2.5 Flash-Lite scores higher in 7 categories and Mistral Small in 3 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 2.5 Flash-Lite leads 38.0 to 16.4.
- The biggest single-benchmark swing is DTBench: 62.8% for Gemini 2.5 Flash-Lite and 70.9% for Mistral Small.
- Gemini 2.5 Flash-Lite is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.15 / $0.60 for Mistral Small.
- Gemini 2.5 Flash-Lite accepts more context: 1.05M tokens versus 262K.
- Mistral Small has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 2.5 Flash-Lite | Mistral Small |
|---|---|---|
| Provider | Google | Mistral AI |
| Noometry Index | 37.0 | 33.4 |
| Rank | 211 | 243 |
| Context | 1.05M | 262K |
| Input $/M | $0.10 | $0.15 |
| Output $/M | $0.40 | $0.60 |
| Weights | Proprietary | Open |

## Coding

- Gemini 2.5 Flash-Lite: 38.5 (#173)
- Mistral Small: 34.0 (#247)

| Benchmark | Gemini 2.5 Flash-Lite | Mistral Small |
|---|---|---|
| LMArena Coding | 1373 | 1362 |
| ALE-Bench | 325.9 | 497.62 |
| SciCode | — | 26.5% |
| WeirdML | 35.2% | — |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |

## Agentic & Tool Use

- Gemini 2.5 Flash-Lite: 28.0 (#96)
- Mistral Small: 28.1 (#93)

| Benchmark | Gemini 2.5 Flash-Lite | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | 36.9% | 37.1% |

## Reasoning

- Gemini 2.5 Flash-Lite: 22.2 (#205)
- Mistral Small: 19.8 (#250)

| Benchmark | Gemini 2.5 Flash-Lite | Mistral Small |
|---|---|---|
| Kagi LLM Benchmark | 40.5% | 37.8% |
| LMArena Hard Prompts | 1377 | 1335 |
| DTBench | 62.8% | 70.9% |
| LMCA | 18.1% | 20.6% |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 44.8% |
| LiveBench Data Analysis | — | 53.7% |
| Epoch Capabilities Index | 133.94 | — |
| LiveBench | — | 44% |

## Math

- Gemini 2.5 Flash-Lite: 38.0 (#144)
- Mistral Small: 16.4 (#293)

| Benchmark | Gemini 2.5 Flash-Lite | Mistral Small |
|---|---|---|
| LMArena Math | 1373 | 1341 |
| OTIS Mock AIME 2024-2025 | — | 5.8% |
| Omni-MATH | 48% | — |
| LiveBench Math | — | 39.9% |
| MATH Level 5 | — | 46.8% |

## Knowledge

- Gemini 2.5 Flash-Lite: 32.5 (#210)
- Mistral Small: 31.0 (#222)

| Benchmark | Gemini 2.5 Flash-Lite | Mistral Small |
|---|---|---|
| Vectara Hallucination Rate | 3.3% | 5.1% |
| LMArena Expert | 1373 | 1291 |
| GPQA Diamond | — | 47.5% |
| MMLU-Pro | 53.7% | — |
| GPQA (HELM) | 30.9% | — |
| MMLU | — | 68.7% |

## Multimodal

- Gemini 2.5 Flash-Lite: 29.1 (#114)
- Mistral Small: 33.5 (#96)

| Benchmark | Gemini 2.5 Flash-Lite | Mistral Small |
|---|---|---|
| LMArena Vision | 1198 | 1142 |
| VPCT | 30% | — |

## Multilingual

- Gemini 2.5 Flash-Lite: 49.3 (#134)
- Mistral Small: 45.5 (#169)

| Benchmark | Gemini 2.5 Flash-Lite | Mistral Small |
|---|---|---|
| LMArena Non-English | 1369 | 1315 |
| LMArena Chinese | 1404 | 1340 |
| LMArena French | 1388 | 1337 |
| LMArena German | 1389 | 1340 |
| LMArena Japanese | 1359 | 1275 |
| LMArena Korean | 1360 | 1259 |
| LMArena Russian | 1373 | 1324 |
| LMArena Spanish | 1396 | 1346 |

## Instruction Following

- Gemini 2.5 Flash-Lite: 70.0 (#168)
- Mistral Small: 66.4 (#209)

| Benchmark | Gemini 2.5 Flash-Lite | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1367 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
| IFEval | 81% | — |

## Long Context

- Gemini 2.5 Flash-Lite: 33.3 (#262)
- Mistral Small: 40.4 (#156)

| Benchmark | Gemini 2.5 Flash-Lite | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1373 | 1327 |
| Fiction.LiveBench | 47.2% | — |

## Writing & Preference

- Gemini 2.5 Flash-Lite: 56.8 (#135)
- Mistral Small: 52.5 (#171)

| Benchmark | Gemini 2.5 Flash-Lite | Mistral Small |
|---|---|---|
| LMArena Text | 1379 | 1338 |
| LMArena Creative Writing | 1367 | 1305 |
| LMArena Multi-Turn | 1366 | 1344 |
| WildBench | 81.8% | — |
| LiveBench Language | — | 30.5% |

## FAQ

### Is Gemini 2.5 Flash-Lite better than Mistral Small?

Gemini 2.5 Flash-Lite is the stronger model overall, scoring 37.0 to 33.4 on the Noometry Index.

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

Gemini 2.5 Flash-Lite is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Mistral Small lists at $0.15 and $0.60.

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

Gemini 2.5 Flash-Lite scores higher on coding benchmarks: 38.5 versus 34.0 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 Small share?

24 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and Mistral Small has 39.