# Gemini 2.5 Flash-Lite vs Mixtral 8x22B

> Gemini 2.5 Flash-Lite is the stronger model overall, scoring 36.4 to 26.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-2-5-flash-lite-vs-mixtral-8x22b
- Last updated: 2026-10-10
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. Gemini 2.5 Flash-Lite scores higher in 8 categories and Mixtral 8x22B in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini 2.5 Flash-Lite leads 57.0 to 37.1.
- The biggest single-benchmark swing is WeirdML: 35.2% for Gemini 2.5 Flash-Lite and 3.2% for Mixtral 8x22B.
- Gemini 2.5 Flash-Lite is cheaper at $0.10 / $0.40 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- Gemini 2.5 Flash-Lite accepts more context: 1.05M tokens versus 64K.
- Mixtral 8x22B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 2.5 Flash-Lite | Mixtral 8x22B |
|---|---|---|
| Provider | Google | Mistral AI |
| Noometry Index | 36.4 | 26.7 |
| Rank | 208 | 330 |
| Context | 1.05M | 64K |
| Input $/M | $0.10 | $2 |
| Output $/M | $0.40 | $6 |
| Weights | Proprietary | Open |

## Coding

- Gemini 2.5 Flash-Lite: 38.0 (#167)
- Mixtral 8x22B: 23.8 (#324)

| Benchmark | Gemini 2.5 Flash-Lite | Mixtral 8x22B |
|---|---|---|
| WeirdML | 35.2% | 3.2% |
| LMArena Coding | 1373 | 1166 |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| ALE-Bench | 325.9 | — |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |

## Agentic & Tool Use

- Gemini 2.5 Flash-Lite: 27.8 (#89)
- Mixtral 8x22B: 22.8 (#119)

| Benchmark | Gemini 2.5 Flash-Lite | Mixtral 8x22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 36.9% | — |
| Cybench | — | 7.5% |

## Reasoning

- Gemini 2.5 Flash-Lite: 21.5 (#196)
- Mixtral 8x22B: 19.1 (#246)

| Benchmark | Gemini 2.5 Flash-Lite | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1377 | 1150 |
| DTBench | 62.8% | 55.1% |
| Epoch Capabilities Index | 133.93 | 122 |
| Kagi LLM Benchmark | 40.5% | — |
| LMCA | 18.1% | — |
| ForecastBench | — | 56.3 |

## Math

- Gemini 2.5 Flash-Lite: 35.5 (#144)
- Mixtral 8x22B: 21.2 (#271)

| Benchmark | Gemini 2.5 Flash-Lite | Mixtral 8x22B |
|---|---|---|
| Omni-MATH | 48% | 16.3% |
| LMArena Math | 1373 | 1184 |
| MATH Level 5 | — | 24.2% |

## Knowledge

- Gemini 2.5 Flash-Lite: 32.1 (#206)
- Mixtral 8x22B: 15.1 (#288)

| Benchmark | Gemini 2.5 Flash-Lite | Mixtral 8x22B |
|---|---|---|
| MMLU-Pro | 53.7% | 46% |
| GPQA (HELM) | 30.9% | 33.4% |
| LMArena Expert | 1373 | 1113 |
| GPQA Diamond | — | 34.1% |
| Vectara Hallucination Rate | 3.3% | — |
| MMLU | — | 77.8% |

## Multimodal

- Gemini 2.5 Flash-Lite: 28.6 (#109)
- Mixtral 8x22B: —

| Benchmark | Gemini 2.5 Flash-Lite | Mixtral 8x22B |
|---|---|---|
| LMArena Vision | 1198 | — |
| VPCT | 30% | — |

## Multilingual

- Gemini 2.5 Flash-Lite: 49.5 (#129)
- Mixtral 8x22B: 32.9 (#250)

| Benchmark | Gemini 2.5 Flash-Lite | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1369 | 1128 |
| LMArena Chinese | 1404 | 1116 |
| LMArena French | 1388 | 1165 |
| LMArena German | 1390 | 1141 |
| LMArena Japanese | 1359 | 1037 |
| LMArena Korean | 1358 | 1056 |
| LMArena Russian | 1373 | 1158 |
| LMArena Spanish | 1396 | 1150 |

## Instruction Following

- Gemini 2.5 Flash-Lite: 70.2 (#163)
- Mixtral 8x22B: 57.9 (#261)

| Benchmark | Gemini 2.5 Flash-Lite | Mixtral 8x22B |
|---|---|---|
| IFEval | 81% | 72.4% |
| LMArena Instruction Following | 1366 | 1147 |

## Long Context

- Gemini 2.5 Flash-Lite: 33.3 (#257)
- Mixtral 8x22B: 34.6 (#242)

| Benchmark | Gemini 2.5 Flash-Lite | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1373 | 1144 |
| Fiction.LiveBench | 47.2% | — |

## Writing & Preference

- Gemini 2.5 Flash-Lite: 57.0 (#130)
- Mixtral 8x22B: 37.1 (#257)

| Benchmark | Gemini 2.5 Flash-Lite | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1379 | 1162 |
| LMArena Creative Writing | 1366 | 1141 |
| WildBench | 81.8% | 71.1% |
| LMArena Multi-Turn | 1367 | 1130 |

## FAQ

### Is Gemini 2.5 Flash-Lite better than Mixtral 8x22B?

Gemini 2.5 Flash-Lite is the stronger model overall, scoring 36.4 to 26.7 on the Noometry Index.

### Which is cheaper, Gemini 2.5 Flash-Lite or Mixtral 8x22B?

Gemini 2.5 Flash-Lite is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Mixtral 8x22B lists at $2 and $6.

### Is Gemini 2.5 Flash-Lite or Mixtral 8x22B better for coding?

Gemini 2.5 Flash-Lite scores higher on coding benchmarks: 38.0 versus 23.8 in the Noometry coding category.

### Which has the bigger context window?

Gemini 2.5 Flash-Lite does, with 1.05M tokens against 64K.

### How many benchmarks do Gemini 2.5 Flash-Lite and Mixtral 8x22B share?

25 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and Mixtral 8x22B has 34.