# Mixtral 8x22B vs Yi-Lightning

> Yi-Lightning is the stronger model overall, scoring 36.5 to 26.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mixtral-8x22b-vs-yi-lightning
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Mixtral 8x22B scores higher in 0 categories and Yi-Lightning in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Yi-Lightning leads 34.8 to 15.1.
- Mixtral 8x22B has downloadable open weights; the other is API-only.

## Snapshot

| | Mixtral 8x22B | Yi-Lightning |
|---|---|---|
| Provider | Mistral AI | 01.AI |
| Noometry Index | 26.7 | 36.5 |
| Rank | 330 | 206 |
| Context | 64K | — |
| Input $/M | $2 | — |
| Output $/M | $6 | — |
| Weights | Open | Proprietary |

## Coding

- Mixtral 8x22B: 23.8 (#324)
- Yi-Lightning: 27.0 (#315)

| Benchmark | Mixtral 8x22B | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1166 | 1313 |
| Aider Polyglot | — | 12.9% |
| WeirdML | 3.2% | — |
| BigCodeBench Instruct | 40.6% | — |
| BigCodeBench Complete | 50.2% | — |
| HumanEval+ | 72% | — |
| MBPP+ | 64.3% | — |

## Agentic & Tool Use

- Mixtral 8x22B: 22.8 (#119)
- Yi-Lightning: —

| Benchmark | Mixtral 8x22B | Yi-Lightning |
|---|---|---|
| Cybench | 7.5% | — |

## Reasoning

- Mixtral 8x22B: 19.1 (#246)
- Yi-Lightning: 24.9 (#137)

| Benchmark | Mixtral 8x22B | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1150 | 1302 |
| DTBench | 55.1% | — |
| Epoch Capabilities Index | 122 | — |
| ForecastBench | 56.3 | — |

## Math

- Mixtral 8x22B: 21.2 (#271)
- Yi-Lightning: 33.5 (#173)

| Benchmark | Mixtral 8x22B | Yi-Lightning |
|---|---|---|
| LMArena Math | 1184 | 1300 |
| Omni-MATH | 16.3% | — |
| MATH Level 5 | 24.2% | — |

## Knowledge

- Mixtral 8x22B: 15.1 (#288)
- Yi-Lightning: 34.8 (#182)

| Benchmark | Mixtral 8x22B | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1113 | 1286 |
| GPQA Diamond | 34.1% | — |
| MMLU-Pro | 46% | — |
| GPQA (HELM) | 33.4% | — |
| MMLU | 77.8% | — |

## Multilingual

- Mixtral 8x22B: 32.9 (#250)
- Yi-Lightning: 42.4 (#191)

| Benchmark | Mixtral 8x22B | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1128 | 1269 |
| LMArena Chinese | 1116 | 1320 |
| LMArena French | 1165 | 1304 |
| LMArena German | 1141 | 1267 |
| LMArena Japanese | 1037 | 1228 |
| LMArena Korean | 1056 | 1192 |
| LMArena Russian | 1158 | 1255 |
| LMArena Spanish | 1150 | 1315 |

## Instruction Following

- Mixtral 8x22B: 57.9 (#261)
- Yi-Lightning: 67.6 (#191)

| Benchmark | Mixtral 8x22B | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1147 | 1278 |
| IFEval | 72.4% | — |

## Long Context

- Mixtral 8x22B: 34.6 (#242)
- Yi-Lightning: 39.4 (#176)

| Benchmark | Mixtral 8x22B | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1144 | 1297 |

## Writing & Preference

- Mixtral 8x22B: 37.1 (#257)
- Yi-Lightning: 50.4 (#178)

| Benchmark | Mixtral 8x22B | Yi-Lightning |
|---|---|---|
| LMArena Text | 1162 | 1302 |
| LMArena Creative Writing | 1141 | 1280 |
| LMArena Multi-Turn | 1130 | 1311 |
| WildBench | 71.1% | — |

## FAQ

### Is Mixtral 8x22B better than Yi-Lightning?

Yi-Lightning is the stronger model overall, scoring 36.5 to 26.7 on the Noometry Index.

### Is Mixtral 8x22B or Yi-Lightning better for coding?

Yi-Lightning scores higher on coding benchmarks: 27.0 versus 23.8 in the Noometry coding category.

### How many benchmarks do Mixtral 8x22B and Yi-Lightning share?

17 benchmarks have published results for both models. Mixtral 8x22B has 34 scored results on Noometry and Yi-Lightning has 18.