# Llama 3.2 90B vs Yi-Lightning

> Yi-Lightning is the stronger model overall, scoring 37.1 to 27.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-2-90b-vs-yi-lightning
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in math, where Yi-Lightning leads 36.2 to 11.1.
- Llama 3.2 90B has downloadable open weights; the other is API-only.

## Snapshot

| | Llama 3.2 90B | Yi-Lightning |
|---|---|---|
| Provider | Meta | 01.AI |
| Noometry Index | 27.5 | 37.1 |
| Rank | 331 | 209 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Proprietary |

## Coding

- Llama 3.2 90B: —
- Yi-Lightning: 27.4 (#320)

| Benchmark | Llama 3.2 90B | Yi-Lightning |
|---|---|---|
| Aider Polyglot | — | 12.9% |
| LMArena Coding | — | 1312 |

## Agentic & Tool Use

- Llama 3.2 90B: 30.0 (#80)
- Yi-Lightning: —

| Benchmark | Llama 3.2 90B | Yi-Lightning |
|---|---|---|
| BALROG | 27.3% | — |

## Reasoning

- Llama 3.2 90B: 21.7 (#217)
- Yi-Lightning: 25.9 (#139)

| Benchmark | Llama 3.2 90B | Yi-Lightning |
|---|---|---|
| EnigmaEval | 0.4% | — |
| LMArena Hard Prompts | — | 1302 |
| Epoch Capabilities Index | 125.5 | — |

## Math

- Llama 3.2 90B: 11.1 (#308)
- Yi-Lightning: 36.2 (#172)

| Benchmark | Llama 3.2 90B | Yi-Lightning |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.6% | — |
| LMArena Math | — | 1300 |
| MATH Level 5 | 39.4% | — |

## Knowledge

- Llama 3.2 90B: 21.7 (#274)
- Yi-Lightning: 35.4 (#185)

| Benchmark | Llama 3.2 90B | Yi-Lightning |
|---|---|---|
| GPQA Diamond | 41% | — |
| LMArena Expert | — | 1286 |
| MMLU | 80.3% | — |

## Multimodal

- Llama 3.2 90B: 25.4 (#124)
- Yi-Lightning: —

| Benchmark | Llama 3.2 90B | Yi-Lightning |
|---|---|---|
| LMArena Vision | 1000 | — |
| GeoBench | 52% | — |

## Multilingual

- Llama 3.2 90B: —
- Yi-Lightning: 42.2 (#196)

| Benchmark | Llama 3.2 90B | Yi-Lightning |
|---|---|---|
| LMArena Non-English | — | 1269 |
| LMArena Chinese | — | 1320 |
| LMArena French | — | 1305 |
| LMArena German | — | 1267 |
| LMArena Japanese | — | 1228 |
| LMArena Korean | — | 1192 |
| LMArena Russian | — | 1255 |
| LMArena Spanish | — | 1315 |

## Instruction Following

- Llama 3.2 90B: —
- Yi-Lightning: 67.4 (#196)

| Benchmark | Llama 3.2 90B | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | — | 1278 |

## Long Context

- Llama 3.2 90B: —
- Yi-Lightning: 39.4 (#181)

| Benchmark | Llama 3.2 90B | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | — | 1297 |

## Writing & Preference

- Llama 3.2 90B: —
- Yi-Lightning: 50.2 (#184)

| Benchmark | Llama 3.2 90B | Yi-Lightning |
|---|---|---|
| LMArena Text | — | 1302 |
| LMArena Creative Writing | — | 1280 |
| LMArena Multi-Turn | — | 1311 |

## FAQ

### Is Llama 3.2 90B better than Yi-Lightning?

Yi-Lightning is the stronger model overall, scoring 37.1 to 27.5 on the Noometry Index.

### How many benchmarks do Llama 3.2 90B and Yi-Lightning share?

0 benchmarks have published results for both models. Llama 3.2 90B has 9 scored results on Noometry and Yi-Lightning has 18.