# Qwen3-Next 80B-A3B Instruct vs Yi-34B

> Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 43.0 to 27.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen3-next-80b-a3b-instruct-vs-yi-34b
- Last updated: 2026-10-12
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Qwen3-Next 80B-A3B Instruct scores higher in 8 categories and Yi-34B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3-Next 80B-A3B Instruct leads 41.8 to 7.5.

## Snapshot

| | Qwen3-Next 80B-A3B Instruct | Yi-34B |
|---|---|---|
| Provider | Alibaba (Qwen) | 01.AI |
| Noometry Index | 43.0 | 27.8 |
| Rank | 102 | 329 |
| Context | 131K | — |
| Input $/M | $0.50 | — |
| Output $/M | $2 | — |
| Weights | Open | Open |

## Coding

- Qwen3-Next 80B-A3B Instruct: 42.5 (#98)
- Yi-34B: 32.3 (#274)

| Benchmark | Qwen3-Next 80B-A3B Instruct | Yi-34B |
|---|---|---|
| LMArena Coding | 1440 | 1112 |

## Reasoning

- Qwen3-Next 80B-A3B Instruct: 31.1 (#81)
- Yi-34B: 21.2 (#226)

| Benchmark | Qwen3-Next 80B-A3B Instruct | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1428 | 1104 |
| Kagi LLM Benchmark | 66.7% | — |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | — | 117.39 |

## Math

- Qwen3-Next 80B-A3B Instruct: 38.8 (#126)
- Yi-34B: 21.6 (#282)

| Benchmark | Qwen3-Next 80B-A3B Instruct | Yi-34B |
|---|---|---|
| LMArena Math | 1440 | 1114 |
| Omni-MATH | 46.7% | — |
| MATH Level 5 | — | 5.1% |
| GSM8K | — | 76% |

## Knowledge

- Qwen3-Next 80B-A3B Instruct: 41.8 (#106)
- Yi-34B: 7.5 (#309)

| Benchmark | Qwen3-Next 80B-A3B Instruct | Yi-34B |
|---|---|---|
| LMArena Expert | 1417 | 1061 |
| GPQA Diamond | — | 14.7% |
| MMLU-Pro | 78.6% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 63% | — |
| MMLU | — | 76.3% |

## Multilingual

- Qwen3-Next 80B-A3B Instruct: 52.1 (#93)
- Yi-34B: 29.7 (#264)

| Benchmark | Qwen3-Next 80B-A3B Instruct | Yi-34B |
|---|---|---|
| LMArena Non-English | 1407 | 1079 |
| LMArena Chinese | 1460 | 1176 |
| LMArena French | 1413 | 1081 |
| LMArena German | 1417 | 1042 |
| LMArena Japanese | 1395 | 993 |
| LMArena Korean | 1364 | 959 |
| LMArena Russian | 1404 | 1050 |
| LMArena Spanish | 1435 | 1070 |

## Instruction Following

- Qwen3-Next 80B-A3B Instruct: 70.8 (#159)
- Yi-34B: 56.2 (#274)

| Benchmark | Qwen3-Next 80B-A3B Instruct | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1389 | 1091 |
| IFEval | 81% | — |

## Long Context

- Qwen3-Next 80B-A3B Instruct: 37.0 (#223)
- Yi-34B: 33.2 (#264)

| Benchmark | Qwen3-Next 80B-A3B Instruct | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1403 | 1094 |
| Fiction.LiveBench | 55.6% | — |

## Writing & Preference

- Qwen3-Next 80B-A3B Instruct: 58.0 (#121)
- Yi-34B: 34.1 (#273)

| Benchmark | Qwen3-Next 80B-A3B Instruct | Yi-34B |
|---|---|---|
| LMArena Text | 1417 | 1129 |
| LMArena Creative Writing | 1334 | 1108 |
| LMArena Multi-Turn | 1416 | 1113 |
| WildBench | 80.7% | — |

## FAQ

### Is Qwen3-Next 80B-A3B Instruct better than Yi-34B?

Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 43.0 to 27.8 on the Noometry Index.

### Is Qwen3-Next 80B-A3B Instruct or Yi-34B better for coding?

Qwen3-Next 80B-A3B Instruct scores higher on coding benchmarks: 42.5 versus 32.3 in the Noometry coding category.

### How many benchmarks do Qwen3-Next 80B-A3B Instruct and Yi-34B share?

17 benchmarks have published results for both models. Qwen3-Next 80B-A3B Instruct has 25 scored results on Noometry and Yi-34B has 23.