# Qwen3 235B-A22B vs Yi-34B

> Qwen3 235B-A22B is the stronger model overall, scoring 43.2 to 27.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen3-235b-a22b-vs-yi-34b
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. Qwen3 235B-A22B scores higher in 7 categories and Yi-34B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 235B-A22B leads 49.5 to 7.5.
- The biggest single-benchmark swing is GPQA Diamond: 80.1% for Qwen3 235B-A22B and 14.7% for Yi-34B.

## Snapshot

| | Qwen3 235B-A22B | Yi-34B |
|---|---|---|
| Provider | Alibaba (Qwen) | 01.AI |
| Noometry Index | 43.2 | 27.4 |
| Rank | 83 | 325 |
| Context | 131K | — |
| Input $/M | $0.70 | — |
| Output $/M | $2.80 | — |
| Weights | Open | Open |

## Coding

- Qwen3 235B-A22B: 43.8 (#72)
- Yi-34B: 31.8 (#269)

| Benchmark | Qwen3 235B-A22B | Yi-34B |
|---|---|---|
| LMArena Coding | 1445 | 1112 |
| Aider Polyglot | 59.6% | — |
| SciCode | 42.4% | — |
| WeirdML | 41% | — |

## Agentic & Tool Use

- Qwen3 235B-A22B: 33.7 (#48)
- Yi-34B: —

| Benchmark | Qwen3 235B-A22B | Yi-34B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 52.1% | — |
| Vending-Bench 2 | -11.34 | — |

## Reasoning

- Qwen3 235B-A22B: 15.8 (#302)
- Yi-34B: 20.3 (#222)

| Benchmark | Qwen3 235B-A22B | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1433 | 1104 |
| Epoch Capabilities Index | 143.87 | 117.28 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 31% | — |
| Kagi LLM Benchmark | 69.4% | — |
| ARC-AGI-1 | 11% | — |
| CritPt | 0% | — |
| Chess Puzzles | 12% | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 80.3% | — |
| LMCA | 29.3% | — |
| BIG-Bench Hard | — | 71.7% |
| ForecastBench | 59.7 | — |

## Math

- Qwen3 235B-A22B: 48.5 (#51)
- Yi-34B: 19.8 (#277)

| Benchmark | Qwen3 235B-A22B | Yi-34B |
|---|---|---|
| LMArena Math | 1431 | 1114 |
| MATH Level 5 | 68.9% | 5.1% |
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| Omni-MATH | 71.8% | — |
| FrontierMath (Feb 2025 set) | 8.5% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
| GSM8K | — | 76% |

## Knowledge

- Qwen3 235B-A22B: 49.5 (#67)
- Yi-34B: 7.5 (#304)

| Benchmark | Qwen3 235B-A22B | Yi-34B |
|---|---|---|
| GPQA Diamond | 80.1% | 14.7% |
| LMArena Expert | 1460 | 1061 |
| SimpleQA Verified | 40.4% | — |
| MMLU-Pro | 84.4% | — |
| Confabulations | 15.6% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 72.7% | — |
| MMLU | — | 76.3% |

## Multilingual

- Qwen3 235B-A22B: 52.5 (#84)
- Yi-34B: 29.9 (#259)

| Benchmark | Qwen3 235B-A22B | Yi-34B |
|---|---|---|
| LMArena Non-English | 1410 | 1079 |
| LMArena Chinese | 1481 | 1175 |
| LMArena French | 1445 | 1080 |
| LMArena German | 1432 | 1042 |
| LMArena Japanese | 1400 | 993 |
| LMArena Korean | 1391 | 959 |
| LMArena Russian | 1411 | 1050 |
| LMArena Spanish | 1429 | 1070 |

## Instruction Following

- Qwen3 235B-A22B: 72.8 (#132)
- Yi-34B: 56.4 (#269)

| Benchmark | Qwen3 235B-A22B | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1408 | 1091 |
| IFEval | 83.5% | — |

## Long Context

- Qwen3 235B-A22B: 46.1 (#25)
- Yi-34B: 33.2 (#259)

| Benchmark | Qwen3 235B-A22B | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1426 | 1094 |
| Fiction.LiveBench | 75% | — |

## Writing & Preference

- Qwen3 235B-A22B: 59.8 (#103)
- Yi-34B: 34.3 (#268)

| Benchmark | Qwen3 235B-A22B | Yi-34B |
|---|---|---|
| LMArena Text | 1419 | 1129 |
| LMArena Creative Writing | 1384 | 1108 |
| LMArena Multi-Turn | 1432 | 1113 |
| Short-Story Creative Writing | 83% | — |
| EQ-Bench Creative Writing | 1366 | — |
| WildBench | 86.6% | — |

## FAQ

### Is Qwen3 235B-A22B better than Yi-34B?

Qwen3 235B-A22B is the stronger model overall, scoring 43.2 to 27.4 on the Noometry Index.

### Is Qwen3 235B-A22B or Yi-34B better for coding?

Qwen3 235B-A22B scores higher on coding benchmarks: 43.8 versus 31.8 in the Noometry coding category.

### How many benchmarks do Qwen3 235B-A22B and Yi-34B share?

20 benchmarks have published results for both models. Qwen3 235B-A22B has 49 scored results on Noometry and Yi-34B has 23.