# Qwen3 32B vs Yi-1.5-34B

> Qwen3 32B is the stronger model overall, scoring 39.2 to 30.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen3-32b-vs-yi-1-5-34b
- Last updated: 2026-10-12
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. Qwen3 32B scores higher in 7 categories and Yi-1.5-34B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 32B leads 40.0 to 14.8.
- The biggest single-benchmark swing is GPQA Diamond: 65.7% for Qwen3 32B and 32% for Yi-1.5-34B.

## Snapshot

| | Qwen3 32B | Yi-1.5-34B |
|---|---|---|
| Provider | Alibaba (Qwen) | 01.AI |
| Noometry Index | 39.2 | 30.6 |
| Rank | 172 | 289 |
| Context | 131K | — |
| Input $/M | $0.70 | — |
| Output $/M | $2.80 | — |
| Weights | Open | Open |

## Coding

- Qwen3 32B: 37.7 (#190)
- Yi-1.5-34B: 32.4 (#272)

| Benchmark | Qwen3 32B | Yi-1.5-34B |
|---|---|---|
| LMArena Coding | 1358 | 1169 |
| Aider Polyglot | 40% | — |
| SciCode | 35.4% | — |
| BigCodeBench Instruct | — | 33.9% |
| BigCodeBench Complete | — | 43.8% |

## Agentic & Tool Use

- Qwen3 32B: 32.6 (#62)
- Yi-1.5-34B: —

| Benchmark | Qwen3 32B | Yi-1.5-34B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 48.7% | — |

## Reasoning

- Qwen3 32B: 20.2 (#241)
- Yi-1.5-34B: 22.5 (#191)

| Benchmark | Qwen3 32B | Yi-1.5-34B |
|---|---|---|
| LMArena Hard Prompts | 1334 | 1160 |
| Kagi LLM Benchmark | 54.9% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | 5% | — |
| DTBench | 67.5% | — |
| LMCA | 17.3% | — |
| Epoch Capabilities Index | 138.51 | — |

## Math

- Qwen3 32B: 39.7 (#99)
- Yi-1.5-34B: 27.5 (#249)

| Benchmark | Qwen3 32B | Yi-1.5-34B |
|---|---|---|
| LMArena Math | 1399 | 1182 |
| OTIS Mock AIME 2024-2025 | 66.9% | — |
| MATH Level 5 | — | 25.5% |

## Knowledge

- Qwen3 32B: 40.0 (#125)
- Yi-1.5-34B: 14.8 (#295)

| Benchmark | Qwen3 32B | Yi-1.5-34B |
|---|---|---|
| GPQA Diamond | 65.7% | 32% |
| LMArena Expert | 1362 | 1144 |
| Vectara Hallucination Rate | 5.9% | — |

## Multilingual

- Qwen3 32B: 45.6 (#167)
- Yi-1.5-34B: 32.3 (#256)

| Benchmark | Qwen3 32B | Yi-1.5-34B |
|---|---|---|
| LMArena Non-English | 1317 | 1121 |
| LMArena Chinese | 1357 | 1213 |
| LMArena German | 1341 | 1111 |
| LMArena Russian | 1311 | 1091 |
| LMArena French | — | 1156 |
| LMArena Japanese | — | 1021 |
| LMArena Korean | — | 1005 |
| LMArena Spanish | — | 1121 |

## Instruction Following

- Qwen3 32B: 68.9 (#179)
- Yi-1.5-34B: 59.2 (#257)

| Benchmark | Qwen3 32B | Yi-1.5-34B |
|---|---|---|
| LMArena Instruction Following | 1305 | 1139 |

## Long Context

- Qwen3 32B: 43.8 (#87)
- Yi-1.5-34B: 34.6 (#248)

| Benchmark | Qwen3 32B | Yi-1.5-34B |
|---|---|---|
| LMArena Longer Query | 1327 | 1143 |
| Fiction.LiveBench | 74.2% | — |

## Writing & Preference

- Qwen3 32B: 52.9 (#163)
- Yi-1.5-34B: 37.4 (#257)

| Benchmark | Qwen3 32B | Yi-1.5-34B |
|---|---|---|
| LMArena Text | 1340 | 1173 |
| LMArena Creative Writing | 1297 | 1135 |
| LMArena Multi-Turn | 1331 | 1153 |

## FAQ

### Is Qwen3 32B better than Yi-1.5-34B?

Qwen3 32B is the stronger model overall, scoring 39.2 to 30.6 on the Noometry Index.

### Is Qwen3 32B or Yi-1.5-34B better for coding?

Qwen3 32B scores higher on coding benchmarks: 37.7 versus 32.4 in the Noometry coding category.

### How many benchmarks do Qwen3 32B and Yi-1.5-34B share?

14 benchmarks have published results for both models. Qwen3 32B has 26 scored results on Noometry and Yi-1.5-34B has 21.