# QwQ-32B vs Yi-34B

> QwQ-32B is the stronger model overall, scoring 39.4 to 27.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwq-32b-vs-yi-34b
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. QwQ-32B 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 QwQ-32B leads 37.2 to 7.5.
- The biggest single-benchmark swing is GPQA Diamond: 65.3% for QwQ-32B and 14.7% for Yi-34B.

## Snapshot

| | QwQ-32B | Yi-34B |
|---|---|---|
| Provider | Alibaba (Qwen) | 01.AI |
| Noometry Index | 39.4 | 27.4 |
| Rank | 153 | 325 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- QwQ-32B: 34.9 (#220)
- Yi-34B: 31.8 (#269)

| Benchmark | QwQ-32B | Yi-34B |
|---|---|---|
| LMArena Coding | 1333 | 1112 |
| Aider Polyglot | 20.9% | — |
| BigCodeBench Instruct | 44.6% | — |
| LiveBench Coding | 72.2% | — |
| BigCodeBench Complete | 54.4% | — |

## Reasoning

- QwQ-32B: 22.9 (#171)
- Yi-34B: 20.3 (#222)

| Benchmark | QwQ-32B | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1326 | 1104 |
| Epoch Capabilities Index | 137.6 | 117.28 |
| Chess Puzzles | 5% | — |
| LiveBench Reasoning | 83.5% | — |
| LiveBench Data Analysis | 65% | — |
| BIG-Bench Hard | — | 71.7% |
| ForecastBench | 58.3 | — |
| LiveBench | 72% | — |

## Math

- QwQ-32B: 36.2 (#123)
- Yi-34B: 19.8 (#277)

| Benchmark | QwQ-32B | Yi-34B |
|---|---|---|
| LMArena Math | 1359 | 1114 |
| OTIS Mock AIME 2024-2025 | 59.2% | — |
| LiveBench Math | 77.8% | — |
| MATH Level 5 | — | 5.1% |
| GSM8K | — | 76% |

## Knowledge

- QwQ-32B: 37.2 (#150)
- Yi-34B: 7.5 (#304)

| Benchmark | QwQ-32B | Yi-34B |
|---|---|---|
| GPQA Diamond | 65.3% | 14.7% |
| LMArena Expert | 1323 | 1061 |
| Confabulations | 15.6% | — |
| MMLU | — | 76.3% |

## Multilingual

- QwQ-32B: 45.0 (#171)
- Yi-34B: 29.9 (#259)

| Benchmark | QwQ-32B | Yi-34B |
|---|---|---|
| LMArena Non-English | 1306 | 1079 |
| LMArena Chinese | 1378 | 1175 |
| LMArena French | 1337 | 1080 |
| LMArena German | 1313 | 1042 |
| LMArena Japanese | 1263 | 993 |
| LMArena Korean | 1278 | 959 |
| LMArena Russian | 1297 | 1050 |
| LMArena Spanish | 1353 | 1070 |

## Instruction Following

- QwQ-32B: 72.8 (#131)
- Yi-34B: 56.4 (#269)

| Benchmark | QwQ-32B | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1297 | 1091 |
| LiveBench Instruction Following | 81.8% | — |

## Long Context

- QwQ-32B: 49.0 (#11)
- Yi-34B: 33.2 (#259)

| Benchmark | QwQ-32B | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1308 | 1094 |
| Fiction.LiveBench | 83.3% | — |

## Writing & Preference

- QwQ-32B: 50.9 (#175)
- Yi-34B: 34.3 (#268)

| Benchmark | QwQ-32B | Yi-34B |
|---|---|---|
| LMArena Text | 1329 | 1129 |
| LMArena Creative Writing | 1288 | 1108 |
| LMArena Multi-Turn | 1314 | 1113 |
| Short-Story Creative Writing | 80.2% | — |
| EQ-Bench Creative Writing | 1257 | — |
| LiveBench Language | 51.4% | — |

## FAQ

### Is QwQ-32B better than Yi-34B?

QwQ-32B is the stronger model overall, scoring 39.4 to 27.4 on the Noometry Index.

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

QwQ-32B scores higher on coding benchmarks: 34.9 versus 31.8 in the Noometry coding category.

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

19 benchmarks have published results for both models. QwQ-32B has 36 scored results on Noometry and Yi-34B has 23.