Model comparison
Qwen3 32B vs Yi-34B
Qwen3 32B is the stronger model overall, scoring 38.8 to 27.4 on the Noometry Index.
Last verified . 15 shared benchmarks.
Alibaba (Qwen)Summary
- They share 15 benchmarks with published results for both. Qwen3 32B scores higher in 7 categories and Yi-34B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 32B leads 40.0 to 7.5.
- The biggest single-benchmark swing is GPQA Diamond: 65.7% for Qwen3 32B and 14.7% for Yi-34B.
Side by side
| Qwen3 32B | Yi-34B | |
|---|---|---|
| Provider | Alibaba (Qwen) | 01.AI |
| Noometry Index | 38.8 | 27.4 |
| Released | 2025-04 | 2023-11-02 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.70 | — |
| Output $ / M tokens | $2.80 | — |
| Results tracked | 26 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 32B leads
Qwen3 32B: 37.3 (#184), Yi-34B: 31.8 (#269)
| Benchmark | Qwen3 32B | Yi-34B |
|---|---|---|
| LMArena Coding | 1358 | 1112 |
| Aider Polyglot | 40% | — |
| SciCode | 35.4% | — |
Agentic & Tool Use Not comparable
Qwen3 32B: 32.3 (#58), Yi-34B: —
| Benchmark | Qwen3 32B | Yi-34B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 48.7% | — |
Reasoning Too close to call
Qwen3 32B: 19.6 (#233), Yi-34B: 20.3 (#222)
| Benchmark | Qwen3 32B | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1335 | 1104 |
| Epoch Capabilities Index | 138.51 | 117.28 |
| Kagi LLM Benchmark | 54.9% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | 5% | — |
| DTBench | 67.5% | — |
| LMCA | 17.3% | — |
| BIG-Bench Hard | — | 71.7% |
Math Qwen3 32B leads
Qwen3 32B: 37.9 (#89), Yi-34B: 19.8 (#277)
| Benchmark | Qwen3 32B | Yi-34B |
|---|---|---|
| LMArena Math | 1399 | 1114 |
| OTIS Mock AIME 2024-2025 | 66.9% | — |
| MATH Level 5 | — | 5.1% |
| GSM8K | — | 76% |
Knowledge Qwen3 32B leads
Qwen3 32B: 40.0 (#112), Yi-34B: 7.5 (#304)
| Benchmark | Qwen3 32B | Yi-34B |
|---|---|---|
| GPQA Diamond | 65.7% | 14.7% |
| LMArena Expert | 1362 | 1061 |
| Vectara Hallucination Rate | 5.9% | — |
| MMLU | — | 76.3% |
Multilingual Qwen3 32B leads
Qwen3 32B: 45.8 (#162), Yi-34B: 29.9 (#259)
| Benchmark | Qwen3 32B | Yi-34B |
|---|---|---|
| LMArena Non-English | 1317 | 1079 |
| LMArena Chinese | 1357 | 1175 |
| LMArena German | 1341 | 1042 |
| LMArena Russian | 1311 | 1050 |
| LMArena French | — | 1080 |
| LMArena Japanese | — | 993 |
| LMArena Korean | — | 959 |
| LMArena Spanish | — | 1070 |
Instruction Following Qwen3 32B leads
Qwen3 32B: 69.1 (#174), Yi-34B: 56.4 (#269)
| Benchmark | Qwen3 32B | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1305 | 1091 |
Long Context Qwen3 32B leads
Qwen3 32B: 43.7 (#83), Yi-34B: 33.2 (#259)
| Benchmark | Qwen3 32B | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1327 | 1094 |
| Fiction.LiveBench | 74.2% | — |
Writing & Preference Qwen3 32B leads
Qwen3 32B: 53.1 (#158), Yi-34B: 34.3 (#268)
| Benchmark | Qwen3 32B | Yi-34B |
|---|---|---|
| LMArena Text | 1340 | 1129 |
| LMArena Creative Writing | 1297 | 1108 |
| LMArena Multi-Turn | 1331 | 1113 |
Frequently asked questions
Is Qwen3 32B better than Yi-34B?
Qwen3 32B is the stronger model overall, scoring 38.8 to 27.4 on the Noometry Index.
Is Qwen3 32B or Yi-34B better for coding?
Qwen3 32B scores higher on coding benchmarks: 37.3 versus 31.8 in the Noometry coding category.
How many benchmarks do Qwen3 32B and Yi-34B share?
15 benchmarks have published results for both models. Qwen3 32B has 26 scored results on Noometry and Yi-34B has 23.