Model comparison
Qwen1.5-32B vs Yi-34B
Qwen1.5-32B is the stronger model overall, scoring 30.0 to 27.4 on the Noometry Index.
Last verified . 19 shared benchmarks.
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. Qwen1.5-32B scores higher in 7 categories and Yi-34B in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen1.5-32B leads 30.5 to 19.8.
- The biggest single-benchmark swing is GPQA Diamond: 30.7% for Qwen1.5-32B and 14.7% for Yi-34B.
Side by side
| Qwen1.5-32B | Yi-34B | |
|---|---|---|
| Provider | Alibaba (Qwen) | 01.AI |
| Noometry Index | 30.0 | 27.4 |
| Released | 2024-02-04 | 2023-11-02 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Qwen1.5-32B: 31.1 (#278), Yi-34B: 31.8 (#269)
| Benchmark | Qwen1.5-32B | Yi-34B |
|---|---|---|
| LMArena Coding | 1155 | 1112 |
| BigCodeBench Instruct | 32.3% | — |
| BigCodeBench Complete | 42% | — |
Reasoning Too close to call
Qwen1.5-32B: 20.9 (#210), Yi-34B: 20.3 (#222)
| Benchmark | Qwen1.5-32B | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1131 | 1104 |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | — | 117.28 |
Math Qwen1.5-32B leads
Qwen1.5-32B: 30.5 (#207), Yi-34B: 19.8 (#277)
| Benchmark | Qwen1.5-32B | Yi-34B |
|---|---|---|
| LMArena Math | 1155 | 1114 |
| MATH Level 5 | — | 5.1% |
| GSM8K | — | 76% |
Knowledge Qwen1.5-32B leads
Qwen1.5-32B: 13.5 (#291), Yi-34B: 7.5 (#304)
| Benchmark | Qwen1.5-32B | Yi-34B |
|---|---|---|
| GPQA Diamond | 30.7% | 14.7% |
| LMArena Expert | 1126 | 1061 |
| MMLU | 74.4% | 76.3% |
Multilingual Qwen1.5-32B leads
Qwen1.5-32B: 31.6 (#254), Yi-34B: 29.9 (#259)
| Benchmark | Qwen1.5-32B | Yi-34B |
|---|---|---|
| LMArena Non-English | 1106 | 1079 |
| LMArena Chinese | 1176 | 1175 |
| LMArena French | 1100 | 1080 |
| LMArena German | 1058 | 1042 |
| LMArena Japanese | 1027 | 993 |
| LMArena Korean | 1007 | 959 |
| LMArena Russian | 1073 | 1050 |
| LMArena Spanish | 1089 | 1070 |
Instruction Following Qwen1.5-32B leads
Qwen1.5-32B: 58.0 (#260), Yi-34B: 56.4 (#269)
| Benchmark | Qwen1.5-32B | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1116 | 1091 |
Long Context Qwen1.5-32B leads
Qwen1.5-32B: 34.7 (#241), Yi-34B: 33.2 (#259)
| Benchmark | Qwen1.5-32B | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1146 | 1094 |
Writing & Preference Too close to call
Qwen1.5-32B: 34.4 (#266), Yi-34B: 34.3 (#268)
| Benchmark | Qwen1.5-32B | Yi-34B |
|---|---|---|
| LMArena Text | 1137 | 1129 |
| LMArena Creative Writing | 1083 | 1108 |
| LMArena Multi-Turn | 1140 | 1113 |
Frequently asked questions
Is Qwen1.5-32B better than Yi-34B?
Qwen1.5-32B is the stronger model overall, scoring 30.0 to 27.4 on the Noometry Index.
Is Qwen1.5-32B or Yi-34B better for coding?
They score almost the same on coding (31.1 vs 31.8); test both on your own repository before choosing.
How many benchmarks do Qwen1.5-32B and Yi-34B share?
19 benchmarks have published results for both models. Qwen1.5-32B has 21 scored results on Noometry and Yi-34B has 23.