Model comparison
Qwen2.5-Coder-32B vs Yi-1.5-34B
Qwen2.5-Coder-32B is the stronger model overall, scoring 33.4 to 30.6 on the Noometry Index.
Last verified . 14 shared benchmarks.
Alibaba (Qwen)Summary
- They share 14 benchmarks with published results for both. Qwen2.5-Coder-32B scores higher in 6 categories and Yi-1.5-34B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen2.5-Coder-32B leads 33.4 to 14.8.
- The biggest single-benchmark swing is BigCodeBench Instruct: 49% for Qwen2.5-Coder-32B and 33.9% for Yi-1.5-34B.
Side by side
| Qwen2.5-Coder-32B | Yi-1.5-34B | |
|---|---|---|
| Provider | Alibaba (Qwen) | 01.AI |
| Noometry Index | 33.4 | 30.6 |
| Released | 2024-09-18 | 2024-05-13 |
| Weights | Open | Open |
| Context window | 33K | — |
| Max output | 29K | — |
| Input $ / M tokens | $0.66 | — |
| Output $ / M tokens | $1 | — |
| Results tracked | 31 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Yi-1.5-34B leads
Qwen2.5-Coder-32B: 22.6 (#333), Yi-1.5-34B: 32.4 (#272)
| Benchmark | Qwen2.5-Coder-32B | Yi-1.5-34B |
|---|---|---|
| BigCodeBench Instruct | 49% | 33.9% |
| LMArena Coding | 1276 | 1169 |
| BigCodeBench Complete | 58% | 43.8% |
| SWE-bench Verified (bash only) | 9% | — |
| Aider Polyglot | 16.4% | — |
| LiveBench Coding | 56.9% | — |
| HumanEval+ | 87.2% | — |
| MBPP+ | 77% | — |
Reasoning Yi-1.5-34B leads
Qwen2.5-Coder-32B: 21.2 (#225), Yi-1.5-34B: 22.5 (#191)
| Benchmark | Qwen2.5-Coder-32B | Yi-1.5-34B |
|---|---|---|
| LMArena Hard Prompts | 1251 | 1160 |
| LiveBench Reasoning | 42.1% | — |
| LiveBench Data Analysis | 49.9% | — |
| Epoch Capabilities Index | 119.49 | — |
| HellaSwag | 83% | — |
| LiveBench | 46.2% | — |
| WinoGrande | 80.8% | — |
Math Qwen2.5-Coder-32B leads
Qwen2.5-Coder-32B: 33.3 (#204), Yi-1.5-34B: 27.5 (#249)
| Benchmark | Qwen2.5-Coder-32B | Yi-1.5-34B |
|---|---|---|
| LMArena Math | 1251 | 1182 |
| LiveBench Math | 46.6% | — |
| MATH Level 5 | — | 25.5% |
| GSM8K | 93% | — |
Knowledge Qwen2.5-Coder-32B leads
Qwen2.5-Coder-32B: 33.4 (#203), Yi-1.5-34B: 14.8 (#295)
| Benchmark | Qwen2.5-Coder-32B | Yi-1.5-34B |
|---|---|---|
| LMArena Expert | 1221 | 1144 |
| GPQA Diamond | — | 32% |
| ARC (AI2) Challenge | 70.5% | — |
| MMLU | 79.1% | — |
Multilingual Qwen2.5-Coder-32B leads
Qwen2.5-Coder-32B: 37.8 (#235), Yi-1.5-34B: 32.3 (#256)
| Benchmark | Qwen2.5-Coder-32B | Yi-1.5-34B |
|---|---|---|
| LMArena Non-English | 1205 | 1121 |
| LMArena Chinese | 1222 | 1213 |
| LMArena Russian | 1228 | 1091 |
| LMArena French | — | 1156 |
| LMArena German | — | 1111 |
| LMArena Japanese | — | 1021 |
| LMArena Korean | — | 1005 |
| LMArena Spanish | — | 1121 |
Instruction Following Qwen2.5-Coder-32B leads
Qwen2.5-Coder-32B: 61.4 (#245), Yi-1.5-34B: 59.2 (#257)
| Benchmark | Qwen2.5-Coder-32B | Yi-1.5-34B |
|---|---|---|
| LMArena Instruction Following | 1223 | 1139 |
| LiveBench Instruction Following | 58.7% | — |
Long Context Qwen2.5-Coder-32B leads
Qwen2.5-Coder-32B: 38.0 (#208), Yi-1.5-34B: 34.6 (#248)
| Benchmark | Qwen2.5-Coder-32B | Yi-1.5-34B |
|---|---|---|
| LMArena Longer Query | 1251 | 1143 |
Writing & Preference Qwen2.5-Coder-32B leads
Qwen2.5-Coder-32B: 41.6 (#240), Yi-1.5-34B: 37.4 (#257)
| Benchmark | Qwen2.5-Coder-32B | Yi-1.5-34B |
|---|---|---|
| LMArena Text | 1230 | 1173 |
| LMArena Creative Writing | 1174 | 1135 |
| LMArena Multi-Turn | 1222 | 1153 |
| LiveBench Language | 23.3% | — |
Frequently asked questions
Is Qwen2.5-Coder-32B better than Yi-1.5-34B?
Qwen2.5-Coder-32B is the stronger model overall, scoring 33.4 to 30.6 on the Noometry Index.
Is Qwen2.5-Coder-32B or Yi-1.5-34B better for coding?
Yi-1.5-34B scores higher on coding benchmarks: 32.4 versus 22.6 in the Noometry coding category.
How many benchmarks do Qwen2.5-Coder-32B and Yi-1.5-34B share?
14 benchmarks have published results for both models. Qwen2.5-Coder-32B has 31 scored results on Noometry and Yi-1.5-34B has 21.