Model comparison
Qwen1.5-72B vs Yi-34B
Qwen1.5-72B is the stronger model overall, scoring 30.8 to 27.8 on the Noometry Index.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Qwen1.5-72B scores higher in 7 categories and Yi-34B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen1.5-72B leads 33.2 to 21.6.
- The biggest single-benchmark swing is GPQA Diamond: 28.8% for Qwen1.5-72B and 14.7% for Yi-34B.
Side by side
| Qwen1.5-72B | Yi-34B | |
|---|---|---|
| Provider | Alibaba (Qwen) | 01.AI |
| Noometry Index | 30.8 | 27.8 |
| Released | 2024-02-04 | 2023-11-02 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Qwen1.5-72B: 31.9 (#277), Yi-34B: 32.3 (#274)
| Benchmark | Qwen1.5-72B | Yi-34B |
|---|---|---|
| LMArena Coding | 1165 | 1112 |
| BigCodeBench Instruct | 33.2% | — |
| BigCodeBench Complete | 40.3% | — |
| HumanEval+ | 59.1% | — |
| MBPP+ | 61.6% | — |
Reasoning Qwen1.5-72B leads
Qwen1.5-72B: 22.2 (#203), Yi-34B: 21.2 (#226)
| Benchmark | Qwen1.5-72B | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1148 | 1104 |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | — | 117.39 |
Math Qwen1.5-72B leads
Qwen1.5-72B: 33.2 (#205), Yi-34B: 21.6 (#282)
| Benchmark | Qwen1.5-72B | Yi-34B |
|---|---|---|
| LMArena Math | 1164 | 1114 |
| MATH Level 5 | — | 5.1% |
| GSM8K | — | 76% |
Knowledge Qwen1.5-72B leads
Qwen1.5-72B: 11.5 (#300), Yi-34B: 7.5 (#309)
| Benchmark | Qwen1.5-72B | Yi-34B |
|---|---|---|
| GPQA Diamond | 28.8% | 14.7% |
| LMArena Expert | 1136 | 1061 |
| MMLU | — | 76.3% |
Multilingual Qwen1.5-72B leads
Qwen1.5-72B: 33.2 (#253), Yi-34B: 29.7 (#264)
| Benchmark | Qwen1.5-72B | Yi-34B |
|---|---|---|
| LMArena Non-English | 1135 | 1079 |
| LMArena Chinese | 1186 | 1176 |
| LMArena French | 1159 | 1081 |
| LMArena German | 1084 | 1042 |
| LMArena Japanese | 1061 | 993 |
| LMArena Korean | 1050 | 959 |
| LMArena Russian | 1104 | 1050 |
| LMArena Spanish | 1110 | 1070 |
Instruction Following Qwen1.5-72B leads
Qwen1.5-72B: 59.3 (#256), Yi-34B: 56.2 (#274)
| Benchmark | Qwen1.5-72B | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1141 | 1091 |
Long Context Qwen1.5-72B leads
Qwen1.5-72B: 35.1 (#243), Yi-34B: 33.2 (#264)
| Benchmark | Qwen1.5-72B | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1157 | 1094 |
Writing & Preference Qwen1.5-72B leads
Qwen1.5-72B: 37.3 (#258), Yi-34B: 34.1 (#273)
| Benchmark | Qwen1.5-72B | Yi-34B |
|---|---|---|
| LMArena Text | 1166 | 1129 |
| LMArena Creative Writing | 1137 | 1108 |
| LMArena Multi-Turn | 1160 | 1113 |
Frequently asked questions
Is Qwen1.5-72B better than Yi-34B?
Qwen1.5-72B is the stronger model overall, scoring 30.8 to 27.8 on the Noometry Index.
Is Qwen1.5-72B or Yi-34B better for coding?
They score almost the same on coding (31.9 vs 32.3); test both on your own repository before choosing.
How many benchmarks do Qwen1.5-72B and Yi-34B share?
18 benchmarks have published results for both models. Qwen1.5-72B has 22 scored results on Noometry and Yi-34B has 23.