Model comparison
Qwen2-72B vs Yi-34B
Qwen2-72B is the stronger model overall, scoring 30.0 to 27.8 on the Noometry Index.
Last verified . 21 shared benchmarks.
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. Qwen2-72B scores higher in 7 categories and Yi-34B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen2-72B leads 21.2 to 7.5.
- The biggest single-benchmark swing is MATH Level 5: 39.1% for Qwen2-72B and 5.1% for Yi-34B.
Side by side
| Qwen2-72B | Yi-34B | |
|---|---|---|
| Provider | Alibaba (Qwen) | 01.AI |
| Noometry Index | 30.0 | 27.8 |
| Released | 2024-06-07 | 2023-11-02 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 26 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Yi-34B leads
Qwen2-72B: 29.1 (#310), Yi-34B: 32.3 (#274)
| Benchmark | Qwen2-72B | Yi-34B |
|---|---|---|
| LMArena Coding | 1196 | 1112 |
| WeirdML | 11.3% | — |
| BigCodeBench Instruct | 38.5% | — |
| BigCodeBench Complete | 54% | — |
Agentic & Tool Use Not comparable
Qwen2-72B: 17.0 (#146), Yi-34B: —
| Benchmark | Qwen2-72B | Yi-34B |
|---|---|---|
| TheAgentCompany | 1.1% | — |
| METR Time Horizons | 29.9% | — |
Reasoning Qwen2-72B leads
Qwen2-72B: 23.2 (#181), Yi-34B: 21.2 (#226)
| Benchmark | Qwen2-72B | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1104 |
| Epoch Capabilities Index | 125.28 | 117.39 |
| BIG-Bench Hard | — | 71.7% |
Math Qwen2-72B leads
Qwen2-72B: 30.2 (#236), Yi-34B: 21.6 (#282)
| Benchmark | Qwen2-72B | Yi-34B |
|---|---|---|
| LMArena Math | 1235 | 1114 |
| MATH Level 5 | 39.1% | 5.1% |
| GSM8K | — | 76% |
Knowledge Qwen2-72B leads
Qwen2-72B: 21.2 (#275), Yi-34B: 7.5 (#309)
| Benchmark | Qwen2-72B | Yi-34B |
|---|---|---|
| GPQA Diamond | 40.8% | 14.7% |
| LMArena Expert | 1171 | 1061 |
| MMLU | 82.4% | 76.3% |
Multilingual Qwen2-72B leads
Qwen2-72B: 35.9 (#244), Yi-34B: 29.7 (#264)
| Benchmark | Qwen2-72B | Yi-34B |
|---|---|---|
| LMArena Non-English | 1176 | 1079 |
| LMArena Chinese | 1240 | 1176 |
| LMArena French | 1170 | 1081 |
| LMArena German | 1151 | 1042 |
| LMArena Japanese | 1111 | 993 |
| LMArena Korean | 1083 | 959 |
| LMArena Russian | 1169 | 1050 |
| LMArena Spanish | 1169 | 1070 |
Instruction Following Qwen2-72B leads
Qwen2-72B: 61.7 (#241), Yi-34B: 56.2 (#274)
| Benchmark | Qwen2-72B | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1181 | 1091 |
Long Context Qwen2-72B leads
Qwen2-72B: 36.1 (#235), Yi-34B: 33.2 (#264)
| Benchmark | Qwen2-72B | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1192 | 1094 |
Writing & Preference Qwen2-72B leads
Qwen2-72B: 40.8 (#241), Yi-34B: 34.1 (#273)
| Benchmark | Qwen2-72B | Yi-34B |
|---|---|---|
| LMArena Text | 1203 | 1129 |
| LMArena Creative Writing | 1181 | 1108 |
| LMArena Multi-Turn | 1196 | 1113 |
Frequently asked questions
Is Qwen2-72B better than Yi-34B?
Qwen2-72B is the stronger model overall, scoring 30.0 to 27.8 on the Noometry Index.
Is Qwen2-72B or Yi-34B better for coding?
Yi-34B scores higher on coding benchmarks: 32.3 versus 29.1 in the Noometry coding category.
How many benchmarks do Qwen2-72B and Yi-34B share?
21 benchmarks have published results for both models. Qwen2-72B has 26 scored results on Noometry and Yi-34B has 23.