Model comparison
Qwen-14B vs Yi-1.5-34B
Qwen-14B and Yi-1.5-34B score almost the same on the Noometry Index (31.4 vs 30.6), so choose on price, context window or the category you care about most.
Last verified . 10 shared benchmarks.
Alibaba (Qwen)Summary
- They share 10 benchmarks with published results for both. Qwen-14B scores higher in 1 category and Yi-1.5-34B in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Yi-1.5-34B leads 37.4 to 27.6.
Side by side
| Qwen-14B | Yi-1.5-34B | |
|---|---|---|
| Provider | Alibaba (Qwen) | 01.AI |
| Noometry Index | 31.4 | 30.6 |
| Released | 2023-09-24 | 2024-05-13 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 18 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Yi-1.5-34B leads
Qwen-14B: 31.2 (#288), Yi-1.5-34B: 32.4 (#272)
| Benchmark | Qwen-14B | Yi-1.5-34B |
|---|---|---|
| LMArena Coding | 1071 | 1169 |
| BigCodeBench Instruct | — | 33.9% |
| BigCodeBench Complete | — | 43.8% |
Reasoning Yi-1.5-34B leads
Qwen-14B: 19.6 (#257), Yi-1.5-34B: 22.5 (#191)
| Benchmark | Qwen-14B | Yi-1.5-34B |
|---|---|---|
| LMArena Hard Prompts | 1027 | 1160 |
| BIG-Bench Hard | 55% | — |
| Epoch Capabilities Index | 113.03 | — |
| LAMBADA | 71.1% | — |
| PIQA | 79.9% | — |
Math Qwen-14B leads
Qwen-14B: 31.2 (#227), Yi-1.5-34B: 27.5 (#249)
| Benchmark | Qwen-14B | Yi-1.5-34B |
|---|---|---|
| LMArena Math | 1068 | 1182 |
| MATH Level 5 | — | 25.5% |
| GSM8K | 61.3% | — |
Knowledge Not comparable
Qwen-14B: —, Yi-1.5-34B: 14.8 (#295)
| Benchmark | Qwen-14B | Yi-1.5-34B |
|---|---|---|
| GPQA Diamond | — | 32% |
| LMArena Expert | — | 1144 |
| ARC (AI2) Challenge | 84.4% | — |
| BoolQ | 86.2% | — |
| MMLU | 66.3% | — |
Multilingual Yi-1.5-34B leads
Qwen-14B: 27.5 (#275), Yi-1.5-34B: 32.3 (#256)
| Benchmark | Qwen-14B | Yi-1.5-34B |
|---|---|---|
| LMArena Non-English | 1041 | 1121 |
| LMArena Chinese | 1077 | 1213 |
| LMArena French | — | 1156 |
| LMArena German | — | 1111 |
| LMArena Japanese | — | 1021 |
| LMArena Korean | — | 1005 |
| LMArena Russian | — | 1091 |
| LMArena Spanish | — | 1121 |
Instruction Following Yi-1.5-34B leads
Qwen-14B: 52.4 (#289), Yi-1.5-34B: 59.2 (#257)
| Benchmark | Qwen-14B | Yi-1.5-34B |
|---|---|---|
| LMArena Instruction Following | 1031 | 1139 |
Long Context Yi-1.5-34B leads
Qwen-14B: 31.3 (#280), Yi-1.5-34B: 34.6 (#248)
| Benchmark | Qwen-14B | Yi-1.5-34B |
|---|---|---|
| LMArena Longer Query | 1028 | 1143 |
Writing & Preference Yi-1.5-34B leads
Qwen-14B: 27.6 (#299), Yi-1.5-34B: 37.4 (#257)
| Benchmark | Qwen-14B | Yi-1.5-34B |
|---|---|---|
| LMArena Text | 1051 | 1173 |
| LMArena Creative Writing | 1028 | 1135 |
| LMArena Multi-Turn | 1022 | 1153 |
Frequently asked questions
Is Qwen-14B better than Yi-1.5-34B?
Qwen-14B and Yi-1.5-34B score almost the same on the Noometry Index (31.4 vs 30.6), so choose on price, context window or the category you care about most.
Is Qwen-14B or Yi-1.5-34B better for coding?
Yi-1.5-34B scores higher on coding benchmarks: 32.4 versus 31.2 in the Noometry coding category.
How many benchmarks do Qwen-14B and Yi-1.5-34B share?
10 benchmarks have published results for both models. Qwen-14B has 18 scored results on Noometry and Yi-1.5-34B has 21.