Model comparison
Yi-1.5-34B vs Yi-34B
Yi-1.5-34B is the stronger model overall, scoring 30.6 to 27.8 on the Noometry Index.
Last verified . 19 shared benchmarks.
Summary
- They share 19 benchmarks with published results for both. Yi-1.5-34B scores higher in 8 categories and Yi-34B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Yi-1.5-34B leads 14.8 to 7.5.
- The biggest single-benchmark swing is MATH Level 5: 25.5% for Yi-1.5-34B and 5.1% for Yi-34B.
Side by side
| Yi-1.5-34B | Yi-34B | |
|---|---|---|
| Provider | 01.AI | 01.AI |
| Noometry Index | 30.6 | 27.8 |
| Released | 2024-05-13 | 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
Yi-1.5-34B: 32.4 (#272), Yi-34B: 32.3 (#274)
| Benchmark | Yi-1.5-34B | Yi-34B |
|---|---|---|
| LMArena Coding | 1169 | 1112 |
| BigCodeBench Instruct | 33.9% | — |
| BigCodeBench Complete | 43.8% | — |
Reasoning Yi-1.5-34B leads
Yi-1.5-34B: 22.5 (#191), Yi-34B: 21.2 (#226)
| Benchmark | Yi-1.5-34B | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1160 | 1104 |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | — | 117.39 |
Math Yi-1.5-34B leads
Yi-1.5-34B: 27.5 (#249), Yi-34B: 21.6 (#282)
| Benchmark | Yi-1.5-34B | Yi-34B |
|---|---|---|
| LMArena Math | 1182 | 1114 |
| MATH Level 5 | 25.5% | 5.1% |
| GSM8K | — | 76% |
Knowledge Yi-1.5-34B leads
Yi-1.5-34B: 14.8 (#295), Yi-34B: 7.5 (#309)
| Benchmark | Yi-1.5-34B | Yi-34B |
|---|---|---|
| GPQA Diamond | 32% | 14.7% |
| LMArena Expert | 1144 | 1061 |
| MMLU | — | 76.3% |
Multilingual Yi-1.5-34B leads
Yi-1.5-34B: 32.3 (#256), Yi-34B: 29.7 (#264)
| Benchmark | Yi-1.5-34B | Yi-34B |
|---|---|---|
| LMArena Non-English | 1121 | 1079 |
| LMArena Chinese | 1213 | 1176 |
| LMArena French | 1156 | 1081 |
| LMArena German | 1111 | 1042 |
| LMArena Japanese | 1021 | 993 |
| LMArena Korean | 1005 | 959 |
| LMArena Russian | 1091 | 1050 |
| LMArena Spanish | 1121 | 1070 |
Instruction Following Yi-1.5-34B leads
Yi-1.5-34B: 59.2 (#257), Yi-34B: 56.2 (#274)
| Benchmark | Yi-1.5-34B | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1139 | 1091 |
Long Context Yi-1.5-34B leads
Yi-1.5-34B: 34.6 (#248), Yi-34B: 33.2 (#264)
| Benchmark | Yi-1.5-34B | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1143 | 1094 |
Writing & Preference Yi-1.5-34B leads
Yi-1.5-34B: 37.4 (#257), Yi-34B: 34.1 (#273)
| Benchmark | Yi-1.5-34B | Yi-34B |
|---|---|---|
| LMArena Text | 1173 | 1129 |
| LMArena Creative Writing | 1135 | 1108 |
| LMArena Multi-Turn | 1153 | 1113 |
Frequently asked questions
Is Yi-1.5-34B better than Yi-34B?
Yi-1.5-34B is the stronger model overall, scoring 30.6 to 27.8 on the Noometry Index.
Is Yi-1.5-34B or Yi-34B better for coding?
They score almost the same on coding (32.4 vs 32.3); test both on your own repository before choosing.
How many benchmarks do Yi-1.5-34B and Yi-34B share?
19 benchmarks have published results for both models. Yi-1.5-34B has 21 scored results on Noometry and Yi-34B has 23.