Model comparison
Yi-34B vs Yi-Lightning
Yi-Lightning is the stronger model overall, scoring 37.1 to 27.8 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. Yi-34B scores higher in 1 category and Yi-Lightning in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Yi-Lightning leads 35.4 to 7.5.
- Yi-34B has downloadable open weights; the other is API-only.
Side by side
| Yi-34B | Yi-Lightning | |
|---|---|---|
| Provider | 01.AI | 01.AI |
| Noometry Index | 27.8 | 37.1 |
| Released | 2023-11-02 | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 23 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Yi-34B leads
Yi-34B: 32.3 (#274), Yi-Lightning: 27.4 (#320)
| Benchmark | Yi-34B | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1112 | 1312 |
| Aider Polyglot | — | 12.9% |
Reasoning Yi-Lightning leads
Yi-34B: 21.2 (#226), Yi-Lightning: 25.9 (#139)
| Benchmark | Yi-34B | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1104 | 1302 |
| BIG-Bench Hard | 71.7% | — |
| Epoch Capabilities Index | 117.39 | — |
Math Yi-Lightning leads
Yi-34B: 21.6 (#282), Yi-Lightning: 36.2 (#172)
| Benchmark | Yi-34B | Yi-Lightning |
|---|---|---|
| LMArena Math | 1114 | 1300 |
| MATH Level 5 | 5.1% | — |
| GSM8K | 76% | — |
Knowledge Yi-Lightning leads
Yi-34B: 7.5 (#309), Yi-Lightning: 35.4 (#185)
| Benchmark | Yi-34B | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1061 | 1286 |
| GPQA Diamond | 14.7% | — |
| MMLU | 76.3% | — |
Multilingual Yi-Lightning leads
Yi-34B: 29.7 (#264), Yi-Lightning: 42.2 (#196)
| Benchmark | Yi-34B | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1079 | 1269 |
| LMArena Chinese | 1176 | 1320 |
| LMArena French | 1081 | 1305 |
| LMArena German | 1042 | 1267 |
| LMArena Japanese | 993 | 1228 |
| LMArena Korean | 959 | 1192 |
| LMArena Russian | 1050 | 1255 |
| LMArena Spanish | 1070 | 1315 |
Instruction Following Yi-Lightning leads
Yi-34B: 56.2 (#274), Yi-Lightning: 67.4 (#196)
| Benchmark | Yi-34B | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1091 | 1278 |
Long Context Yi-Lightning leads
Yi-34B: 33.2 (#264), Yi-Lightning: 39.4 (#181)
| Benchmark | Yi-34B | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1094 | 1297 |
Writing & Preference Yi-Lightning leads
Yi-34B: 34.1 (#273), Yi-Lightning: 50.2 (#184)
| Benchmark | Yi-34B | Yi-Lightning |
|---|---|---|
| LMArena Text | 1129 | 1302 |
| LMArena Creative Writing | 1108 | 1280 |
| LMArena Multi-Turn | 1113 | 1311 |
Frequently asked questions
Is Yi-34B better than Yi-Lightning?
Yi-Lightning is the stronger model overall, scoring 37.1 to 27.8 on the Noometry Index.
Is Yi-34B or Yi-Lightning better for coding?
Yi-34B scores higher on coding benchmarks: 32.3 versus 27.4 in the Noometry coding category.
How many benchmarks do Yi-34B and Yi-Lightning share?
17 benchmarks have published results for both models. Yi-34B has 23 scored results on Noometry and Yi-Lightning has 18.