Model comparison
Mistral vs Yi-Lightning
Yi-Lightning is the stronger model overall, scoring 37.1 to 29.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AISummary
- They share 17 benchmarks with published results for both. Mistral 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 16.6.
Side by side
| Mistral | Yi-Lightning | |
|---|---|---|
| Provider | Mistral AI | 01.AI |
| Noometry Index | 29.9 | 37.1 |
| Released | — | 2024-12-02 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral leads
Mistral: 33.8 (#250), Yi-Lightning: 27.4 (#320)
| Benchmark | Mistral | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1162 | 1312 |
| Aider Polyglot | — | 12.9% |
Reasoning Yi-Lightning leads
Mistral: 22.2 (#200), Yi-Lightning: 25.9 (#139)
| Benchmark | Mistral | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1149 | 1302 |
Math Yi-Lightning leads
Mistral: 22.3 (#278), Yi-Lightning: 36.2 (#172)
| Benchmark | Mistral | Yi-Lightning |
|---|---|---|
| LMArena Math | 1180 | 1300 |
| Omni-MATH | 7.2% | — |
Knowledge Yi-Lightning leads
Mistral: 16.6 (#288), Yi-Lightning: 35.4 (#185)
| Benchmark | Mistral | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1125 | 1286 |
| MMLU-Pro | 27.7% | — |
| GPQA (HELM) | 30.3% | — |
Multilingual Yi-Lightning leads
Mistral: 32.8 (#254), Yi-Lightning: 42.2 (#196)
| Benchmark | Mistral | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1129 | 1269 |
| LMArena Chinese | 1109 | 1320 |
| LMArena French | 1180 | 1305 |
| LMArena German | 1155 | 1267 |
| LMArena Japanese | 1013 | 1228 |
| LMArena Korean | 1032 | 1192 |
| LMArena Russian | 1168 | 1255 |
| LMArena Spanish | 1143 | 1315 |
Instruction Following Yi-Lightning leads
Mistral: 52.6 (#288), Yi-Lightning: 67.4 (#196)
| Benchmark | Mistral | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1152 | 1278 |
| IFEval | 56.8% | — |
Long Context Yi-Lightning leads
Mistral: 35.0 (#245), Yi-Lightning: 39.4 (#181)
| Benchmark | Mistral | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1153 | 1297 |
Writing & Preference Yi-Lightning leads
Mistral: 37.0 (#260), Yi-Lightning: 50.2 (#184)
| Benchmark | Mistral | Yi-Lightning |
|---|---|---|
| LMArena Text | 1165 | 1302 |
| LMArena Creative Writing | 1158 | 1280 |
| LMArena Multi-Turn | 1147 | 1311 |
| WildBench | 66% | — |
Frequently asked questions
Is Mistral better than Yi-Lightning?
Yi-Lightning is the stronger model overall, scoring 37.1 to 29.9 on the Noometry Index.
Is Mistral or Yi-Lightning better for coding?
Mistral scores higher on coding benchmarks: 33.8 versus 27.4 in the Noometry coding category.
How many benchmarks do Mistral and Yi-Lightning share?
17 benchmarks have published results for both models. Mistral has 22 scored results on Noometry and Yi-Lightning has 18.