Model comparison
Mistral Small 3 vs Yi-Lightning
Yi-Lightning is the stronger model overall, scoring 37.1 to 31.2 on the Noometry Index.
Last verified . 16 shared benchmarks.
Mistral AISummary
- They share 16 benchmarks with published results for both. Mistral Small 3 scores higher in 1 category and Yi-Lightning in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Yi-Lightning leads 36.2 to 16.3.
- Mistral Small 3 has downloadable open weights; the other is API-only.
Side by side
| Mistral Small 3 | Yi-Lightning | |
|---|---|---|
| Provider | Mistral AI | 01.AI |
| Noometry Index | 31.2 | 37.1 |
| Released | 2025-01-30 | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | 33K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 24 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3 leads
Mistral Small 3: 36.5 (#207), Yi-Lightning: 27.4 (#320)
| Benchmark | Mistral Small 3 | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1246 | 1312 |
| Aider Polyglot | — | 12.9% |
| BigCodeBench Instruct | 45.3% | — |
| BigCodeBench Complete | 50.4% | — |
Reasoning Yi-Lightning leads
Mistral Small 3: 18.9 (#273), Yi-Lightning: 25.9 (#139)
| Benchmark | Mistral Small 3 | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1233 | 1302 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 127.07 | — |
Math Yi-Lightning leads
Mistral Small 3: 16.3 (#295), Yi-Lightning: 36.2 (#172)
| Benchmark | Mistral Small 3 | Yi-Lightning |
|---|---|---|
| LMArena Math | 1240 | 1300 |
| OTIS Mock AIME 2024-2025 | 6.7% | — |
Knowledge Yi-Lightning leads
Mistral Small 3: 25.1 (#263), Yi-Lightning: 35.4 (#185)
| Benchmark | Mistral Small 3 | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1202 | 1286 |
| GPQA Diamond | 47.3% | — |
| Confabulations | 25.2% | — |
Multilingual Yi-Lightning leads
Mistral Small 3: 37.3 (#236), Yi-Lightning: 42.2 (#196)
| Benchmark | Mistral Small 3 | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1198 | 1269 |
| LMArena Chinese | 1204 | 1320 |
| LMArena French | 1203 | 1305 |
| LMArena German | 1211 | 1267 |
| LMArena Japanese | 1111 | 1228 |
| LMArena Korean | 1188 | 1192 |
| LMArena Russian | 1216 | 1255 |
| LMArena Spanish | — | 1315 |
Instruction Following Yi-Lightning leads
Mistral Small 3: 63.7 (#229), Yi-Lightning: 67.4 (#196)
| Benchmark | Mistral Small 3 | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1214 | 1278 |
Long Context Yi-Lightning leads
Mistral Small 3: 37.8 (#211), Yi-Lightning: 39.4 (#181)
| Benchmark | Mistral Small 3 | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1246 | 1297 |
Writing & Preference Yi-Lightning leads
Mistral Small 3: 32.2 (#280), Yi-Lightning: 50.2 (#184)
| Benchmark | Mistral Small 3 | Yi-Lightning |
|---|---|---|
| LMArena Text | 1234 | 1302 |
| LMArena Creative Writing | 1195 | 1280 |
| LMArena Multi-Turn | 1217 | 1311 |
| EQ-Bench Creative Writing | 707 | — |
Frequently asked questions
Is Mistral Small 3 better than Yi-Lightning?
Yi-Lightning is the stronger model overall, scoring 37.1 to 31.2 on the Noometry Index.
Is Mistral Small 3 or Yi-Lightning better for coding?
Mistral Small 3 scores higher on coding benchmarks: 36.5 versus 27.4 in the Noometry coding category.
How many benchmarks do Mistral Small 3 and Yi-Lightning share?
16 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Yi-Lightning has 18.