Model comparison
Olmo 3 32b Think vs Yi-Lightning
Olmo 3 32b Think is the stronger model overall, scoring 38.7 to 37.1 on the Noometry Index.
Last verified . 14 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 14 benchmarks with published results for both. Olmo 3 32b Think scores higher in 2 categories and Yi-Lightning in 6 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in coding, where Olmo 3 32b Think leads 38.6 to 27.4.
- Olmo 3 32b Think has downloadable open weights; the other is API-only.
Side by side
| Olmo 3 32b Think | Yi-Lightning | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | 01.AI |
| Noometry Index | 38.7 | 37.1 |
| Released | — | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Olmo 3 32b Think leads
Olmo 3 32b Think: 38.6 (#172), Yi-Lightning: 27.4 (#320)
| Benchmark | Olmo 3 32b Think | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1319 | 1312 |
| Aider Polyglot | — | 12.9% |
Reasoning Too close to call
Olmo 3 32b Think: 25.9 (#140), Yi-Lightning: 25.9 (#139)
| Benchmark | Olmo 3 32b Think | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1302 | 1302 |
Math Too close to call
Olmo 3 32b Think: 36.5 (#165), Yi-Lightning: 36.2 (#172)
| Benchmark | Olmo 3 32b Think | Yi-Lightning |
|---|---|---|
| LMArena Math | 1316 | 1300 |
Knowledge Too close to call
Olmo 3 32b Think: 35.0 (#190), Yi-Lightning: 35.4 (#185)
| Benchmark | Olmo 3 32b Think | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1273 | 1286 |
Multilingual Yi-Lightning leads
Olmo 3 32b Think: 41.2 (#210), Yi-Lightning: 42.2 (#196)
| Benchmark | Olmo 3 32b Think | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1255 | 1269 |
| LMArena Chinese | 1300 | 1320 |
| LMArena French | 1291 | 1305 |
| LMArena German | 1290 | 1267 |
| LMArena Russian | 1254 | 1255 |
| LMArena Japanese | — | 1228 |
| LMArena Korean | — | 1192 |
| LMArena Spanish | — | 1315 |
Instruction Following Too close to call
Olmo 3 32b Think: 67.2 (#198), Yi-Lightning: 67.4 (#196)
| Benchmark | Olmo 3 32b Think | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1275 | 1278 |
Long Context Too close to call
Olmo 3 32b Think: 39.4 (#182), Yi-Lightning: 39.4 (#181)
| Benchmark | Olmo 3 32b Think | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1296 | 1297 |
Writing & Preference Yi-Lightning leads
Olmo 3 32b Think: 49.1 (#193), Yi-Lightning: 50.2 (#184)
| Benchmark | Olmo 3 32b Think | Yi-Lightning |
|---|---|---|
| LMArena Text | 1300 | 1302 |
| LMArena Creative Writing | 1256 | 1280 |
| LMArena Multi-Turn | 1290 | 1311 |
Frequently asked questions
Is Olmo 3 32b Think better than Yi-Lightning?
Olmo 3 32b Think is the stronger model overall, scoring 38.7 to 37.1 on the Noometry Index.
Is Olmo 3 32b Think or Yi-Lightning better for coding?
Olmo 3 32b Think scores higher on coding benchmarks: 38.6 versus 27.4 in the Noometry coding category.
How many benchmarks do Olmo 3 32b Think and Yi-Lightning share?
14 benchmarks have published results for both models. Olmo 3 32b Think has 14 scored results on Noometry and Yi-Lightning has 18.