Model comparison
MiMo-V2.6-Pro vs Olmo 3 32b Think
MiMo-V2.6-Pro is the stronger model overall, scoring 46.7 to 38.1 on the Noometry Index.
Last verified . 12 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 12 benchmarks with published results for both. MiMo-V2.6-Pro scores higher in 8 categories and Olmo 3 32b Think in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.6-Pro leads 66.9 to 49.2.
Side by side
| MiMo-V2.6-Pro | Olmo 3 32b Think | |
|---|---|---|
| Provider | Xiaomi | Allen Institute for AI (Ai2) |
| Noometry Index | 46.7 | 38.1 |
| Released | 2026-09-22 | — |
| Weights | Open | Open |
| Context window | 1.05M | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.43 | — |
| Output $ / M tokens | $0.87 | — |
| Results tracked | 14 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 53.2 (#27), Olmo 3 32b Think: 38.0 (#169)
| Benchmark | MiMo-V2.6-Pro | Olmo 3 32b Think |
|---|---|---|
| LMArena Coding | 1538 | 1318 |
| LMArena WebDev | 1618 | — |
Reasoning MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 30.4 (#76), Olmo 3 32b Think: 24.9 (#138)
| Benchmark | MiMo-V2.6-Pro | Olmo 3 32b Think |
|---|---|---|
| LMArena Hard Prompts | 1511 | 1302 |
Math MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 37.9 (#91), Olmo 3 32b Think: 33.8 (#165)
| Benchmark | MiMo-V2.6-Pro | Olmo 3 32b Think |
|---|---|---|
| LMArena Math | 1497 | 1315 |
Knowledge MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 43.0 (#85), Olmo 3 32b Think: 34.4 (#189)
| Benchmark | MiMo-V2.6-Pro | Olmo 3 32b Think |
|---|---|---|
| LMArena Expert | 1548 | 1272 |
Multimodal Not comparable
MiMo-V2.6-Pro: 40.2 (#40), Olmo 3 32b Think: —
| Benchmark | MiMo-V2.6-Pro | Olmo 3 32b Think |
|---|---|---|
| LMArena Vision | 1265 | — |
Multilingual MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 57.0 (#15), Olmo 3 32b Think: 41.4 (#205)
| Benchmark | MiMo-V2.6-Pro | Olmo 3 32b Think |
|---|---|---|
| LMArena Non-English | 1474 | 1255 |
| LMArena Chinese | 1532 | 1300 |
| LMArena Russian | 1481 | 1255 |
| LMArena French | — | 1291 |
| LMArena German | — | 1290 |
Instruction Following MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 78.2 (#10), Olmo 3 32b Think: 67.4 (#193)
| Benchmark | MiMo-V2.6-Pro | Olmo 3 32b Think |
|---|---|---|
| LMArena Instruction Following | 1490 | 1275 |
Long Context MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 46.0 (#26), Olmo 3 32b Think: 39.4 (#177)
| Benchmark | MiMo-V2.6-Pro | Olmo 3 32b Think |
|---|---|---|
| LMArena Longer Query | 1500 | 1296 |
Writing & Preference MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 66.9 (#32), Olmo 3 32b Think: 49.2 (#188)
| Benchmark | MiMo-V2.6-Pro | Olmo 3 32b Think |
|---|---|---|
| LMArena Text | 1491 | 1300 |
| LMArena Creative Writing | 1465 | 1256 |
| LMArena Multi-Turn | 1463 | 1289 |
Frequently asked questions
Is MiMo-V2.6-Pro better than Olmo 3 32b Think?
MiMo-V2.6-Pro is the stronger model overall, scoring 46.7 to 38.1 on the Noometry Index.
Is MiMo-V2.6-Pro or Olmo 3 32b Think better for coding?
MiMo-V2.6-Pro scores higher on coding benchmarks: 53.2 versus 38.0 in the Noometry coding category.
How many benchmarks do MiMo-V2.6-Pro and Olmo 3 32b Think share?
12 benchmarks have published results for both models. MiMo-V2.6-Pro has 14 scored results on Noometry and Olmo 3 32b Think has 14.