Model comparison
MiMo-V2.6-Pro vs Olmo 2 0325 32b Instruct
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 32.7 on the Noometry Index.
Last verified . 11 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 11 benchmarks with published results for both. MiMo-V2.6-Pro scores higher in 8 categories and Olmo 2 0325 32b Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where MiMo-V2.6-Pro leads 54.5 to 26.8.
Side by side
| MiMo-V2.6-Pro | Olmo 2 0325 32b Instruct | |
|---|---|---|
| Provider | Xiaomi | Allen Institute for AI (Ai2) |
| Noometry Index | 50.3 | 32.7 |
| Released | 2026-09-21 | — |
| Weights | Open | Open |
| Context window | 1.05M | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.43 | — |
| Output $ / M tokens | $0.87 | — |
| Results tracked | 19 | 16 |
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: 55.5 (#23), Olmo 2 0325 32b Instruct: 35.2 (#227)
| Benchmark | MiMo-V2.6-Pro | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Coding | 1534 | 1210 |
| LMArena WebDev | 1629 | — |
| SciCode | 60.9% | — |
| ALE-Bench | 1,158 | — |
Agentic & Tool Use Not comparable
MiMo-V2.6-Pro: 37.5 (#35), Olmo 2 0325 32b Instruct: —
| Benchmark | MiMo-V2.6-Pro | Olmo 2 0325 32b Instruct |
|---|---|---|
| APEX-Agents | 59.5% | — |
Reasoning MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 43.1 (#50), Olmo 2 0325 32b Instruct: 23.6 (#175)
| Benchmark | MiMo-V2.6-Pro | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1512 | 1208 |
| CritPt | 26.6% | — |
Math MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 54.5 (#45), Olmo 2 0325 32b Instruct: 26.8 (#255)
| Benchmark | MiMo-V2.6-Pro | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Math | 1494 | 1208 |
| ProofBench | 70% | — |
| Omni-MATH | — | 16.1% |
Knowledge MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 43.5 (#92), Olmo 2 0325 32b Instruct: 19.5 (#279)
| Benchmark | MiMo-V2.6-Pro | Olmo 2 0325 32b Instruct |
|---|---|---|
| MMLU-Pro | — | 41.4% |
| GPQA (HELM) | — | 28.7% |
| LMArena Expert | 1543 | — |
Multimodal Not comparable
MiMo-V2.6-Pro: 40.8 (#43), Olmo 2 0325 32b Instruct: —
| Benchmark | MiMo-V2.6-Pro | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Vision | 1264 | — |
Multilingual MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 56.9 (#14), Olmo 2 0325 32b Instruct: 34.8 (#248)
| Benchmark | MiMo-V2.6-Pro | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Non-English | 1474 | 1160 |
| LMArena Chinese | 1529 | 1192 |
| LMArena Russian | 1480 | 1187 |
Instruction Following MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 78.2 (#12), Olmo 2 0325 32b Instruct: 61.5 (#244)
| Benchmark | MiMo-V2.6-Pro | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Instruction Following | 1493 | 1186 |
| IFEval | — | 78% |
Long Context MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 46.0 (#27), Olmo 2 0325 32b Instruct: 36.2 (#234)
| Benchmark | MiMo-V2.6-Pro | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Longer Query | 1501 | 1194 |
Writing & Preference MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 66.8 (#33), Olmo 2 0325 32b Instruct: 42.1 (#236)
| Benchmark | MiMo-V2.6-Pro | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Text | 1492 | 1218 |
| LMArena Creative Writing | 1468 | 1199 |
| LMArena Multi-Turn | 1464 | 1221 |
| WildBench | — | 73.4% |
Frequently asked questions
Is MiMo-V2.6-Pro better than Olmo 2 0325 32b Instruct?
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 32.7 on the Noometry Index.
Is MiMo-V2.6-Pro or Olmo 2 0325 32b Instruct better for coding?
MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 35.2 in the Noometry coding category.
How many benchmarks do MiMo-V2.6-Pro and Olmo 2 0325 32b Instruct share?
11 benchmarks have published results for both models. MiMo-V2.6-Pro has 19 scored results on Noometry and Olmo 2 0325 32b Instruct has 16.