Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Holo3-122B-A10B
~79
0/8 categoriesMiMo-V2-Pro
~85
Winner · 1/8 categoriesHolo3-122B-A10B· MiMo-V2-Pro
Pick MiMo-V2-Pro if you want the stronger benchmark profile. Holo3-122B-A10B only becomes the better choice if you would rather avoid the extra latency and token burn of a reasoning model.
MiMo-V2-Pro is clearly ahead on the aggregate, 85 to 79. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
MiMo-V2-Pro's sharpest advantage is in agentic, where it averages 86.7 against 78.9.
MiMo-V2-Pro is the reasoning model in the pair, while Holo3-122B-A10B is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. MiMo-V2-Pro gives you the larger context window at 1M, compared with 64K for Holo3-122B-A10B.
BenchLM keeps the benchmark table and the operator tradeoffs on the same page so a better score does not hide a materially slower, pricier, or smaller-context model.
Runtime metrics show N/A when BenchLM does not have a sourced snapshot for that exact model. The scoring rules and freshness policy are documented on the methodology page.
| Benchmark | Holo3-122B-A10B | MiMo-V2-Pro |
|---|---|---|
| AgenticMiMo-V2-Pro wins | ||
| OSWorld-Verified | 78.8% | — |
| Terminal-Bench 2.0 | — | 86.7% |
| Coding | ||
| SWE-bench Verified | — | 78% |
| Multimodal & Grounded | ||
| Coming soon | ||
| Reasoning | ||
| Coming soon | ||
| Knowledge | ||
| GPQA | — | 87% |
| Instruction Following | ||
| Coming soon | ||
| Multilingual | ||
| Coming soon | ||
| Mathematics | ||
| Coming soon | ||
MiMo-V2-Pro is ahead overall, 85 to 79.
MiMo-V2-Pro has the edge for agentic tasks in this comparison, averaging 86.7 versus 78.9. Holo3-122B-A10B stays close enough that the answer can still flip depending on your workload.
Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.
Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.