MIT-licensed open-weight model with text, image, video, and audio inputs and text output. The efficiency-focused MiMo-V2.6 model has independent results across all five SI categories. API prices are Xiaomi rates listed by OpenRouter.
SI v3 uses weighted percentages from one Artificial Analysis configuration. Ranking requires all five benchmarks. Partial scores average only available weights. Scores are not comparable to SI v2 or a probability of reaching singularity.
Compared with models released within six months of it.
| Benchmark | Score | Rank |
|---|---|---|
HLEArtificial Analysis Challenging multidisciplinary questions evaluated by Artificial Analysis | 35.1% | #49 / 95 |
| Benchmark / source | Score |
|---|---|
HLE Artificial AnalysisMiMo-V2.6-Flash | 35.1% |
MMMU-Pro Artificial AnalysisMiMo-V2.6-Flash | 73.1% |
Terminal-Bench 4.0 Artificial AnalysisMiMo-V2.6-Flash | 22.7% |
SciCode Artificial AnalysisMiMo-V2.6-Flash | 51.3% |
AA-LCR Artificial AnalysisMiMo-V2.6-Flash | 74.3% |
CritPt Artificial AnalysisMiMo-V2.6-Flash | 12% |