Basis
Xiaomi·MODEL DOSSIER·TRACKED 4D AGO·LAST SEEN 37M AGO
MiMo V2.6 Pro
Strong on Long Context; capable on Reasoning and Agentic +1 more; limited on Coding — at $0.43/M input across 3 providers. Insufficient data on 5 of 10 axes.
Aliases:mimo-v2-6-proMiMo-V2.6-Pro-RLmimo 2.6 promimo-v2.6 proxiaomimimo/mimo-v2.6-pro-rl+1 more
1 Strong3 Capable1 Limited5 Insufficient
CAPABILITY CLASSIFICATION10 axes
VS AXIS LEADER · BAR = 100 − DISTANCE · ROWS EXPAND TO THEIR EVIDENCE
PRICING3View Pricing →
| Provider | Model name | Input $/M | Output $/M | Effective | Current |
|---|---|---|---|---|---|
| direct ↗ | mimo-v2-6-pro | $0.43 | $0.87 | 2026-09-23 | ● |
| deepinfra ↗ | XiaomiMiMo/MiMo-V2.6-Pro | $0.43 | $0.87 | 2026-09-22 | ● |
| xiaomi ↗ | mimo-v2.6-pro | $0.43 | $0.87 | 2026-09-22 | ● |
RECEIPTS — ALL MEASURED BENCHMARKS21
| Benchmark | Score | Settings | Source | Verification | Methodology | Measured | Reference |
|---|---|---|---|---|---|---|---|
Artificial Analysis Intelligence Index | 46.00 | — | artificialanalysis.aimimo-v2-6-pro | VERIFIED | OTHER | 22h ago | view ↗ |
| 58.66 | reasoning | artificialanalysis.ai | AGGREGATOR | AGGR | 22h ago | view ↗ | |
aa_lcr | 86.33 | reasoning | artificialanalysis.ai | AGGREGATOR | AGGR | 22h ago | view ↗ |
aa_omniscience | 8.38 | reasoning | artificialanalysis.ai | AGGREGATOR | AGGR | 22h ago | view ↗ |
aa_hle | 49.35 | reasoning | artificialanalysis.ai | AGGREGATOR | AGGR | 22h ago | view ↗ |
aa_scicode | 60.88 | reasoning | artificialanalysis.ai | AGGREGATOR | AGGR | 22h ago | view ↗ |
omniscienceAccuracy | 34.85 | reasoning | artificialanalysis.ai | AGGREGATOR | AGGR | 22h ago | view ↗ |
omniscienceNonHallucination | 59.38 | reasoning | artificialanalysis.ai | AGGREGATOR | AGGR | 22h ago | view ↗ |
terminalbenchV40 | 34.85 | reasoning | artificialanalysis.ai | AGGREGATOR | AGGR | 22h ago | view ↗ |
| 26.57 | reasoning | artificialanalysis.ai | AGGREGATOR | AGGR | 22h ago | view ↗ | |
CyberGym | 94.00 | — | api.llm-stats.comscores | VENDOR | OTHER | 1d ago | view ↗ |
| 62.00 | — | api.llm-stats.comscores | VENDOR | OTHER | 1d ago | view ↗ | |
| 82.00 | — | api.llm-stats.comscores | VENDOR | OTHER | 1d ago | view ↗ | |
| 89.90 | — | api.llm-stats.comscores | VENDOR | OTHER | 1d ago | view ↗ | |
Terminal-Bench 4.0 | 34.90 | — | api.llm-stats.comscores | VENDOR | OTHER | 1d ago | view ↗ |
Toolathlon-Verified | 76.90 | — | api.llm-stats.comscores | VENDOR | OTHER | 1d ago | view ↗ |
| 26.50 | — | api.llm-stats.comscores | VENDOR | OTHER | 1d ago | view ↗ | |
| 71.90 | — | api.llm-stats.comscores | VENDOR | OTHER | 1d ago | view ↗ | |
| 31.60 | — | huggingface.coREADME | VENDOR | VENDOR | 1d ago | view ↗ | |
GDPval-AA 2.1 | 1673.00 | — | huggingface.coREADME | VENDOR | VENDOR | 1d ago | view ↗ |
aa_intelligence_index | 46.32 | reasoning | artificialanalysis.ai | AGGREGATOR | AGGR | 22h ago | view ↗ |
Verification: 21 scores · 1 independently verified · 10 aggregator-attributed · 10 vendor-reported. How these tiers are assigned
Comparisons — MiMo V2.6 ProΔ THE DELTA
VSGPT-5.6 Sol· OPENAI26SHARED BENCHMARKSVSMiMo V2.5 Pro· XIAOMI24SHARED BENCHMARKSVSClaude Fable 5· ANTHROPIC23SHARED BENCHMARKSVSClaude Opus 5· ANTHROPIC23SHARED BENCHMARKSVSClaude Opus 4.8· ANTHROPIC20SHARED BENCHMARKS
+ 3 MORE CURATED MATCHUPS — ALL IN THE INDEX BELOW
The Xiaomi lineMiMo V2.5 ProMiMo V2 FlashMiMo V2 Flash BaseMiMo 7B RLMiMo V2.5 BaseMiMo V2.5 Pro BaseALL XIAOMI →