MiMo V2 Omni
MiMo V2 Omni is capable in long context; and behind the leaders in factuality, coding, multimodal tasks, reasoning, agentic tasks, and instruction following. Too few results yet to rate safety, math, or multilingual tasks.
Capability profile
Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.
Too few results yet to rate Safety, Math or Multilingual.
Price
$0.40input$2.00outputper million tokens
From xiaomi · All prices
Evidence
37results on20benchmarks
- 2 independently verified
- 32 aggregator
- 3 vendor-reported
From 4 sources · latest Oct 8, 2026 · How verification works
API features
Tool callingJSON modeReasoning
As listed by OpenRouter
MiMo V2 Omni benchmark results
37 results on 20 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
18.7% behind the leader1 of 3 ranked benchmarks measured
- 75.00Oct 8, 2026
Show 1 more long context resultHide 1 long context result
- 73.33Oct 8, 2026
29.9% behind the leader2 of 4 ranked benchmarks measured
- AA-Omniscience · Non-hallucination51.14Oct 8, 2026omniscienceNonHallucination
- AA-Omniscience · Accuracy19.30Oct 8, 2026omniscienceAccuracy
Show 2 more factuality resultsHide 2 factuality results
- AA-Omniscience · Accuracy17.82Oct 8, 2026omniscienceAccuracy
- AA-Omniscience · Non-hallucination59.95Oct 8, 2026omniscienceNonHallucination
31.8% behind the leader3 of 10 ranked benchmarks measured
- 74.80Oct 7, 2026
- SciCode36.69Sep 4, 2026aa_scicode
- Terminal-Bench Hard34.85Oct 8, 2026aa_terminalbench_hard
Show 2 more coding resultsHide 2 coding results
- SciCode39.47Sep 4, 2026aa_scicode
- Terminal-Bench Hard35.61Oct 8, 2026aa_terminalbench_hard
32.1% behind the leader1 of 6 ranked benchmarks measured
- MMMU-Pro69.88Oct 8, 2026aa_mmmu_pro
Show 3 more multimodal resultsHide 3 multimodal results
- 1227.77Aug 25, 2026
- 1218Jun 17, 2026
- MMMU-Pro73.93Oct 8, 2026aa_mmmu_pro
33.7% behind the leader3 of 6 ranked benchmarks measured
- GPQA Diamond82.83Oct 8, 2026gpqa
- Humanity's Last Exam22.10Oct 8, 2026aa_hle
- 1.14Oct 8, 2026
Show 3 more reasoning resultsHide 3 reasoning results
- 0.86Oct 8, 2026
- GPQA Diamond85.45Oct 8, 2026gpqa
- Humanity's Last Exam22.57Oct 8, 2026aa_hle
35.5% behind the leader1 of 7 ranked benchmarks measured
- 40.87Jun 15, 2026
Show 1 more agentic resultHide 1 agentic result
- 42.37Jun 15, 2026
37.4% behind the leader1 of 3 ranked benchmarks measured
- IFBench53.54Oct 8, 2026aa_ifbench
Show 1 more instruction following resultHide 1 instruction following result
- IFBench67.35Oct 8, 2026aa_ifbench
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- -20.13Oct 8, 2026
- τ²-Bench Telecom (AA run)91.23Oct 8, 2026aa_tau2
- AA Intelligence23.92Oct 8, 2026aa_intelligence_index
- τ²-Bench Telecom (AA run)88.01Oct 8, 2026aa_tau2
- AA Intelligence25.12Oct 8, 2026aa_intelligence_index
- -15.10Oct 8, 2026
Show 6 more resultsHide 6 results
- 58.56Jun 18, 2026
- 58.63Jun 18, 2026
- 35.46Jun 18, 2026
- 36.89Jun 18, 2026
- Claw Eval (pass@3)54.80Oct 7, 2026Claw-Eval
- 81.20Oct 7, 2026
MiMo V2 Omni: common questions
Who makes MiMo V2 Omni?
MiMo V2 Omni is made by Xiaomi.
When was MiMo V2 Omni released?
MiMo V2 Omni was released on Mar 19, 2026, according to Artificial Analysis.
What is MiMo V2 Omni good at?
MiMo V2 Omni is capable in long context; and behind the leaders in factuality, coding, multimodal tasks, reasoning, agentic tasks, and instruction following. Too few results yet to rate safety, math, or multilingual tasks.
How much does MiMo V2 Omni cost?
MiMo V2 Omni costs $0.40 per million input tokens and $2.00 per million output tokens, according to xiaomi. At a mix of three input tokens to one output token, it costs more than 52% of the 331 priced models we track.
How many benchmarks has MiMo V2 Omni been tested on?
We track 37 results for MiMo V2 Omni on 20 benchmarks from 4 sources, 2 of them independently verified. The latest was recorded on Oct 8, 2026.
Which API features does MiMo V2 Omni support?
OpenRouter lists tool calling, json mode, and reasoning for MiMo V2 Omni.
About this record
Where MiMo V2 Omni's numbers come from, and every name it appears under.
- Tracked since
- Apr 27, 2026
- Newest source mention
- Jul 20, 2026
Where the results come from
Verification: 37 scores · 2 independently verified · 32 aggregator-attributed · 3 vendor-reported. How these tiers are assigned
From 4 sources on 4 sites. Artificial Analysis supplies 32 of them; the 2 independently verified results come from 2 sites. Bars are coloured by trust tier.
- artificialanalysis.ai32
- api.llm-stats.com3
- datasets-server.huggingface.co1
- lmarena.ai1