MiMo V2 Flash
MiMo V2 Flash is capable in long context; and behind the leaders in reasoning, coding, and instruction following. Too few results yet to rate agentic tasks, safety, math, multimodal tasks, multilingual tasks, or factuality.
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 Agentic, Safety, Math, Multimodal, Multilingual or Factuality.
Price
$0.10input$0.30outputper million tokens
From Artificial Analysis · All prices
Evidence
85results on42benchmarks
- 2 independently verified
- 47 aggregator
- 21 vendor-reported
- 15 cross-referenced
From 7 sources · latest Oct 8, 2026 · How verification works
API features
Tool callingJSON modeReasoning
As listed by OpenRouter
Research
2 papers reference MiMo V2 FlashMiMo V2 Flash benchmark results
85 results on 42 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
22.0% behind the leader2 of 3 ranked benchmarks measured
- 60.60Oct 7, 2026
- 70.67Oct 8, 2026
29.6% behind the leader3 of 6 ranked benchmarks measured
- GPQA Diamond84.65Oct 8, 2026gpqa
- Humanity's Last Exam22.85Oct 8, 2026aa_hle
- 4.29Oct 8, 2026
Show 8 more reasoning resultsHide 8 reasoning results
- 0.00Oct 8, 2026
- 2.86Oct 8, 2026
- GPQA Diamond65.56Oct 8, 2026gpqa
- GPQA Diamond83.54Oct 8, 2026gpqa
- GPQA Diamond83.70Oct 7, 2026GPQA
- Humanity's Last Exam8.57Oct 8, 2026aa_hle
- Humanity's Last Exam22.10Oct 8, 2026aa_hle
- 22.10Oct 7, 2026
31.6% behind the leader7 of 10 ranked benchmarks measured
- 80.60Oct 7, 2026
- 73.40Oct 7, 2026
- 71.70Oct 7, 2026
- Terminal-Bench 2.161.80Oct 8, 2026terminalbenchV21
- SciCode39.35Sep 4, 2026aa_scicode
- 1330.89Aug 29, 2026
- Terminal-Bench Hard28.03Oct 8, 2026aa_terminalbench_hard
Show 8 more coding resultsHide 8 coding results
- 80.60May 30, 2026
- 1292.49May 22, 2026
- SciCode25.93Sep 4, 2026aa_scicode
- SciCode38.31Sep 4, 2026aa_scicode
- 73.40May 30, 2026
- Terminal-Bench Hard25.76Oct 8, 2026aa_terminalbench_hard
- Terminal-Bench Hard31.06Oct 8, 2026aa_terminalbench_hard
- 30.50Jun 13, 2026
32.2% behind the leader1 of 3 ranked benchmarks measured
- IFBench64.22Oct 8, 2026aa_ifbench
0 of 7 ranked benchmarks measured
- 6.56Oct 8, 2026
- τ-Bench V3 · Banking3.09Aug 10, 2026tauBanking
- 28.98Jun 15, 2026
Show 4 more agentic resultsHide 4 agentic results
- 58.30Oct 7, 2026
- 45.40Jun 13, 2026
- 45.40May 30, 2026
- 28.94May 2, 2026
0 of 5 ranked benchmarks measured
- 80.90May 30, 2026
0 of 4 ranked benchmarks measured
- AA-Omniscience · Accuracy15.63Oct 8, 2026omniscienceAccuracy
- AA-Omniscience · Accuracy24.83Oct 8, 2026omniscienceAccuracy
- AA-Omniscience · Non-hallucination24.04Oct 8, 2026omniscienceNonHallucination
Show 3 more factuality resultsHide 3 factuality results
- AA-Omniscience · Accuracy19.78Oct 8, 2026omniscienceAccuracy
- AA-Omniscience · Non-hallucination6.63Oct 8, 2026omniscienceNonHallucination
- AA-Omniscience · Non-hallucination51.59Oct 8, 2026omniscienceNonHallucination
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- AA Intelligence16.05Oct 8, 2026aa_intelligence_index
- τ²-Bench Telecom (AA run)83.92Oct 8, 2026aa_tau2
- -48.45Oct 8, 2026
- τ²-Bench Telecom (AA run)95.03Oct 8, 2026aa_tau2
- AA Intelligence20.82Oct 8, 2026aa_intelligence_index
- -45.35Oct 8, 2026
Show 32 more resultsHide 32 results
- 11.99Aug 10, 2026
- 52.10Jun 18, 2026
- 48.76Jun 18, 2026
- AA Intelligence22.44Oct 8, 2026aa_intelligence_index
- -19.05Oct 8, 2026
- 94.10Oct 7, 2026
- 94.10May 30, 2026
- 86.20Jun 13, 2026
- 54.10Jun 13, 2026
- 86.20Oct 7, 2026
- Artificial Analysis Coding Index49.84Sep 9, 2026aa_coding_index
- 31.80Jun 18, 2026
- 33.48Jun 18, 2026
- browsecomp_with_context_manager58.30Jun 13, 2026BrowseComp (w/ Context Manage)
- browsecomp_with_context_manager58.30May 30, 2026BrowseComp (w/ Context Manager)
- 51.20May 30, 2026
- 78.20May 30, 2026
- 84.40Oct 7, 2026
- 84.40Jun 13, 2026
- HMMT Feb. 202584.40May 30, 2026HMMT 2025 (Feb.)
- HMMT Nov. 202591.00May 30, 2026HMMT 2025 (Nov.)
- 84.90Oct 7, 2026
- 45.70Oct 7, 2026
- 54.30May 30, 2026
- 30.50Sep 23, 2026
- 38.50Oct 7, 2026
- 38.50May 30, 2026
- xbench-DeepSearch44.00May 30, 2026xbench-DeepSearch (2025.10)
- 44.00May 3, 2026
- 80.30Jun 13, 2026
- 80.30Jun 12, 2026
- τ²-Bench Telecom (AA run)93.27Oct 8, 2026aa_tau2
MiMo V2 Flash: common questions
Who makes MiMo V2 Flash?
MiMo V2 Flash is made by Xiaomi.
When was MiMo V2 Flash released?
MiMo V2 Flash was released on Dec 16, 2025, according to Artificial Analysis.
What is MiMo V2 Flash good at?
MiMo V2 Flash is capable in long context; and behind the leaders in reasoning, coding, and instruction following. Too few results yet to rate agentic tasks, safety, math, multimodal tasks, multilingual tasks, or factuality.
How much does MiMo V2 Flash cost?
MiMo V2 Flash costs $0.10 per million input tokens and $0.30 per million output tokens, according to Artificial Analysis. At a mix of three input tokens to one output token, it is cheaper than 85% of the 330 priced models we track.
How many benchmarks has MiMo V2 Flash been tested on?
We track 85 results for MiMo V2 Flash on 42 benchmarks from 7 sources, 2 of them independently verified. The latest was recorded on Oct 8, 2026.
Which API features does MiMo V2 Flash support?
OpenRouter lists tool calling, json mode, and reasoning for MiMo V2 Flash.
About this record
Where MiMo V2 Flash's numbers come from, and every name it appears under.
- Tracked since
- May 3, 2026
- Newest source mention
- Aug 11, 2026
Where the results come from
Verification: 85 scores · 2 independently verified · 47 aggregator-attributed · 15 vendor cross-reference · 21 vendor-reported. How these tiers are assigned
From 7 sources on 4 sites. Artificial Analysis supplies 47 of them; the 2 independently verified results come from 1 site. Bars are coloured by trust tier.
- artificialanalysis.ai47
- huggingface.co22
- api.llm-stats.com14
- datasets-server.huggingface.co2