Models / MiMo-V2.6-Flash

Xiaomi

MiMo-V2.6-Flash

MiMo-V2.6-Flash is best for agents and tool use; a strong pick at a modest price.

Results 16 Nov 2026 · 18 results · 2 sources

Test MiMo-V2.6-Flash on your prompt → It runs beside the models you could use instead, with every answer checked and costed.

Price per million tokens
$0.14 in · $0.28 out
Xiaomi's list price, 10 Nov 2026 · compare prices$0.00 cached input · 50% off in batch
Speed
46 tokens a second; on its test prompt the answer starts after 47.4 s, thinking time included
Artificial Analysis, on its usual API
Intelligence Index
37.9
Artificial Analysis
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
Xiaomi, based in China
Weights published
Released
21 Sep 2026
1,050,000 tokens of context

Where it stands among the models you could choose

Available models grouped by price, intelligence, speed and developer location, plus models with published weights. Retired models are excluded.

AmongIntelligence IndexSpring Prompt overallPrice, blendedSpeed
Models available today 38th of 185Claude Opus 5.5 – $0.18 blended, 15th percentilecheapest: Mistral Nemo 60th of 65Nemotron 3.5 Super VL
Models priced under $0.25 per million tokens 4th of 41Claude Haiku 5.5 – sets this group 18th of 19Nemotron 3.5 Super VL
Models with similar intelligence sets this group – $0.18 blended, 0th percentilethe cheapest 9th of 10DeepSeek-V4.1-Flash
Models writing under 50 tokens a second 5th of 9MiMo-V2.6-Pro – $0.18 blended, 12th percentilecheapest: Phi-4 sets this group
Models from developers based in China 10th of 75MiMo-V2.6-Pro – $0.18 blended, 10th percentilecheapest: Qwen3.5-9B 19th of 23DeepSeek-V4.1-Flash
Open-weights models 11th of 104MiMo-V2.6-Pro – $0.18 blended, 24th percentilecheapest: Mistral Nemo 39th of 43Nemotron 3.5 Super VL

The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.

How good is it, and for what?

Each use case ranks the available models its benchmarks measured, then those priced under $0.25 per million tokens. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.

Product listingsTurning a sparse product feed and photos into listings that can go live Not measured
  • CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is Not measured
  • DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled Not measured
  • SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending Not measured
  • ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 42nd of 159 available · 3rd of 37 at its price
BenchmarkMiMo-V2.6-FlashRank among availableBest available
Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported 22.7% 26th of 107 Kimi K3.1 Pro 67.2%
  • tau2-bench: pending. Its latest results are dated 26 May 2026, before this model was released.
  • Berkeley Function Calling Leaderboard (BFCL) V4: pending. Its latest results are dated 16 Dec 2025, before this model was released.
  • OpenHands Index: pending. Its latest results are dated 30 Jun 2026, before this model was released.
  • Microsoft STATE-Bench: pending. Its latest results are dated 29 May 2026, before this model was released.
  • Vending-Bench 2: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects Not measured
  • APEX-Agents: has not measured this model.
  • GDP.pdf: has not measured this model.
  • Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge 55th of 187 available · 5th of 41 at its price
BenchmarkMiMo-V2.6-FlashRank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 37.9 38th of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 35.1% 60th of 186 Claude Opus 5.5 61.4%
WritingWhat people prefer in blind comparisons, and judged writing quality 56th of 169 available · 2nd of 39 at its price
BenchmarkMiMo-V2.6-FlashRank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,452 52nd of 153 Gemini 4 Argon 1,525
  • UGI Leaderboard: has not measured this model.
Sticking to the factsSummarising without inventing things, and factual answers 46th of 139 available · 12th of 30 at its price
BenchmarkMiMo-V2.6-FlashRank among availableBest available
Arena (formerly LMArena)Arena Text factuality: overall · reported 1,457 39th of 109 Gemini 4 Argon 1,511
  • Vectara Hallucination Leaderboard: has not measured this model.
  • SimpleQA Verified (Epoch AI): has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess) Too slow for the clock
  • BulletBench: too slow for Bullet 60s: lost its first 4 games on time, at a median 4.7 s a move; too slow for Lightning 10+1: lost its first 4 games on time, at a median 3.2 s a move.

Where to run it

7 hosts on OpenRouter at the standard service tier, with a median of $0.17 blended per million tokens; quantisation where the host states it: BF16, FP4, FP8. Cheapest first.

HostQuantisationInputOutputBlended
GMICloudBF16$0.11$0.22$0.14
DarkbloomFP4$0.10$0.28$0.15
CohereFP8$0.14$0.28$0.18
DeepInfraFP8$0.14$0.28$0.18
MakoraFP8$0.14$0.28$0.18
XiaomiFP8$0.14$0.28$0.18
VeniceFP8$0.17$0.35$0.22

Prices per million tokens from OpenRouter's public endpoint list, checked 10 Nov 2026.

Against the alternatives

The models you would most likely weigh it against: the leaders of the groups above.

Scroll sideways to see every alternative.

MiMo-V2.6-FlashClaude Haiku 5.5
most intelligent at under $0.25 per million tokens
DeepSeek-V4.1-Flash
fastest with similar intelligence
Claude Opus 5.5
most intelligent available today
MiMo-V2.6-Pro
most intelligent from China
Price per million tokens $0.18 $0.20$0.52$8.00$0.54
Tokens a second 46 2403699643
Intelligence Index 37.9 43.439.557.646.3
Spring Prompt overall – 405182–
Rank among available models, by use case
Product listings – 20th15th13th–
Decks from an analysis – 18th–7th–
User surveys – 7th–4th–
Marketing planning – 30th–9th–
Agents and tool use 42nd of 159 28th31st3rd23rd
Professional work – ––3rd–
Reasoning and knowledge 55th of 187 25th42nd1st13th
Writing 56th of 169 –29th5th23rd
Sticking to the facts 46th of 139 –23rd3rd10th
Speed under pressure 36th of 36 21st–––

Shaded figures are better than MiMo-V2.6-Flash's. A dash means no result.

Where it has been measured

Cheapest of the 21 models with similar intelligence, and 2nd cheapest of the 9 models writing under 50 tokens a second. 4th most intelligent of the 41 models priced under $0.25 per million tokens. Among models available today, in the top quarter (by percentile) for agents and tool use; in the bottom quarter for speed under pressure.

Every result

18 published results from 2 sources, each in the source's own units, with the configuration that produced it.

Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 11 results
MeasureValueRankConfigurationDated
Arena Agent: confirmed task successIPS effect estimate, higher is better 0.06
0.03–0.08
15 of 50 MiMo-V2.6-Flash (arena agent) 2 Oct 2026
Arena Agent: praise over complaintIPS effect estimate, higher is better -0.01
-0.05–0.03
29 of 50 MiMo-V2.6-Flash (arena agent) 2 Oct 2026
Arena Agent: steerabilityIPS effect estimate, higher is better -0.00
-0.02–0.01
34 of 50 MiMo-V2.6-Flash (arena agent) 2 Oct 2026
Arena Agent: tool groundingIPS effect estimate, higher is better -0.04
-0.04–-0.03
50 of 50 MiMo-V2.6-Flash (arena agent) 2 Oct 2026
Arena Text factuality: overallArena rating, higher is better 1,457
1,450–1,464
51 of 182 MiMo-V2.6-Flash 2 Oct 2026
Arena Text: business, management and financeArena rating, higher is better 1,459
1,441–1,477
64 of 406 MiMo-V2.6-Flash 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,385
1,367–1,404
135 of 411 MiMo-V2.6-Flash 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,509
1,487–1,531
30 of 363 MiMo-V2.6-Flash 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,453
1,440–1,466
58 of 413 MiMo-V2.6-Flash 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,452
1,444–1,460
77 of 413 MiMo-V2.6-Flash 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,419
1,404–1,435
96 of 412 MiMo-V2.6-Flash 2 Oct 2026

Not shown: Not a success rate: the estimated effect of choosing this model as the agent's orchestrator, against an even mix of the models tested, inside Arena's own harness.

Artificial Analysis · reported by Artificial Analysis · 7 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 37.9 78 of 413 MiMo-V2.6-Flash 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 35.1% 119 of 419 MiMo-V2.6-Flash 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 74.3% 157 of 407 MiMo-V2.6-Flash 20 Oct 2026
Artificial Analysis: Output speedtokens per second, higher is better 46.2 121 of 137 MiMo-V2.6-Flash 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 51.3% 100 of 205 MiMo-V2.6-Flash 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 22.7% 63 of 204 MiMo-V2.6-Flash 20 Oct 2026
Artificial Analysis: Time to first answer tokenseconds, lower is better 47.4 112 of 137 MiMo-V2.6-Flash 20 Oct 2026

Not shown: Not business work, and a blend: read the parts for any one task.

Will MiMo-V2.6-Flash work for your product?

Benchmarks aren't your task. Paste the prompt your product uses and run it beside the models you could use instead, with every answer checked and costed.

New here? Your email starts a free trial. No credit card needed.