ResearchLLM Verifications Leaderboard

Data as of · 78 models, 80 questions · reviewed by Suhas Bhairav · methodology

Head to head · tested 27 Oct 2026

MiMo-V2.6-Flash vs MiMo-V2.6-Pro: accuracy, speed and price

Similar accuracy; MiMo-V2.6-Flash costs less per question.

XiaomiMiMo-V2.6-Flash62.5% score · #36$0.00056 per question77 tok/sXiaomiMiMo-V2.6-Pro68.8% score · #26$0.002 per question58 tok/s

Verdict

Built from the measurements below

  • Accuracy is too close to call: MiMo-V2.6-Flash scored 62.5% and MiMo-V2.6-Pro 68.8% on the same 80 questions, a gap within what chance alone could produce.
  • MiMo-V2.6-Flash is 3.5× cheaper per question as billed ($0.00056 vs $0.002), reasoning tokens included.
  • MiMo-V2.6-Flash generates text 1.3× faster: 77 tokens per second against 58.
  • MiMo-V2.6-Flash starts answering sooner: 0.4 s to the first token, against 0.7 s for MiMo-V2.6-Pro.

Which should you choose?

Choose MiMo-V2.6-Flash for the lower cost per correct answer ($0.0009 against $0.0029), faster streaming, a quicker first token and more hosts to choose from on OpenRouter (10 against 5).

Accuracy gap -6.3 points (z = -0.83). A winner is called only when z is at least 1.96, the usual 95% threshold. Speed, latency and price need a 10% margin.

Head to head

Same questions, same prompt, same API

MeasureMiMo-V2.6-FlashMiMo-V2.6-ProEdge
Verification scoreHigher is better62.5%68.8%Too close to call
Cost per questionLower is better$0.00056$0.002MiMo-V2.6-Flash
Output speedHigher is better7758MiMo-V2.6-Flash
Time to first tokenLower is better0.4 s0.7 sMiMo-V2.6-Flash
End-to-end response timeLower is better5.4 s7.9 sMiMo-V2.6-Flash
Tokens per questionLower is better1,8502,157MiMo-V2.6-Flash
Context windowHigher is better1.1M1.1MSimilar

Side by side

Bars are scaled to the larger of the two values. The winner on each measure is marked in bold.

Every measure

MiMo-V2.6-Flash first, MiMo-V2.6-Pro second

Verification scorehigher is better
MiMo-V2.6-Flash62.5%
MiMo-V2.6-Pro68.8%
Cost per questionlower is better
MiMo-V2.6-Flash$0.00056
MiMo-V2.6-Pro$0.002
Output speedhigher is better
MiMo-V2.6-Flash77
MiMo-V2.6-Pro58
Time to first tokenlower is better
MiMo-V2.6-Flash0.4 s
MiMo-V2.6-Pro0.7 s
End-to-end response timelower is better
MiMo-V2.6-Flash5.4 s
MiMo-V2.6-Pro7.9 s
Tokens per questionlower is better
MiMo-V2.6-Flash1,850
MiMo-V2.6-Pro2,157
Context windowhigher is better
MiMo-V2.6-Flash1.1M
MiMo-V2.6-Pro1.1M

Score vs. cost per question

Both models in color, every other model in grey

Most attractive quadrant0255075100$0.00001$0.0001$0.001$0.01$0.10Cost per question (USD, log) →Verification score (%) →Qwen3.8 2.4T A95BCommand AReka Flash 3Gemma 4 26B A4BGemma 4 31BQwen3.5 397B A17BHermes 4 405BMuse WonderGrok 4.7o3gpt-oss-20bMinistral 3 3B 2512Nova Micro 1.0Phi 4Granite 4.2 8BHy3GLM 5.3 FlashSolar Pro 4Trinity Large ThinkingMiniMax M3Mistral Large 4Claude Opus 5.5GPT-6.1 SolGemini 4 ArgonGPT-5.4GPT-6 Lunagpt-oss-120bLlama 4 Maverick

Specifications and pricing

From OpenRouter's catalogue, plus the leaderboard's test dates

SpecificationMiMo-V2.6-FlashMiMo-V2.6-Pro
CreatorXiaomiXiaomi
Released21 Sept 202621 Sept 2026
WeightsOpen weightsOpen weights
ReasoningYesYes
Inputtext, image, video, audiotext, image, video, audio
Outputtexttext
Context window1.1M tokens1.1M tokens
Knowledge cutoff——
List price in / out per 1M$0.14 / $0.28$0.435 / $0.87
Blended price per 1M (3:1)$0.18$0.54
Cheapest hostGMICloud · $0.119 / $0.238GMICloud · $0.36975 / $0.7395
Hosts on OpenRouter105
Last tested26 Oct 202625 Oct 2026

Compare any two models →

MiMo-V2.6-Flash vs MiMo-V2.6-Pro: frequently asked questions

Is MiMo-V2.6-Flash better than MiMo-V2.6-Pro?
On accuracy they are statistically tied: MiMo-V2.6-Flash scored 62.5% and MiMo-V2.6-Pro 68.8% on the same 80 questions from open datasets. Similar accuracy; MiMo-V2.6-Flash costs less per question.
Which is cheaper, MiMo-V2.6-Flash or MiMo-V2.6-Pro?
MiMo-V2.6-Flash is cheaper: $0.00056 per question as billed, against $0.002. List prices: MiMo-V2.6-Flash $0.14 in / $0.28 out, MiMo-V2.6-Pro $0.435 in / $0.87 out per million tokens.
Which is faster, MiMo-V2.6-Flash or MiMo-V2.6-Pro?
MiMo-V2.6-Flash is faster at 77 output tokens per second, against 58. Time to first token: 0.4 s for MiMo-V2.6-Flash, 0.7 s for MiMo-V2.6-Pro.
Which has the larger context window, MiMo-V2.6-Flash or MiMo-V2.6-Pro?
Both accept about the same amount of context: 1.1M and 1.1M tokens.