Compare / GPT-6 Luna vs MiMo-V2.6-Flash

GPT-6 Luna vs MiMo-V2.6-Flash

Which is cheaper, which is more capable, and which does better at each kind of work, from 18 results on 2 sources that measured both models.

OpenAIGPT-6 Luna Released 22 Sep 2026 · $0.10 in · $0.50 out
XiaomiMiMo-V2.6-Flash Released 21 Sep 2026 · $0.14 in · $0.28 out
GPT-6 Luna wins 87 too close to callMiMo-V2.6-Flash wins 3

Of the 18 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 16 November 2026 (catalogue release 2026-11-16-49bdfa045dee). See also OpenAI vs Xiaomi, every model from both labs.

GPT-6 Luna or MiMo-V2.6-Flash? The short answer

They score and cost about the same; GPT-6 Luna writes faster. Pick on the results below that match your work.

  • They cost about the same: $0.20 and $0.18 per million tokens (three input to one output).
  • They score about the same on the Artificial Analysis Intelligence Index (38.1 and 37.9).
  • GPT-6 Luna writes faster: 127 tokens a second against 46.
  • GPT-6 Luna is newer: released 22 Sep 2026, against 21 Sep 2026 for MiMo-V2.6-Flash.
  • On third-party benchmarks, on the results both models have: GPT-6 Luna does better for reasoning and knowledge; MiMo-V2.6-Flash for agents and tool use and sticking to the facts.

Head to head

38.1
Intelligence Index
37.9
$0.20
Price per million tokens, blendedlower is better
$0.18
127
Output speed, tokens a second
46
1,050,000
Context window, tokens
1,050,000

Every fact side by side

GPT-6 LunaMiMo-V2.6-Flash
Price per million tokens$0.10 in · $0.50 out$0.14 in · $0.28 out
Blended (3 in : 1 out)$0.20$0.18
Cheapest host, blended$0.20 (Amazon Bedrock)$0.14 (GMICloud, BF16)
Cached input, per million$0.010 cached input$0.003 cached input
Intelligence Index38.137.9
Spring Prompt overall39–
Output speed, tokens a second12746
Context window1,050,000 tokens1,050,000 tokens
Released22 Sep 2026 (newer)21 Sep 2026
WeightsClosedOpen
Developer based inthe USChina

Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.

Which is better for what

Each model's rank among the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.

Product listingsTurning a sparse product feed and photos into listings that can go live 7 of 32 not measured
Decks from an analysisTurning a finished analysis into a deck you could present as it is 10 of 32 not measured
User surveysPlanning a user survey and reading its results without being misled 12 of 23 not measured
Marketing planningPlanning a year of ad spend without overspending 6 of 32 not measured
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 53 of 159 42 of 159
Professional workReal tasks from banking, consulting and law, business documents and freelance projects 25 of 51 not measured
Reasoning and knowledgeHard questions across science, maths and general knowledge 48 of 187 55 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 61 of 169 56 of 169
Sticking to the factsSummarising without inventing things, and factual answers 89 of 139 46 of 139
Speed under pressureGood decisions against a real clock (fast chess) 24 of 35 36 of 36

From our research

Every shared result

Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.

MeasureGPT-6 LunaMiMo-V2.6-Flash
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 78 · 66 of 387 measured 1,443max reasoning 1,452
Overall · Text factualityArena rating, higher is better 98 · 43 of 163 measured 1,430max reasoning 1,457
Business, management and finance · TextArena rating, higher is better 71 · 56 of 380 measured 1,447max reasoning 1,459
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 39 · 40 of 249 measured 38.1max reasoning 37.9
Humanity's Last Exam% of questions, higher is better 53 · 64 of 250 measured 38.5%max reasoning 35.1%
Terminal-Bench 4.0% of tasks, higher is better 37 · 27 of 120 measured 12.6%max reasoning 22.7%
Show all 18 results (12 more)
MeasureGPT-6 LunaMiMo-V2.6-Flash
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 8 results
Confirmed task success · AgentIPS effect estimate, higher is better 29 · 14 of 48 measured -0.00max reasoning, arena agent 0.06arena agent
Creative writing · TextArena rating, higher is better 77 · 113 of 385 measured 1,413max reasoning 1,385
Expert prompts · TextArena rating, higher is better 40 · 25 of 338 measured 1,498max reasoning 1,509
Instruction following · TextArena rating, higher is better 57 · 48 of 387 measured 1,448max reasoning 1,453
Praise over complaint · AgentIPS effect estimate, higher is better 30 · 27 of 48 measured -0.02max reasoning, arena agent -0.01arena agent
Steerability · AgentIPS effect estimate, higher is better 16 · 32 of 48 measured 0.04max reasoning, arena agent -0.00arena agent
Tool grounding · AgentIPS effect estimate, higher is better 39 · 48 of 48 measured -0.00max reasoning, arena agent -0.04arena agent
Writing, literature and language · TextArena rating, higher is better 79 · 82 of 386 measured 1,421max reasoning 1,419
Artificial Analysis reported by Artificial Analysis · 4 results
Long-context reasoning (AA-LCR)% of questions, higher is better 13 · 89 of 241 measured 83.3%max reasoning 74.3%
Output speedtokens per second, higher is better 37 · 71 of 78 measured 127max reasoning 46.2
SciCode% of problems, higher is better 31 · 47 of 121 measured 54.6%max reasoning 51.3%
Time to first answer tokenseconds, lower is better 20 · 73 of 78 measured 0.74no reasoning 47.4

Quick answers

Is GPT-6 Luna better than MiMo-V2.6-Flash?

They score and cost about the same; GPT-6 Luna writes faster. Pick on the results below that match your work.

Which is cheaper, GPT-6 Luna or MiMo-V2.6-Flash?

They cost about the same: $0.20 and $0.18 per million tokens (three input to one output).

Which is faster, GPT-6 Luna or MiMo-V2.6-Flash?

GPT-6 Luna writes about 127 tokens a second on its usual API, against 46 for MiMo-V2.6-Flash (Artificial Analysis).

Which is better for agents and tool use, GPT-6 Luna or MiMo-V2.6-Flash?

MiMo-V2.6-Flash ranks 42 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 53 for GPT-6 Luna.

Which is better for reasoning and knowledge, GPT-6 Luna or MiMo-V2.6-Flash?

GPT-6 Luna ranks 48 of 187 models on sale for hard questions across science, maths and general knowledge, against 55 for MiMo-V2.6-Flash.

Which is better for writing, GPT-6 Luna or MiMo-V2.6-Flash?

MiMo-V2.6-Flash ranks 56 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 61 for GPT-6 Luna.

Which is better for sticking to the facts, GPT-6 Luna or MiMo-V2.6-Flash?

MiMo-V2.6-Flash ranks 46 of 139 models on sale for summarising without inventing things, and factual answers, against 89 for GPT-6 Luna.

Run GPT-6 Luna and MiMo-V2.6-Flash on your own prompt.

Benchmarks aren't your task. Test both side by side on your prompt, with every answer checked against your rules and the cost of each one.