Compare / Qwen3-235B-A22B-Thinking-2507 vs MiMo-V2.6-Pro

Qwen3-235B-A22B-Thinking-2507 vs MiMo-V2.6-Pro

Which is cheaper, which is more capable, and which does better at each kind of work, from 11 results on 2 sources that measured both models.

AlibabaQwen3-235B-A22B-Thinking-2507 Released 25 Jul 2025 · $0.45 in · $3.50 out
XiaomiMiMo-V2.6-Pro Released 21 Sep 2026 · $0.43 in · $0.87 out
Qwen3-235B-A22B-Thinking-2507 wins 0MiMo-V2.6-Pro wins 11

Of the 11 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 Alibaba vs Xiaomi, every model from both labs.

Qwen3-235B-A22B-Thinking-2507 or MiMo-V2.6-Pro? The short answer

Pick MiMo-V2.6-Pro: it scores higher (Intelligence Index 46.3 against 12.7) and costs less.

  • MiMo-V2.6-Pro is cheaper: $0.54 against $1.21 per million tokens, 2.2 times less.
  • MiMo-V2.6-Pro scores higher on the Artificial Analysis Intelligence Index: 46.3 against 12.7.
  • MiMo-V2.6-Pro is newer: released 21 Sep 2026, against 25 Jul 2025 for Qwen3-235B-A22B-Thinking-2507.
  • On third-party benchmarks, on the results both models have: MiMo-V2.6-Pro does better for agents and tool use, reasoning and knowledge and writing.

Head to head

12.7
Intelligence Index
46.3
$1.21
Price per million tokens, blendedlower is better
$0.54
128,000
Context window, tokens
1,050,000

Every fact side by side

Qwen3-235B-A22B-Thinking-2507MiMo-V2.6-Pro
Price per million tokens$0.45 in · $3.50 out$0.43 in · $0.87 out
Blended (3 in : 1 out)$1.21$0.54
Cheapest host, blended–$0.41 (GMICloud, BF16)
Cached input, per million–$0.004 cached input
Intelligence Index12.746.3
Spring Prompt overall––
Output speed, tokens a second–43
Context window128,000 tokens1,050,000 tokens
Released25 Jul 202521 Sep 2026 (newer)
WeightsOpenOpen
Developer based inChinaChina

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.

Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 139 of 159 23 of 159
Reasoning and knowledgeHard questions across science, maths and general knowledge 119 of 187 13 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 119 of 169 23 of 169
Sticking to the factsSummarising without inventing things, and factual answers 83 of 139 10 of 139

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.

MeasureQwen3-235B-A22B-Thinking-2507MiMo-V2.6-Pro
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 139 · 23 of 387 measured 1,400 1,480
Business, management and finance · TextArena rating, higher is better 133 · 50 of 380 measured 1,404 1,461
Creative writing · TextArena rating, higher is better 133 · 38 of 385 measured 1,371 1,446
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 152 · 14 of 249 measured 12.7 46.3
Humanity's Last Exam% of questions, higher is better 130 · 12 of 250 measured 15.9% 49.4%
Terminal-Bench 4.0% of tasks, higher is better 72 · 17 of 120 measured 0.0% 34.8%
Show all 11 results (5 more)
MeasureQwen3-235B-A22B-Thinking-2507MiMo-V2.6-Pro
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Expert prompts · TextArena rating, higher is better 85 · 11 of 338 measured 1,466 1,532
Instruction following · TextArena rating, higher is better 142 · 23 of 387 measured 1,385 1,474
Writing, literature and language · TextArena rating, higher is better 139 · 32 of 386 measured 1,377 1,459
Artificial Analysis reported by Artificial Analysis · 2 results
Long-context reasoning (AA-LCR)% of questions, higher is better 105 · 2 of 241 measured 72.0% 86.3%
SciCode% of problems, higher is better 82 · 6 of 121 measured 41.4% 60.9%

Quick answers

Is Qwen3-235B-A22B-Thinking-2507 better than MiMo-V2.6-Pro?

Pick MiMo-V2.6-Pro: it scores higher (Intelligence Index 46.3 against 12.7) and costs less.

Which is cheaper, Qwen3-235B-A22B-Thinking-2507 or MiMo-V2.6-Pro?

MiMo-V2.6-Pro is cheaper: $0.54 against $1.21 per million tokens, 2.2 times less.

Which is better for agents and tool use, Qwen3-235B-A22B-Thinking-2507 or MiMo-V2.6-Pro?

MiMo-V2.6-Pro ranks 23 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 139 for Qwen3-235B-A22B-Thinking-2507.

Which is better for reasoning and knowledge, Qwen3-235B-A22B-Thinking-2507 or MiMo-V2.6-Pro?

MiMo-V2.6-Pro ranks 13 of 187 models on sale for hard questions across science, maths and general knowledge, against 119 for Qwen3-235B-A22B-Thinking-2507.

Which is better for writing, Qwen3-235B-A22B-Thinking-2507 or MiMo-V2.6-Pro?

MiMo-V2.6-Pro ranks 23 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 119 for Qwen3-235B-A22B-Thinking-2507.

Which is better for sticking to the facts, Qwen3-235B-A22B-Thinking-2507 or MiMo-V2.6-Pro?

MiMo-V2.6-Pro ranks 10 of 139 models on sale for summarising without inventing things, and factual answers, against 83 for Qwen3-235B-A22B-Thinking-2507.

Which has the bigger context window, Qwen3-235B-A22B-Thinking-2507 or MiMo-V2.6-Pro?

MiMo-V2.6-Pro: 1,050,000 tokens, against 128,000 for Qwen3-235B-A22B-Thinking-2507.

Run Qwen3-235B-A22B-Thinking-2507 and MiMo-V2.6-Pro 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.