Qwen4 Max vs MiMo-V2.5-Pro
Qwen4 Max leads MiMo-V2.5-Pro on coding, 74.0 to 31.5 on the Vibe Coding Index, and MiMo-V2.5-Pro costs 2.4x less per output token ($1.80 vs $4.275 per million). Updated November 22, 2026; 11 benchmarks have a result for both.
Qwen4 Max or MiMo-V2.5-Pro: which to pick
Pick Qwen4 Max for coding: it scores 74.0 on the Vibe Coding Index against 31.5 for MiMo-V2.5-Pro.
Pick MiMo-V2.5-Pro for output tokens 2.4x cheaper ($1.80 vs $4.275 per million).
- Shared results
- 11
- Qwen4 Max only
- 15
- MiMo-V2.5-Pro only
- 60
- Like-for-like categories
- 3 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
Qwen4 Max
Qwen4 Max scores 74.0 against 31.5.
4 benchmarks behind each score
Intelligence
AA Intelligence Index
No call
Only Qwen4 Max has a AA Intelligence Index result, 42.9.
Directional only
Reasoning
GPQA Diamond
No call
Only MiMo-V2.5-Pro has a GPQA Diamond result, 82.6%.
Directional only
Knowledge
MMLU Pro
No call
Only MiMo-V2.5-Pro has a MMLU Pro result, 84.6%.
Directional only
Web design
Design Arena: websites
No call
Only MiMo-V2.5-Pro has a Design Arena: websites result, 1258.
Directional only
General
Vals Index
No call
Only Qwen4 Max has a Vals Index result, 63.2%.
Directional only
Long documents
Listed context window
Qwen4 Max
Qwen4 Max takes 1M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiMo-V2.5-Pro
Qwen4 Max $0.0036, MiMo-V2.5-Pro $0.0014 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only MiMo-V2.5-Pro has the number, $0.03.
Directional only
At a glance
- Coding index
- Qwen4 Max 74.0 from 4 benchmarks, MiMo-V2.5-Pro 31.5 from 4 benchmarks.
- Widest category
- General, 56.7 points apart on average over 1 shared benchmark.
- Widest single gap
- Terminal-Bench 4 (Vals AI): Qwen4 Max 48.5% against MiMo-V2.5-Pro 0.5%, 64.0 points apart on a 0 to 100 scale.
- Output price
- Qwen4 Max $4.275 against MiMo-V2.5-Pro $1.80 per million output tokens, 2.4x apart.
- Context window
- Qwen4 Max takes 1M tokens, MiMo-V2.5-Pro 262K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Qwen4 Max | Bars | MiMo-V2.5-Pro | Ties |
|---|---|---|---|---|
| Coding | 8 | 0 | ||
| Agentic work | 2 | 0 | ||
| General | 1 | 0 | ||
| All shared boards | 11 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index80
| Benchmark | Qwen4 Max | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| LiveBench coding | 69.8% | Not measured | Only Qwen4 Max measured |
| LMArena WebDev | 1751 | 1479 | Qwen4 Max |
| LiveCodeBench (Vals AI) | Not measured | 81.3% | Only MiMo-V2.5-Pro measured |
| SWE-bench Verified (Vals AI) | Not measured | 74.0% | Only MiMo-V2.5-Pro measured |
| Terminal-Bench 4 (Vals AI) | 48.5% | 0.5% | Qwen4 Max |
| Vibe Code Bench (Vals AI) | 86.7% | 34.1% | Qwen4 Max |
| Code migration (Vals AI) | Not measured | 21.6% | Only MiMo-V2.5-Pro measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 57.3% | Only MiMo-V2.5-Pro measured |
| SciCode | Not measured | 50.6% | Only MiMo-V2.5-Pro measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 43.2% | Only MiMo-V2.5-Pro measured |
| Terminal-Bench 4.0 (Artificial Analysis run) | 48.5% | 0.0% | Qwen4 Max |
| FrontierCode 2.0 | 26.5% | Not measured | Only Qwen4 Max measured |
| ALE-Bench | 1831.0 | 899.8 | Qwen4 Max |
| LMArena Text: coding | Not measured | 1500 | Only MiMo-V2.5-Pro measured |
| LMArena Text: software and IT | Not measured | 1494 | Only MiMo-V2.5-Pro measured |
| LMArena WebDev: React | 1785 | 1468 | Qwen4 Max |
| LMArena WebDev: HTML | 1752 | 1470 | Qwen4 Max |
| LMArena WebDev: from an image | 1675 | Not measured | Only Qwen4 Max measured |
| GameBench 2 | 82.4 | 37.5 | Qwen4 Max |
| Neither model has a result on the other 33 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Qwen4 Max | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| AA Intelligence Index | 42.9 | Not measured | Only Qwen4 Max measured |
| Neither model has a result on the other 1 board here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Qwen4 Max | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| LiveBench research | 84.7% | Not measured | Only Qwen4 Max measured |
| LiveBench browser | 80.7% | Not measured | Only Qwen4 Max measured |
| LiveBench long agentic | 46.6% | Not measured | Only Qwen4 Max measured |
| Finance Agent (Vals AI) | Not measured | 41.5% | Only MiMo-V2.5-Pro measured |
| Tax Agent Bench (Vals AI) | 40.4% | 11.5% | Qwen4 Max |
| Legal Research Bench (Vals AI) | 41.4% | 15.9% | Qwen4 Max |
| Harvey's Legal Agent Benchmark (Vals AI) | 21.3% | Not measured | Only Qwen4 Max measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 55.2% | Only MiMo-V2.5-Pro measured |
| τ²-Bench Telecom | Not measured | 94.2% | Only MiMo-V2.5-Pro measured |
| Neither model has a result on the other 35 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | Qwen4 Max | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 82.6% | Only MiMo-V2.5-Pro measured |
| LiveBench reasoning | 92.2% | Not measured | Only Qwen4 Max measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 86.6% | Only MiMo-V2.5-Pro measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 35.7% | Only MiMo-V2.5-Pro measured |
| HLE-Diamond (Artificial Analysis run) | 44.9% | Not measured | Only Qwen4 Max measured |
| CritPt v2, hard subset (Artificial Analysis run) | 43.0% | Not measured | Only Qwen4 Max measured |
| LMArena Text: hard prompts | Not measured | 1485 | Only MiMo-V2.5-Pro measured |
| LMArena Text: expert | Not measured | 1501 | Only MiMo-V2.5-Pro measured |
| LMArena Text: hard prompts in English | Not measured | 1494 | Only MiMo-V2.5-Pro measured |
| Neither model has a result on the other 17 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | Qwen4 Max | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| ProofBench | Not measured | 22.0% | Only MiMo-V2.5-Pro measured |
| LMArena Text: math | Not measured | 1480 | Only MiMo-V2.5-Pro measured |
| LMArena Text: mathematical work | Not measured | 1492 | Only MiMo-V2.5-Pro measured |
| Neither model has a result on the other 11 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index10 boards, none shared
| Benchmark | Qwen4 Max | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 84.6% | Only MiMo-V2.5-Pro measured |
| LegalBench (Vals AI) | Not measured | 77.1% | Only MiMo-V2.5-Pro measured |
| CorpFin (Vals AI) | Not measured | 61.4% | Only MiMo-V2.5-Pro measured |
| TaxEval (Vals AI) | Not measured | 73.8% | Only MiMo-V2.5-Pro measured |
| MedCode (Vals AI) | Not measured | 32.5% | Only MiMo-V2.5-Pro measured |
| AA-Omniscience | 27.7 | Not measured | Only Qwen4 Max measured |
| LMArena Text: science | Not measured | 1482 | Only MiMo-V2.5-Pro measured |
| LMArena Text: medicine and healthcare | Not measured | 1472 | Only MiMo-V2.5-Pro measured |
| LMArena Text: legal and government | Not measured | 1475 | Only MiMo-V2.5-Pro measured |
| LMArena Text: business and finance | Not measured | 1467 | Only MiMo-V2.5-Pro measured |
| Neither model has a result on the other 11 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | Qwen4 Max | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1258 | Only MiMo-V2.5-Pro measured |
| Design Arena: UI components | Not measured | 1239 | Only MiMo-V2.5-Pro measured |
| Design Arena: game dev | Not measured | 1250 | Only MiMo-V2.5-Pro measured |
| Design Arena: data viz | Not measured | 1255 | Only MiMo-V2.5-Pro measured |
| Design Arena: 3D | Not measured | 1221 | Only MiMo-V2.5-Pro measured |
| Design Arena: all code categories | Not measured | 1255 | Only MiMo-V2.5-Pro measured |
| Design Arena: SVG | Not measured | 1180 | Only MiMo-V2.5-Pro measured |
| Design Arena: ASCII art | Not measured | 1144 | Only MiMo-V2.5-Pro measured |
| LiveBench design | 79.1% | Not measured | Only Qwen4 Max measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Qwen4 Max | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| Vals Index | 63.2% | Not measured | Only Qwen4 Max measured |
| LiveBench data analysis | 83.4% | Not measured | Only Qwen4 Max measured |
| MedScribe (Vals AI) | Not measured | 83.7% | Only MiMo-V2.5-Pro measured |
| IFBench | Not measured | 79.9% | Only MiMo-V2.5-Pro measured |
| Long context reasoning (AA-LCR) | Not measured | 79.7% | Only MiMo-V2.5-Pro measured |
| GDPval-AA | 1809 | 1128 | Qwen4 Max |
| DTBench | Not measured | 84.5% | Only MiMo-V2.5-Pro measured |
| LMCA | Not measured | 29.5% | Only MiMo-V2.5-Pro measured |
| LMArena Text | Not measured | 1464 | Only MiMo-V2.5-Pro measured |
| LMArena Text: instruction following | Not measured | 1476 | Only MiMo-V2.5-Pro measured |
| LMArena Text: creative writing | Not measured | 1437 | Only MiMo-V2.5-Pro measured |
| LMArena Text: English | Not measured | 1477 | Only MiMo-V2.5-Pro measured |
| LMArena Text: non-English | Not measured | 1448 | Only MiMo-V2.5-Pro measured |
| LMArena Text: Chinese | Not measured | 1507 | Only MiMo-V2.5-Pro measured |
| LMArena Text: German | Not measured | 1457 | Only MiMo-V2.5-Pro measured |
| LMArena Text: Japanese | Not measured | 1410 | Only MiMo-V2.5-Pro measured |
| LMArena Text: Korean | Not measured | 1439 | Only MiMo-V2.5-Pro measured |
| LMArena Text: French | Not measured | 1488 | Only MiMo-V2.5-Pro measured |
| LMArena Text: Spanish | Not measured | 1470 | Only MiMo-V2.5-Pro measured |
| LMArena Text: Russian | Not measured | 1450 | Only MiMo-V2.5-Pro measured |
| LMArena Text: Polish | Not measured | 1461 | Only MiMo-V2.5-Pro measured |
| LMArena Text: multi-turn | Not measured | 1475 | Only MiMo-V2.5-Pro measured |
| LMArena Text: longer queries | Not measured | 1481 | Only MiMo-V2.5-Pro measured |
| LMArena Text: writing and language | Not measured | 1451 | Only MiMo-V2.5-Pro measured |
| LMArena Text: entertainment and media | Not measured | 1437 | Only MiMo-V2.5-Pro measured |
| EQ-Bench 4 | Not measured | 1198 | Only MiMo-V2.5-Pro measured |
| Neither model has a result on the other 23 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Qwen4 Max | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
MiMo-V2.5-Pro costs less
Repository review
50K input + 3K output tokens
MiMo-V2.5-Pro costs less
Agent loop
200K input + 10K output tokens
MiMo-V2.5-Pro costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Qwen4 Max | Xiaomi MiMo-V2.5-Pro |
|---|---|---|
| Maker | Qwen | Xiaomi |
| Weights | No public weights listed | Open weights |
| Released | November 16, 2026 | April 22, 2026 |
| Context window | 1M | 262K |
| Input $/Mtok | $1.425 | $0.48 |
| Output $/Mtok | $4.275 | $1.80 |
| Coding index | 74.0 | 31.5 |
| Independent measurements behind it | 4 | 4 |
| Cost per solved task | Not computable | $0.03 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Qwen4 Max better than MiMo-V2.5-Pro for coding?
Pick Qwen4 Max for coding: it scores 74.0 on the Vibe Coding Index against 31.5 for MiMo-V2.5-Pro. Pick MiMo-V2.5-Pro for output tokens 2.4x cheaper ($1.80 vs $4.275 per million).
Which is cheaper, Qwen4 Max or MiMo-V2.5-Pro?
Qwen4 Max costs $1.425 per million input tokens and $4.275 per million output tokens; MiMo-V2.5-Pro costs $0.48 and $1.80. Cost per solved task is known for MiMo-V2.5-Pro only.
Which has the bigger context window, Qwen4 Max or MiMo-V2.5-Pro?
Qwen4 Max, with 1M tokens against 262K.
How many benchmarks is the Qwen4 Max vs MiMo-V2.5-Pro comparison based on?
11 benchmarks have a result for both models as of November 22, 2026. Qwen4 Max's coding index rests on 4 independent benchmarks and MiMo-V2.5-Pro's on 4. Where only one model has a result, the page says so instead of naming a winner.