Qwen3.8 Max (0902) vs MiMo-V2.6-Pro
Updated October 21, 2026. 69 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick MiMo-V2.6-Pro for coding: it scores 72.6 on the Vibe Coding Index against 63.5 for Qwen3.8 Max (0902).
Pick Qwen3.8 Max (0902) when what matters is LMArena WebDev or Terminal-Bench 4 (Vals AI), where it leads.
- Shared results
- 69
- Qwen3.8 Max (0902) only
- 44
- MiMo-V2.6-Pro only
- 4
- Like-for-like categories
- 8 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
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, four public coding benchmarks
MiMo-V2.6-Pro
MiMo-V2.6-Pro scores 72.6 against 63.5.
2 benchmarks behind each score
Intelligence
AA Intelligence Index
MiMo-V2.6-Pro
MiMo-V2.6-Pro leads, 46.3 against 45.4.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Qwen3.8 Max (0902) has a AA Agentic Index result, 56.0.
Directional only
Reasoning
GPQA Diamond
No call
Only Qwen3.8 Max (0902) has a GPQA Diamond result, 93.7%.
Directional only
Knowledge
MMLU Pro
No call
Only Qwen3.8 Max (0902) has a MMLU Pro result, 88.6%.
Directional only
Web design
Design Arena: websites
MiMo-V2.6-Pro
MiMo-V2.6-Pro leads, 1308 against 1275.
Same board, both measured
General
Vals Index
No call
Only MiMo-V2.6-Pro has a Vals Index result, 57.8%.
Directional only
Long documents
Listed context window
MiMo-V2.6-Pro
MiMo-V2.6-Pro takes 1.05M tokens against 1M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiMo-V2.6-Pro
Qwen3.8 Max (0902) $0.0050, MiMo-V2.6-Pro $0.0009 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Qwen3.8 Max (0902) has the number, $1.32.
Directional only
At a glance
- Coding index
- Qwen3.8 Max (0902) 63.5 from 2 benchmarks, MiMo-V2.6-Pro 72.6 from 2 benchmarks.
- Widest category
- Coding, 10.3 points apart on average over 16 shared benchmarks.
- Widest single gap
- LiveBench browser: Qwen3.8 Max (0902) 32.0% against MiMo-V2.6-Pro 88.0%, 56.0 points apart on a 0 to 100 scale.
- Output price
- Qwen3.8 Max (0902) $6.00 against MiMo-V2.6-Pro $0.87 per million output tokens, 6.9x apart.
- Context window
- Qwen3.8 Max (0902) takes 1M tokens, MiMo-V2.6-Pro 1.05M.
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 | Qwen3.8 Max (0902) | Bars | MiMo-V2.6-Pro | Ties |
|---|---|---|---|---|
| Coding | 7 | 9 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 4 | 6 | ||
| Reasoning | 4 | 4 | ||
| Math | 1 | 2 | ||
| Knowledge | 4 | 1 | ||
| Web design | 3 | 4 | ||
| General | 10 | 9 | ||
| All shared boards | 33 | 36 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index79
| Benchmark | Qwen3.8 Max (0902) | MiMo-V2.6-Pro | Leader |
|---|---|---|---|
| LiveBench coding | 60.3% | 81.5% | MiMo-V2.6-Pro |
| LMArena WebDev | 1674 | 1625 | Qwen3.8 Max (0902) |
| AA Coding Index | 76.2 | Not measured | Only Qwen3.8 Max (0902) measured |
| LiveCodeBench (Vals AI) | 87.8% | Not measured | Only Qwen3.8 Max (0902) measured |
| SWE-bench Verified (Vals AI) | 85.6% | Not measured | Only Qwen3.8 Max (0902) measured |
| Terminal-Bench 4 (Vals AI) | 34.3% | 31.3% | Qwen3.8 Max (0902) |
| Vibe Code Bench (Vals AI) | 64.7% | 85.2% | MiMo-V2.6-Pro |
| Code migration (Vals AI) | 24.0% | 43.0% | MiMo-V2.6-Pro |
| ProgramBench (Vals AI) | 0.0% | 0.5% | MiMo-V2.6-Pro |
| IOI (Vals AI) | 68.9% | 39.3% | Qwen3.8 Max (0902) |
| Terminal-Bench 2.1 (Vals AI) | 67.4% | 67.8% | MiMo-V2.6-Pro |
| SWE-bench Multimodal (Vals AI) | 42.5% | 41.3% | Qwen3.8 Max (0902) |
| Vibe Code Bench 1-100 (Vals AI) | 12.8% | Not measured | Only Qwen3.8 Max (0902) measured |
| SkillsBench (Vals AI) | 42.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| CyberBench (Vals AI) | 28.6% | 72.9% | MiMo-V2.6-Pro |
| SciCode | 53.2% | 60.9% | MiMo-V2.6-Pro |
| FrontierSWE | 17.8% | Not measured | Only Qwen3.8 Max (0902) measured |
| ALE-Bench | Not measured | 1158.1 | Only MiMo-V2.6-Pro measured |
| LMArena Text: coding | 1502 | 1533 | MiMo-V2.6-Pro |
| LMArena Text: software and IT | 1498 | 1528 | MiMo-V2.6-Pro |
| LMArena WebDev: React | 1692 | 1639 | Qwen3.8 Max (0902) |
| LMArena WebDev: HTML | 1649 | 1616 | Qwen3.8 Max (0902) |
| LMArena WebDev: from an image | 1637 | 1598 | Qwen3.8 Max (0902) |
| Neither model has a result on the other 15 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Qwen3.8 Max (0902) | MiMo-V2.6-Pro | Leader |
|---|---|---|---|
| AA Intelligence Index | 45.4 | 46.3 | MiMo-V2.6-Pro |
| Epoch Capabilities Index | 157.4 | Not measured | Only Qwen3.8 Max (0902) measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index46
| Benchmark | Qwen3.8 Max (0902) | MiMo-V2.6-Pro | Leader |
|---|---|---|---|
| AA Agentic Index | 56.0 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: agents building web apps | 1301 | 1291 | Qwen3.8 Max (0902) |
| Design Arena: agents building full-stack apps | 1305 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: agents building mobile apps | 1223 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: agents building Android apps | 1207 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: agents building Godot games | 1234 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: PowerPoint slides | 1257 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: spreadsheets | 868 | Not measured | Only Qwen3.8 Max (0902) measured |
| LiveBench research | 69.9% | 76.7% | MiMo-V2.6-Pro |
| LiveBench browser | 32.0% | 88.0% | MiMo-V2.6-Pro |
| LiveBench long agentic | 42.3% | 47.5% | MiMo-V2.6-Pro |
| SREBench (Vals AI) | Not measured | 3.0% | Only MiMo-V2.6-Pro measured |
| Finance Agent (Vals AI) | 50.6% | 57.3% | MiMo-V2.6-Pro |
| Tax Agent Bench (Vals AI) | 32.1% | 32.4% | MiMo-V2.6-Pro |
| Legal Research Bench (Vals AI) | 47.6% | 47.1% | Qwen3.8 Max (0902) |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 13.8% | Only MiMo-V2.6-Pro measured |
| Excel Modeling Benchmark (Vals AI) | 60.1% | 62.9% | MiMo-V2.6-Pro |
| Terminal-Bench-Science (Vals AI) | 12.9% | 2.9% | Qwen3.8 Max (0902) |
| APEX-Agents | 63.3% | 54.4% | Qwen3.8 Max (0902) |
| LMArena Search | 1261 | Not measured | Only Qwen3.8 Max (0902) measured |
| Neither model has a result on the other 19 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index44
| Benchmark | Qwen3.8 Max (0902) | MiMo-V2.6-Pro | Leader |
|---|---|---|---|
| GPQA Diamond | 93.7% | Not measured | Only Qwen3.8 Max (0902) measured |
| LiveBench reasoning | 88.2% | 79.6% | Qwen3.8 Max (0902) |
| MysteryMechanism (Vals AI) | 23.9% | 15.3% | Qwen3.8 Max (0902) |
| MMMU Pro (Vals AI) | 88.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| GPQA Diamond (Artificial Analysis run) | 92.8% | Not measured | Only Qwen3.8 Max (0902) measured |
| Humanity's Last Exam (Artificial Analysis run) | 43.1% | 49.4% | MiMo-V2.6-Pro |
| GPQA Diamond (Epoch AI run) | 92.7% | Not measured | Only Qwen3.8 Max (0902) measured |
| Chess puzzles | 46.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| Mystery game puzzles | 38.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: hard prompts | 1496 | 1511 | MiMo-V2.6-Pro |
| LMArena Text: expert | 1507 | 1541 | MiMo-V2.6-Pro |
| LMArena Text: hard prompts in English | 1503 | 1520 | MiMo-V2.6-Pro |
| LMArena Vision: diagrams | 1323 | 1281 | Qwen3.8 Max (0902) |
| LMArena Vision: homework | 1336 | 1264 | Qwen3.8 Max (0902) |
| Neither model has a result on the other 7 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index12
| Benchmark | Qwen3.8 Max (0902) | MiMo-V2.6-Pro | Leader |
|---|---|---|---|
| OTIS Mock AIME | 100.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| FrontierMath, tiers 1 to 3 | 74.7% | Not measured | Only Qwen3.8 Max (0902) measured |
| FrontierMath, tier 4 | 46.3% | Not measured | Only Qwen3.8 Max (0902) measured |
| ProofBench | 58.0% | 70.0% | MiMo-V2.6-Pro |
| LMArena Text: math | 1501 | 1500 | Qwen3.8 Max (0902) |
| LMArena Text: mathematical work | 1491 | 1511 | MiMo-V2.6-Pro |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index41
| Benchmark | Qwen3.8 Max (0902) | MiMo-V2.6-Pro | Leader |
|---|---|---|---|
| MMLU Pro | 88.6% | Not measured | Only Qwen3.8 Max (0902) measured |
| LegalBench (Vals AI) | 83.6% | Not measured | Only Qwen3.8 Max (0902) measured |
| CorpFin (Vals AI) | 65.8% | Not measured | Only Qwen3.8 Max (0902) measured |
| TaxEval (Vals AI) | 75.5% | Not measured | Only Qwen3.8 Max (0902) measured |
| MortgageTax (Vals AI) | 64.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| MedCode (Vals AI) | 40.7% | 45.0% | MiMo-V2.6-Pro |
| SimpleQA Verified | 47.3% | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: science | 1512 | 1506 | Qwen3.8 Max (0902) |
| LMArena Text: medicine and healthcare | 1503 | 1497 | Qwen3.8 Max (0902) |
| LMArena Text: legal and government | 1492 | 1485 | Qwen3.8 Max (0902) |
| LMArena Text: business and finance | 1480 | 1468 | Qwen3.8 Max (0902) |
| Neither model has a result on the other 6 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index34
| Benchmark | Qwen3.8 Max (0902) | MiMo-V2.6-Pro | Leader |
|---|---|---|---|
| Design Arena: websites | 1275 | 1308 | MiMo-V2.6-Pro |
| Design Arena: UI components | 1340 | 1338 | Qwen3.8 Max (0902) |
| Design Arena: game dev | 1313 | 1314 | MiMo-V2.6-Pro |
| Design Arena: data viz | 1281 | 1337 | MiMo-V2.6-Pro |
| Design Arena: 3D | 1337 | 1330 | Qwen3.8 Max (0902) |
| Design Arena: all code categories | 1293 | 1317 | MiMo-V2.6-Pro |
| Design Arena: ASCII art | 1201 | Not measured | Only Qwen3.8 Max (0902) measured |
| LiveBench design | 78.6% | 78.5% | Qwen3.8 Max (0902) |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index109
| Benchmark | Qwen3.8 Max (0902) | MiMo-V2.6-Pro | Leader |
|---|---|---|---|
| Vals Index | Not measured | 57.8% | Only MiMo-V2.6-Pro measured |
| LiveBench data analysis | 78.4% | 72.3% | Qwen3.8 Max (0902) |
| Public Benefits Bench (Vals AI) | 67.1% | 68.9% | MiMo-V2.6-Pro |
| SAGE (Vals AI) | 51.2% | 45.0% | Qwen3.8 Max (0902) |
| MedScribe (Vals AI) | 85.0% | 88.3% | MiMo-V2.6-Pro |
| Vals Multimodal Index | 65.4% | Not measured | Only Qwen3.8 Max (0902) measured |
| Long context reasoning (AA-LCR) | 80.3% | 86.3% | MiMo-V2.6-Pro |
| DTBench | 92.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| LMCA | 46.2% | Not measured | Only Qwen3.8 Max (0902) measured |
| Furniture assembly | 20.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text | 1483 | 1491 | MiMo-V2.6-Pro |
| LMArena Text: instruction following | 1481 | 1491 | MiMo-V2.6-Pro |
| LMArena Text: creative writing | 1477 | 1466 | Qwen3.8 Max (0902) |
| LMArena Vision | 1313 | 1263 | Qwen3.8 Max (0902) |
| LMArena Text: English | 1491 | 1504 | MiMo-V2.6-Pro |
| LMArena Text: non-English | 1473 | 1474 | MiMo-V2.6-Pro |
| LMArena Text: Chinese | 1539 | 1529 | Qwen3.8 Max (0902) |
| LMArena Text: German | 1478 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: Japanese | 1473 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: Korean | 1460 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: French | 1498 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: Spanish | 1489 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: Russian | 1482 | 1479 | Qwen3.8 Max (0902) |
| LMArena Text: Polish | 1471 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: multi-turn | 1489 | 1466 | Qwen3.8 Max (0902) |
| LMArena Text: longer queries | 1488 | 1501 | MiMo-V2.6-Pro |
| LMArena Text: writing and language | 1477 | 1470 | Qwen3.8 Max (0902) |
| LMArena Text: entertainment and media | 1464 | 1465 | MiMo-V2.6-Pro |
| LMArena Vision: English | 1311 | 1268 | Qwen3.8 Max (0902) |
| LMArena Vision: Chinese | 1358 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Vision: reading text | 1322 | 1270 | Qwen3.8 Max (0902) |
| LMArena Vision: humor | 1304 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Vision: creative writing | 1312 | Not measured | Only Qwen3.8 Max (0902) measured |
| Neither model has a result on the other 13 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Qwen3.8 Max (0902) | MiMo-V2.6-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-V2.6-Pro costs less
Repository review
50K input + 3K output tokens
MiMo-V2.6-Pro costs less
Agent loop
200K input + 10K output tokens
MiMo-V2.6-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 | Qwen3.8 Max (0902) | Xiaomi MiMo-V2.6-Pro |
|---|---|---|
| Maker | Qwen | Xiaomi |
| Weights | No public weights listed | Open weights |
| Released | September 3, 2026 | September 21, 2026 |
| Context window | 1M | 1.05M |
| Input $/Mtok | $2.00 | $0.435 |
| Output $/Mtok | $6.00 | $0.87 |
| Coding index | 63.5 | 72.6 |
| Independent measurements behind it | 2 | 2 |
| Cost per solved task | $1.32 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Qwen3.8 Max (0902) better than MiMo-V2.6-Pro for coding?
Pick MiMo-V2.6-Pro for coding: it scores 72.6 on the Vibe Coding Index against 63.5 for Qwen3.8 Max (0902). Pick Qwen3.8 Max (0902) when what matters is LMArena WebDev or Terminal-Bench 4 (Vals AI), where it leads.
Which is cheaper, Qwen3.8 Max (0902) or MiMo-V2.6-Pro?
Qwen3.8 Max (0902) costs $2.00 per million input tokens and $6.00 per million output tokens; MiMo-V2.6-Pro costs $0.435 and $0.87. Cost per solved task is known for Qwen3.8 Max (0902) only.
Which has the bigger context window, Qwen3.8 Max (0902) or MiMo-V2.6-Pro?
MiMo-V2.6-Pro, with 1.05M tokens against 1M.
How many benchmarks is the Qwen3.8 Max (0902) vs MiMo-V2.6-Pro comparison based on?
69 benchmarks have a result for both models as of October 21, 2026. Qwen3.8 Max (0902)'s coding index rests on 2 independent benchmarks and MiMo-V2.6-Pro's on 2. Where only one model has a result, the page says so instead of naming a winner.