Qwen3 235B A22B Thinking 2507 vs MiMo-V2.5
MiMo-V2.5 leads Qwen3 235B A22B Thinking 2507 on the Artificial Analysis Intelligence Index, 21.8 to 12.7, and MiMo-V2.5 costs 10.4x less per output token ($0.336 vs $3.50 per million). Updated October 22, 2026; 36 benchmarks have a result for both.
Qwen3 235B A22B Thinking 2507 or MiMo-V2.5: which to pick
Only MiMo-V2.5 has a coding score, 50.0 on the Vibe Coding Index; Qwen3 235B A22B Thinking 2507 has none, so the two cannot be ranked on coding.
Pick Qwen3 235B A22B Thinking 2507 for work measured by LMArena Text: expert or LMArena Text: medicine and healthcare, where it leads.
- Shared results
- 36
- Qwen3 235B A22B Thinking 2507 only
- 10
- MiMo-V2.5 only
- 44
- Like-for-like categories
- 8 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
No call
Only MiMo-V2.5 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
MiMo-V2.5
MiMo-V2.5 leads, 21.8 against 12.7.
Same board, both measured
Agentic work
AA Agentic Index
MiMo-V2.5
MiMo-V2.5 leads, 15.8 against 1.3.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only MiMo-V2.5 has a GPQA Diamond result, 81.6%.
Directional only
Knowledge
MMLU Pro
No call
Only MiMo-V2.5 has a MMLU Pro result, 82.9%.
Directional only
Web design
Design Arena: websites
MiMo-V2.5
MiMo-V2.5 leads, 1266 against 1052.
Same board, both measured
Long documents
Listed context window
MiMo-V2.5
MiMo-V2.5 takes 1.05M tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiMo-V2.5
Qwen3 235B A22B Thinking 2507 $0.0022, MiMo-V2.5 $0.0003 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only MiMo-V2.5 has the number, $0.01.
Directional only
At a glance
- Coding index
- Qwen3 235B A22B Thinking 2507 not benchmarked, MiMo-V2.5 50.0 from 3 benchmarks.
- Widest category
- Web design, 32.6 points apart on average over 6 shared benchmarks.
- Widest single gap
- Design Arena: UI components: Qwen3 235B A22B Thinking 2507 942 against MiMo-V2.5 1255, 39.1 points apart on a 0 to 100 scale.
- Output price
- Qwen3 235B A22B Thinking 2507 $3.50 against MiMo-V2.5 $0.336 per million output tokens, 10.4x apart.
- Context window
- Qwen3 235B A22B Thinking 2507 takes 128K tokens, MiMo-V2.5 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 235B A22B Thinking 2507 | Bars | MiMo-V2.5 | Ties |
|---|---|---|---|---|
| Coding | 0 | 3 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 1 | 2 | ||
| Math | 0 | 2 | ||
| Knowledge | 1 | 3 | ||
| Web design | 0 | 6 | ||
| General | 4 | 12 | ||
| All shared boards | 6 | 30 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
| Benchmark | Qwen3 235B A22B Thinking 2507 | MiMo-V2.5 | Leader |
|---|---|---|---|
| LMArena WebDev | Not measured | 1438 | Only MiMo-V2.5 measured |
| AA Coding Index | 22.1 | 56.8 | MiMo-V2.5 |
| LiveCodeBench (Vals AI) | Not measured | 81.5% | Only MiMo-V2.5 measured |
| SWE-bench Verified (Vals AI) | Not measured | 71.0% | Only MiMo-V2.5 measured |
| Vibe Code Bench (Vals AI) | Not measured | 42.2% | Only MiMo-V2.5 measured |
| Code migration (Vals AI) | Not measured | 14.2% | Only MiMo-V2.5 measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 60.7% | Only MiMo-V2.5 measured |
| SciCode | Not measured | 43.9% | Only MiMo-V2.5 measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 41.7% | Only MiMo-V2.5 measured |
| WeirdML | 41.0% | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| ALE-Bench | Not measured | 514.0 | Only MiMo-V2.5 measured |
| LMArena Text: coding | 1424 | 1469 | MiMo-V2.5 |
| LMArena Text: software and IT | 1431 | 1463 | MiMo-V2.5 |
| LMArena WebDev: React | Not measured | 1425 | Only MiMo-V2.5 measured |
| LMArena WebDev: HTML | Not measured | 1429 | Only MiMo-V2.5 measured |
| Neither model has a result on the other 28 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Qwen3 235B A22B Thinking 2507 | MiMo-V2.5 | Leader |
|---|---|---|---|
| AA Intelligence Index | 12.7 | 21.8 | MiMo-V2.5 |
| Neither model has a result on the other 1 board here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Qwen3 235B A22B Thinking 2507 | MiMo-V2.5 | Leader |
|---|---|---|---|
| AA Agentic Index | 1.3 | 15.8 | MiMo-V2.5 |
| Finance Agent (Vals AI) | Not measured | 36.7% | Only MiMo-V2.5 measured |
| Tax Agent Bench (Vals AI) | Not measured | 7.8% | Only MiMo-V2.5 measured |
| Legal Research Bench (Vals AI) | Not measured | 9.1% | Only MiMo-V2.5 measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 55.1% | Only MiMo-V2.5 measured |
| τ²-Bench Telecom | Not measured | 90.6% | Only MiMo-V2.5 measured |
| Vending-Bench 2 | -$11 | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| Neither model has a result on the other 35 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index12
| Benchmark | Qwen3 235B A22B Thinking 2507 | MiMo-V2.5 | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 81.6% | Only MiMo-V2.5 measured |
| MMMU Pro (Vals AI) | Not measured | 80.0% | Only MiMo-V2.5 measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 84.9% | Only MiMo-V2.5 measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 27.2% | Only MiMo-V2.5 measured |
| GPQA Diamond (Epoch AI run) | 80.1% | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| Mystery game puzzles | 9.0% | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: hard prompts | 1416 | 1450 | MiMo-V2.5 |
| LMArena Text: expert | 1463 | 1459 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: hard prompts in English | 1432 | 1461 | MiMo-V2.5 |
| LMArena Vision: diagrams | Not measured | 1269 | Only MiMo-V2.5 measured |
| LMArena Vision: homework | Not measured | 1262 | Only MiMo-V2.5 measured |
| Neither model has a result on the other 12 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Qwen3 235B A22B Thinking 2507 | MiMo-V2.5 | Leader |
|---|---|---|---|
| OTIS Mock AIME | 86.7% | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| ProofBench | Not measured | 16.0% | Only MiMo-V2.5 measured |
| LMArena Text: math | 1412 | 1436 | MiMo-V2.5 |
| LMArena Text: mathematical work | 1435 | 1451 | MiMo-V2.5 |
| Neither model has a result on the other 10 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index13
| Benchmark | Qwen3 235B A22B Thinking 2507 | MiMo-V2.5 | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 82.9% | Only MiMo-V2.5 measured |
| LegalBench (Vals AI) | Not measured | 78.9% | Only MiMo-V2.5 measured |
| CorpFin (Vals AI) | Not measured | 59.9% | Only MiMo-V2.5 measured |
| TaxEval (Vals AI) | Not measured | 71.8% | Only MiMo-V2.5 measured |
| MortgageTax (Vals AI) | Not measured | 59.3% | Only MiMo-V2.5 measured |
| MedCode (Vals AI) | Not measured | 31.9% | Only MiMo-V2.5 measured |
| SimpleQA Verified | 40.4% | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: science | 1433 | 1440 | MiMo-V2.5 |
| LMArena Text: medicine and healthcare | 1456 | 1432 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: legal and government | 1415 | 1425 | MiMo-V2.5 |
| LMArena Text: business and finance | 1413 | 1432 | MiMo-V2.5 |
| Neither model has a result on the other 9 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | Qwen3 235B A22B Thinking 2507 | MiMo-V2.5 | Leader |
|---|---|---|---|
| Design Arena: websites | 1052 | 1266 | MiMo-V2.5 |
| Design Arena: UI components | 942 | 1255 | MiMo-V2.5 |
| Design Arena: game dev | 956 | 1249 | MiMo-V2.5 |
| Design Arena: data viz | 950 | 1250 | MiMo-V2.5 |
| Design Arena: 3D | 997 | 1215 | MiMo-V2.5 |
| Design Arena: all code categories | 1032 | 1260 | MiMo-V2.5 |
| Design Arena: SVG | Not measured | 1180 | Only MiMo-V2.5 measured |
| Design Arena: ASCII art | Not measured | 1140 | Only MiMo-V2.5 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index412
| Benchmark | Qwen3 235B A22B Thinking 2507 | MiMo-V2.5 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | Not measured | 43.3% | Only MiMo-V2.5 measured |
| MedScribe (Vals AI) | Not measured | 72.2% | Only MiMo-V2.5 measured |
| Vals Multimodal Index | Not measured | 52.8% | Only MiMo-V2.5 measured |
| IFBench | Not measured | 67.1% | Only MiMo-V2.5 measured |
| Long context reasoning (AA-LCR) | Not measured | 73.0% | Only MiMo-V2.5 measured |
| DTBench | 80.3% | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| LMCA | 29.3% | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| Fiction.LiveBench | 75.0% | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| Creative writing (Lech Mazur) | 82.4% | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text | 1415 | 1428 | MiMo-V2.5 |
| LMArena Text: instruction following | 1386 | 1435 | MiMo-V2.5 |
| LMArena Text: creative writing | 1384 | 1393 | MiMo-V2.5 |
| LMArena Vision | Not measured | 1247 | Only MiMo-V2.5 measured |
| LMArena Text: English | 1429 | 1447 | MiMo-V2.5 |
| LMArena Text: non-English | 1397 | 1405 | MiMo-V2.5 |
| LMArena Text: Chinese | 1481 | 1469 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: German | 1408 | 1421 | MiMo-V2.5 |
| LMArena Text: Japanese | 1386 | 1306 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: Korean | 1375 | 1361 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: French | Not measured | 1448 | Only MiMo-V2.5 measured |
| LMArena Text: Spanish | 1389 | 1414 | MiMo-V2.5 |
| LMArena Text: Russian | 1401 | 1396 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: Polish | 1390 | 1413 | MiMo-V2.5 |
| LMArena Text: multi-turn | 1406 | 1445 | MiMo-V2.5 |
| LMArena Text: longer queries | 1400 | 1445 | MiMo-V2.5 |
| LMArena Text: writing and language | 1388 | 1409 | MiMo-V2.5 |
| LMArena Text: entertainment and media | 1370 | 1399 | MiMo-V2.5 |
| LMArena Vision: English | Not measured | 1259 | Only MiMo-V2.5 measured |
| LMArena Vision: Chinese | Not measured | 1326 | Only MiMo-V2.5 measured |
| LMArena Vision: reading text | Not measured | 1256 | Only MiMo-V2.5 measured |
| LMArena Vision: humor | Not measured | 1226 | Only MiMo-V2.5 measured |
| LMArena Vision: recognizing things | Not measured | 1189 | Only MiMo-V2.5 measured |
| LMArena Vision: creative writing | Not measured | 1230 | Only MiMo-V2.5 measured |
| Neither model has a result on the other 15 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Qwen3 235B A22B Thinking 2507 | MiMo-V2.5 | 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 costs less
Repository review
50K input + 3K output tokens
MiMo-V2.5 costs less
Agent loop
200K input + 10K output tokens
MiMo-V2.5 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 235B A22B Thinking 2507 | Xiaomi MiMo-V2.5 |
|---|---|---|
| Maker | Qwen | Xiaomi |
| Weights | Open weights | Open weights |
| Released | July 25, 2025 | April 22, 2026 |
| Context window | 128K | 1.05M |
| Input $/Mtok | $0.45 | $0.168 |
| Output $/Mtok | $3.50 | $0.336 |
| Coding index | Not benchmarked | 50.0 |
| Independent measurements behind it | 0 | 3 |
| Cost per solved task | Not computable | $0.01 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Qwen3 235B A22B Thinking 2507 better than MiMo-V2.5 for coding?
Only MiMo-V2.5 has a coding score, 50.0 on the Vibe Coding Index; Qwen3 235B A22B Thinking 2507 has none, so the two cannot be ranked on coding. Pick Qwen3 235B A22B Thinking 2507 for work measured by LMArena Text: expert or LMArena Text: medicine and healthcare, where it leads.
Which is cheaper, Qwen3 235B A22B Thinking 2507 or MiMo-V2.5?
Qwen3 235B A22B Thinking 2507 costs $0.45 per million input tokens and $3.50 per million output tokens; MiMo-V2.5 costs $0.168 and $0.336. Cost per solved task is known for MiMo-V2.5 only.
Which has the bigger context window, Qwen3 235B A22B Thinking 2507 or MiMo-V2.5?
MiMo-V2.5, with 1.05M tokens against 128K.
How many benchmarks is the Qwen3 235B A22B Thinking 2507 vs MiMo-V2.5 comparison based on?
36 benchmarks have a result for both models as of October 22, 2026. Qwen3 235B A22B Thinking 2507's coding index rests on 0 independent benchmarks and MiMo-V2.5's on 3. Where only one model has a result, the page says so instead of naming a winner.