DeepSeek V3.2 vs MiMo-V2.5-Pro
MiMo-V2.5-Pro leads DeepSeek V3.2 on coding, 31.6 to 30.0 on the Vibe Coding Index, at about the same output price ($0.9152 vs $0.88 per million). Updated October 22, 2026; 57 benchmarks have a result for both.
DeepSeek V3.2 or MiMo-V2.5-Pro: which to pick
DeepSeek V3.2 and MiMo-V2.5-Pro are level for coding, 30.0 against 31.6 on the Vibe Coding Index, so price and context decide.
Pick DeepSeek V3.2 for output tokens 1.0x cheaper ($0.88 vs $0.9152 per million) and work measured by MMLU Pro or DTBench, where it leads. Pick MiMo-V2.5-Pro for a lower cost per solved task ($0.03 against $0.99) and a larger context window (1.05M against 164K tokens).
- Shared results
- 57
- DeepSeek V3.2 only
- 18
- MiMo-V2.5-Pro only
- 13
- 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
Level: 30.0 against 31.6, inside 2 points.
3 and 4 benchmarks behind the scores
Intelligence
AA Intelligence Index
MiMo-V2.5-Pro
MiMo-V2.5-Pro leads, 26.0 against 21.5.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only MiMo-V2.5-Pro has a AA Agentic Index result, 21.3.
Directional only
Reasoning
GPQA Diamond
MiMo-V2.5-Pro
MiMo-V2.5-Pro leads, 82.6% against 80.3%.
Same board, both measured
Math
AIME
No call
Only DeepSeek V3.2 has a AIME result, 84.6%.
Directional only
Knowledge
MMLU Pro
DeepSeek V3.2
DeepSeek V3.2 leads, 84.9% against 84.6%.
Same board, both measured
Web design
Design Arena: websites
MiMo-V2.5-Pro
MiMo-V2.5-Pro leads, 1266 against 1175.
Same board, both measured
Long documents
Listed context window
MiMo-V2.5-Pro
MiMo-V2.5-Pro takes 1.05M tokens against 164K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V3.2
DeepSeek V3.2 $0.0007, MiMo-V2.5-Pro $0.0009 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
MiMo-V2.5-Pro
DeepSeek V3.2 $0.99, MiMo-V2.5-Pro $0.03.
Published attempt cost and pass rate
At a glance
- Coding index
- DeepSeek V3.2 30.0 from 3 benchmarks, MiMo-V2.5-Pro 31.6 from 4 benchmarks.
- Widest category
- Web design, 13.4 points apart on average over 8 shared benchmarks.
- Widest single gap
- Vibe Code Bench (Vals AI): DeepSeek V3.2 5.1% against MiMo-V2.5-Pro 34.1%, 29.0 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V3.2 $0.88 against MiMo-V2.5-Pro $0.9152 per million output tokens, 1.0x apart.
- Context window
- DeepSeek V3.2 takes 164K tokens, MiMo-V2.5-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 | DeepSeek V3.2 | Bars | MiMo-V2.5-Pro | Ties |
|---|---|---|---|---|
| Coding | 0 | 10 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 0 | 6 | ||
| Math | 0 | 2 | ||
| Knowledge | 1 | 7 | ||
| Web design | 0 | 8 | ||
| General | 1 | 20 | ||
| All shared boards | 2 | 55 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index010
| Benchmark | DeepSeek V3.2 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| SWE-bench Verified | 70.0% | Not measured | Only DeepSeek V3.2 measured |
| SWE-bench Multilingual | 59.0% | Not measured | Only DeepSeek V3.2 measured |
| LMArena WebDev | 1362 | 1480 | MiMo-V2.5-Pro |
| AA Coding Index | 44.2 | 60.2 | MiMo-V2.5-Pro |
| LiveCodeBench (Vals AI) | 80.7% | 81.3% | MiMo-V2.5-Pro |
| SWE-bench Verified (Vals AI) | 67.6% | 74.0% | MiMo-V2.5-Pro |
| Terminal-Bench 4 (Vals AI) | Not measured | 0.5% | Only MiMo-V2.5-Pro measured |
| Vibe Code Bench (Vals AI) | 5.1% | 34.1% | MiMo-V2.5-Pro |
| 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 |
| LiveCodeBench (Artificial Analysis run) | 86.2% | Not measured | Only DeepSeek V3.2 measured |
| SciCode | Not measured | 50.6% | Only MiMo-V2.5-Pro measured |
| Terminal-Bench Hard (Artificial Analysis run) | 35.6% | 43.2% | MiMo-V2.5-Pro |
| Terminal-Bench | 39.6% | Not measured | Only DeepSeek V3.2 measured |
| ALE-Bench | Not measured | 899.8 | Only MiMo-V2.5-Pro measured |
| LMArena Text: coding | 1453 | 1501 | MiMo-V2.5-Pro |
| LMArena Text: software and IT | 1449 | 1495 | MiMo-V2.5-Pro |
| LMArena WebDev: React | 1350 | 1469 | MiMo-V2.5-Pro |
| LMArena WebDev: HTML | 1371 | 1473 | MiMo-V2.5-Pro |
| Neither model has a result on the other 20 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3.2 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| AA Intelligence Index | 21.5 | 26.0 | MiMo-V2.5-Pro |
| Epoch Capabilities Index | 146.1 | Not measured | Only DeepSeek V3.2 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3.2 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 21.3 | Only MiMo-V2.5-Pro measured |
| Finance Agent (Vals AI) | Not measured | 41.5% | Only MiMo-V2.5-Pro measured |
| Tax Agent Bench (Vals AI) | Not measured | 11.5% | Only MiMo-V2.5-Pro measured |
| Legal Research Bench (Vals AI) | Not measured | 15.9% | Only MiMo-V2.5-Pro measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 55.2% | Only MiMo-V2.5-Pro measured |
| τ²-Bench Telecom | 90.6% | 94.2% | MiMo-V2.5-Pro |
| APEX-Agents | 21.3% | Not measured | Only DeepSeek V3.2 measured |
| Vending-Bench 2 | $1,034 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 33 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | DeepSeek V3.2 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| GPQA Diamond | 80.3% | 82.6% | MiMo-V2.5-Pro |
| GPQA Diamond (Artificial Analysis run) | 84.0% | 86.6% | MiMo-V2.5-Pro |
| Humanity's Last Exam (Artificial Analysis run) | 24.6% | 35.7% | MiMo-V2.5-Pro |
| ARC-AGI | 57.0% | Not measured | Only DeepSeek V3.2 measured |
| ARC-AGI-2 | 4.0% | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: hard prompts | 1434 | 1486 | MiMo-V2.5-Pro |
| LMArena Text: expert | 1436 | 1501 | MiMo-V2.5-Pro |
| LMArena Text: hard prompts in English | 1446 | 1494 | MiMo-V2.5-Pro |
| Neither model has a result on the other 14 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | DeepSeek V3.2 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| AIME | 84.6% | Not measured | Only DeepSeek V3.2 measured |
| MGSM (Vals AI) | 86.0% | Not measured | Only DeepSeek V3.2 measured |
| AA Math Index | 92.0 | Not measured | Only DeepSeek V3.2 measured |
| AIME 2025 (Artificial Analysis run) | 92.0% | Not measured | Only DeepSeek V3.2 measured |
| ProofBench | Not measured | 22.0% | Only MiMo-V2.5-Pro measured |
| LMArena Text: math | 1435 | 1481 | MiMo-V2.5-Pro |
| LMArena Text: mathematical work | 1440 | 1491 | MiMo-V2.5-Pro |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index17
| Benchmark | DeepSeek V3.2 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| MMLU Pro | 84.9% | 84.6% | DeepSeek V3.2 |
| LegalBench (Vals AI) | 76.1% | 77.1% | MiMo-V2.5-Pro |
| CaseLaw (Vals AI) | 55.4% | Not measured | Only DeepSeek V3.2 measured |
| CorpFin (Vals AI) | 51.0% | 61.4% | MiMo-V2.5-Pro |
| TaxEval (Vals AI) | 68.2% | 73.8% | MiMo-V2.5-Pro |
| MedQA (Vals AI) | 93.9% | Not measured | Only DeepSeek V3.2 measured |
| MedCode (Vals AI) | Not measured | 32.5% | Only MiMo-V2.5-Pro measured |
| MMLU Pro (Artificial Analysis run) | 86.2% | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: science | 1446 | 1482 | MiMo-V2.5-Pro |
| LMArena Text: medicine and healthcare | 1440 | 1473 | MiMo-V2.5-Pro |
| LMArena Text: legal and government | 1425 | 1474 | MiMo-V2.5-Pro |
| LMArena Text: business and finance | 1410 | 1466 | MiMo-V2.5-Pro |
| Neither model has a result on the other 6 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index08
| Benchmark | DeepSeek V3.2 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| Design Arena: websites | 1175 | 1266 | MiMo-V2.5-Pro |
| Design Arena: UI components | 1146 | 1246 | MiMo-V2.5-Pro |
| Design Arena: game dev | 1131 | 1261 | MiMo-V2.5-Pro |
| Design Arena: data viz | 1158 | 1257 | MiMo-V2.5-Pro |
| Design Arena: 3D | 1132 | 1243 | MiMo-V2.5-Pro |
| Design Arena: all code categories | 1163 | 1265 | MiMo-V2.5-Pro |
| Design Arena: SVG | 1032 | 1181 | MiMo-V2.5-Pro |
| Design Arena: ASCII art | 1083 | 1156 | MiMo-V2.5-Pro |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index120
| Benchmark | DeepSeek V3.2 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| MedScribe (Vals AI) | Not measured | 83.7% | Only MiMo-V2.5-Pro measured |
| IFBench | 60.7% | 79.9% | MiMo-V2.5-Pro |
| Long context reasoning (AA-LCR) | 73.3% | 79.7% | MiMo-V2.5-Pro |
| DTBench | 85.6% | 84.5% | DeepSeek V3.2 |
| LMCA | 28.8% | 29.5% | MiMo-V2.5-Pro |
| CL-bench | 12.4% | Not measured | Only DeepSeek V3.2 measured |
| CL-bench Life | 7.4% | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text | 1425 | 1464 | MiMo-V2.5-Pro |
| LMArena Text: instruction following | 1413 | 1475 | MiMo-V2.5-Pro |
| LMArena Text: creative writing | 1400 | 1438 | MiMo-V2.5-Pro |
| LMArena Text: English | 1439 | 1477 | MiMo-V2.5-Pro |
| LMArena Text: non-English | 1409 | 1448 | MiMo-V2.5-Pro |
| LMArena Text: Chinese | 1455 | 1507 | MiMo-V2.5-Pro |
| LMArena Text: German | 1413 | 1459 | MiMo-V2.5-Pro |
| LMArena Text: Japanese | 1374 | 1410 | MiMo-V2.5-Pro |
| LMArena Text: Korean | 1370 | 1435 | MiMo-V2.5-Pro |
| LMArena Text: French | 1429 | 1487 | MiMo-V2.5-Pro |
| LMArena Text: Spanish | 1424 | 1469 | MiMo-V2.5-Pro |
| LMArena Text: Russian | 1424 | 1449 | MiMo-V2.5-Pro |
| LMArena Text: Polish | 1419 | 1464 | MiMo-V2.5-Pro |
| LMArena Text: multi-turn | 1427 | 1476 | MiMo-V2.5-Pro |
| LMArena Text: longer queries | 1428 | 1481 | MiMo-V2.5-Pro |
| LMArena Text: writing and language | 1407 | 1451 | MiMo-V2.5-Pro |
| LMArena Text: entertainment and media | 1395 | 1438 | MiMo-V2.5-Pro |
| Neither model has a result on the other 22 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V3.2 | 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
DeepSeek V3.2 costs less
Repository review
50K input + 3K output tokens
DeepSeek V3.2 costs less
Agent loop
200K input + 10K output tokens
DeepSeek V3.2 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 | DeepSeek V3.2 | Xiaomi MiMo-V2.5-Pro |
|---|---|---|
| Maker | DeepSeek | Xiaomi |
| Weights | Open weights | Open weights |
| Released | December 1, 2025 | April 22, 2026 |
| Context window | 164K | 1.05M |
| Input $/Mtok | $0.29 | $0.4575 |
| Output $/Mtok | $0.88 | $0.9152 |
| Coding index | 30.0 | 31.6 |
| Independent measurements behind it | 3 | 4 |
| Cost per solved task | $0.99 | $0.03 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V3.2 better than MiMo-V2.5-Pro for coding?
DeepSeek V3.2 and MiMo-V2.5-Pro are level for coding, 30.0 against 31.6 on the Vibe Coding Index, so price and context decide. Pick DeepSeek V3.2 for output tokens 1.0x cheaper ($0.88 vs $0.9152 per million) and work measured by MMLU Pro or DTBench, where it leads. Pick MiMo-V2.5-Pro for a lower cost per solved task ($0.03 against $0.99) and a larger context window (1.05M against 164K tokens).
Which is cheaper, DeepSeek V3.2 or MiMo-V2.5-Pro?
DeepSeek V3.2 costs $0.29 per million input tokens and $0.88 per million output tokens; MiMo-V2.5-Pro costs $0.4575 and $0.9152. Per solved SWE-bench Verified task, DeepSeek V3.2 costs $0.99 and MiMo-V2.5-Pro $0.03.
Which has the bigger context window, DeepSeek V3.2 or MiMo-V2.5-Pro?
MiMo-V2.5-Pro, with 1.05M tokens against 164K.
How many benchmarks is the DeepSeek V3.2 vs MiMo-V2.5-Pro comparison based on?
57 benchmarks have a result for both models as of October 22, 2026. DeepSeek V3.2's coding index rests on 3 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.