DeepSeek V4 Pro 0423 vs MiMo-V2.5-Pro
DeepSeek V4 Pro 0423 leads MiMo-V2.5-Pro on coding, 38.7 to 31.6 on the Vibe Coding Index, and MiMo-V2.5-Pro costs 3.0x less per output token ($0.9152 vs $2.716 per million). Updated October 21, 2026; 63 benchmarks have a result for both.
DeepSeek V4 Pro 0423 or MiMo-V2.5-Pro: which to pick
Pick DeepSeek V4 Pro 0423 for coding: it scores 38.7 on the Vibe Coding Index against 31.6 for MiMo-V2.5-Pro.
Pick MiMo-V2.5-Pro for output tokens 3.0x cheaper ($0.9152 vs $2.716 per million) and a lower cost per solved task ($0.03 against $0.57).
- Shared results
- 63
- DeepSeek V4 Pro 0423 only
- 21
- MiMo-V2.5-Pro only
- 7
- 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
DeepSeek V4 Pro 0423
DeepSeek V4 Pro 0423 scores 38.7 against 31.6.
5 and 4 benchmarks behind the scores
Intelligence
AA Intelligence Index
DeepSeek V4 Pro 0423
DeepSeek V4 Pro 0423 leads, 30.4 against 26.0.
Same board, both measured
Agentic work
AA Agentic Index
DeepSeek V4 Pro 0423
DeepSeek V4 Pro 0423 leads, 26.3 against 21.3.
Same board, both measured
Reasoning
GPQA Diamond
DeepSeek V4 Pro 0423
DeepSeek V4 Pro 0423 leads, 89.4% against 82.6%.
Same board, both measured
Knowledge
MMLU Pro
DeepSeek V4 Pro 0423
DeepSeek V4 Pro 0423 leads, 87.3% against 84.6%.
Same board, both measured
Web design
Design Arena: websites
MiMo-V2.5-Pro
MiMo-V2.5-Pro leads, 1267 against 1234.
Same board, both measured
Long documents
Listed context window
MiMo-V2.5-Pro
MiMo-V2.5-Pro takes 1.05M tokens against 1.05M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiMo-V2.5-Pro
DeepSeek V4 Pro 0423 $0.0026, 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 V4 Pro 0423 $0.57, MiMo-V2.5-Pro $0.03.
Published attempt cost and pass rate
At a glance
- Coding index
- DeepSeek V4 Pro 0423 38.7 from 5 benchmarks, MiMo-V2.5-Pro 31.6 from 4 benchmarks.
- Widest category
- Agentic work, 6.4 points apart on average over 5 shared benchmarks.
- Widest single gap
- Vibe Code Bench (Vals AI): DeepSeek V4 Pro 0423 49.9% against MiMo-V2.5-Pro 34.1%, 15.8 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V4 Pro 0423 $2.716 against MiMo-V2.5-Pro $0.9152 per million output tokens, 3.0x apart.
- Context window
- DeepSeek V4 Pro 0423 takes 1.05M 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 V4 Pro 0423 | Bars | MiMo-V2.5-Pro | Ties |
|---|---|---|---|---|
| Coding | 6 | 7 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 4 | 1 | ||
| Reasoning | 1 | 3 | ||
| Math | 0 | 3 | ||
| Knowledge | 3 | 6 | ||
| Web design | 1 | 7 | ||
| General | 5 | 15 | ||
| All shared boards | 21 | 42 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index67
| Benchmark | DeepSeek V4 Pro 0423 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| LMArena WebDev | 1447 | 1480 | MiMo-V2.5-Pro |
| AA Coding Index | 59.4 | 60.2 | MiMo-V2.5-Pro |
| LiveCodeBench (Vals AI) | 87.5% | 81.3% | DeepSeek V4 Pro 0423 |
| SWE-bench Verified (Vals AI) | 77.4% | 74.0% | DeepSeek V4 Pro 0423 |
| Terminal-Bench 4 (Vals AI) | 11.1% | 0.5% | DeepSeek V4 Pro 0423 |
| Vibe Code Bench (Vals AI) | 49.9% | 34.1% | DeepSeek V4 Pro 0423 |
| Code migration (Vals AI) | 26.2% | 21.6% | DeepSeek V4 Pro 0423 |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Terminal-Bench 2.1 (Vals AI) | 50.2% | 57.3% | MiMo-V2.5-Pro |
| SkillsBench (Vals AI) | 51.3% | Not measured | Only DeepSeek V4 Pro 0423 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 |
| FrontierCode | 17.6% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| WeirdML | 48.9% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| ALE-Bench | 1006.1 | 899.8 | DeepSeek V4 Pro 0423 |
| LMArena Text: coding | 1470 | 1501 | MiMo-V2.5-Pro |
| LMArena Text: software and IT | 1469 | 1495 | MiMo-V2.5-Pro |
| LMArena WebDev: React | 1441 | 1469 | MiMo-V2.5-Pro |
| LMArena WebDev: HTML | 1435 | 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 index10
| Benchmark | DeepSeek V4 Pro 0423 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| AA Intelligence Index | 30.4 | 26.0 | DeepSeek V4 Pro 0423 |
| Epoch Capabilities Index | 149.1 | Not measured | Only DeepSeek V4 Pro 0423 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index41
| Benchmark | DeepSeek V4 Pro 0423 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| AA Agentic Index | 26.3 | 21.3 | DeepSeek V4 Pro 0423 |
| Design Arena: agents building web apps | 1000 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: agents building full-stack apps | 948 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: agents building Godot games | 1059 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Finance Agent (Vals AI) | 44.1% | 41.5% | DeepSeek V4 Pro 0423 |
| Tax Agent Bench (Vals AI) | 25.2% | 11.5% | DeepSeek V4 Pro 0423 |
| Legal Research Bench (Vals AI) | 23.1% | 15.9% | DeepSeek V4 Pro 0423 |
| Excel Modeling Benchmark (Vals AI) | 51.6% | 55.2% | MiMo-V2.5-Pro |
| τ²-Bench Telecom | Not measured | 94.2% | Only MiMo-V2.5-Pro measured |
| Vending-Bench 2 | $3,285 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Neither model has a result on the other 31 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index13
| Benchmark | DeepSeek V4 Pro 0423 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| GPQA Diamond | 89.4% | 82.6% | DeepSeek V4 Pro 0423 |
| 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 |
| GPQA Diamond (Epoch AI run) | 90.9% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Chess puzzles | 19.0% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Mystery game puzzles | 17.0% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LMArena Text: hard prompts | 1461 | 1486 | MiMo-V2.5-Pro |
| LMArena Text: expert | 1463 | 1501 | MiMo-V2.5-Pro |
| LMArena Text: hard prompts in English | 1466 | 1494 | MiMo-V2.5-Pro |
| Kagi LLM Benchmark | 53.5% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Neither model has a result on the other 12 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | DeepSeek V4 Pro 0423 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| OTIS Mock AIME | 96.7% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| FrontierMath, tiers 1 to 3 | 45.3% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| FrontierMath, tier 4 | 2.4% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| ProofBench | 16.0% | 22.0% | MiMo-V2.5-Pro |
| LMArena Text: math | 1443 | 1481 | MiMo-V2.5-Pro |
| LMArena Text: mathematical work | 1455 | 1491 | MiMo-V2.5-Pro |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index36
| Benchmark | DeepSeek V4 Pro 0423 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| MMLU Pro | 87.3% | 84.6% | DeepSeek V4 Pro 0423 |
| LegalBench (Vals AI) | 80.3% | 77.1% | DeepSeek V4 Pro 0423 |
| CaseLaw (Vals AI) | 59.4% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| CorpFin (Vals AI) | 61.4% | 61.4% | MiMo-V2.5-Pro |
| TaxEval (Vals AI) | 72.1% | 73.8% | MiMo-V2.5-Pro |
| MedCode (Vals AI) | 40.5% | 32.5% | DeepSeek V4 Pro 0423 |
| SimpleQA Verified | 47.0% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LMArena Text: science | 1470 | 1482 | MiMo-V2.5-Pro |
| LMArena Text: medicine and healthcare | 1466 | 1473 | MiMo-V2.5-Pro |
| LMArena Text: legal and government | 1464 | 1474 | MiMo-V2.5-Pro |
| LMArena Text: business and finance | 1443 | 1466 | MiMo-V2.5-Pro |
| Neither model has a result on the other 7 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index17
| Benchmark | DeepSeek V4 Pro 0423 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| Design Arena: websites | 1234 | 1267 | MiMo-V2.5-Pro |
| Design Arena: UI components | 1222 | 1249 | MiMo-V2.5-Pro |
| Design Arena: game dev | 1229 | 1262 | MiMo-V2.5-Pro |
| Design Arena: data viz | 1203 | 1257 | MiMo-V2.5-Pro |
| Design Arena: 3D | 1254 | 1244 | DeepSeek V4 Pro 0423 |
| Design Arena: all code categories | 1240 | 1266 | MiMo-V2.5-Pro |
| Design Arena: SVG | 1140 | 1181 | MiMo-V2.5-Pro |
| Design Arena: ASCII art | 1149 | 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 index515
| Benchmark | DeepSeek V4 Pro 0423 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| Public Benefits Bench (Vals AI) | 62.9% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| MedScribe (Vals AI) | 75.1% | 83.7% | MiMo-V2.5-Pro |
| 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 |
| DTBench | 90.7% | 84.5% | DeepSeek V4 Pro 0423 |
| LMCA | 41.2% | 29.5% | DeepSeek V4 Pro 0423 |
| Surface Evolver Bench | 40.0% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| CL-bench Life | 13.5% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LMArena Text | 1451 | 1464 | MiMo-V2.5-Pro |
| LMArena Text: instruction following | 1445 | 1475 | MiMo-V2.5-Pro |
| LMArena Text: creative writing | 1446 | 1438 | DeepSeek V4 Pro 0423 |
| LMArena Text: English | 1459 | 1477 | MiMo-V2.5-Pro |
| LMArena Text: non-English | 1439 | 1448 | MiMo-V2.5-Pro |
| LMArena Text: Chinese | 1481 | 1507 | MiMo-V2.5-Pro |
| LMArena Text: German | 1458 | 1459 | MiMo-V2.5-Pro |
| LMArena Text: Japanese | 1446 | 1410 | DeepSeek V4 Pro 0423 |
| LMArena Text: Korean | 1409 | 1435 | MiMo-V2.5-Pro |
| LMArena Text: French | 1473 | 1487 | MiMo-V2.5-Pro |
| LMArena Text: Spanish | 1457 | 1469 | MiMo-V2.5-Pro |
| LMArena Text: Russian | 1453 | 1449 | DeepSeek V4 Pro 0423 |
| LMArena Text: Polish | 1461 | 1464 | MiMo-V2.5-Pro |
| LMArena Text: multi-turn | 1468 | 1476 | MiMo-V2.5-Pro |
| LMArena Text: longer queries | 1458 | 1481 | MiMo-V2.5-Pro |
| LMArena Text: writing and language | 1447 | 1451 | MiMo-V2.5-Pro |
| LMArena Text: entertainment and media | 1431 | 1438 | MiMo-V2.5-Pro |
| Neither model has a result on the other 21 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V4 Pro 0423 | 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 | DeepSeek V4 Pro 0423 | Xiaomi MiMo-V2.5-Pro |
|---|---|---|
| Maker | DeepSeek | Xiaomi |
| Weights | Open weights | Open weights |
| Released | April 24, 2026 | April 22, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $1.225 | $0.4575 |
| Output $/Mtok | $2.716 | $0.9152 |
| Coding index | 38.7 | 31.6 |
| Independent measurements behind it | 5 | 4 |
| Cost per solved task | $0.57 | $0.03 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V4 Pro 0423 better than MiMo-V2.5-Pro for coding?
Pick DeepSeek V4 Pro 0423 for coding: it scores 38.7 on the Vibe Coding Index against 31.6 for MiMo-V2.5-Pro. Pick MiMo-V2.5-Pro for output tokens 3.0x cheaper ($0.9152 vs $2.716 per million) and a lower cost per solved task ($0.03 against $0.57).
Which is cheaper, DeepSeek V4 Pro 0423 or MiMo-V2.5-Pro?
DeepSeek V4 Pro 0423 costs $1.225 per million input tokens and $2.716 per million output tokens; MiMo-V2.5-Pro costs $0.4575 and $0.9152. Per solved SWE-bench Verified task, DeepSeek V4 Pro 0423 costs $0.57 and MiMo-V2.5-Pro $0.03.
Which has the bigger context window, DeepSeek V4 Pro 0423 or MiMo-V2.5-Pro?
MiMo-V2.5-Pro, with 1.05M tokens against 1.05M.
How many benchmarks is the DeepSeek V4 Pro 0423 vs MiMo-V2.5-Pro comparison based on?
63 benchmarks have a result for both models as of October 21, 2026. DeepSeek V4 Pro 0423's coding index rests on 5 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.