DeepSeek V4 Flash 0731 vs MiMo-V2.5-Pro
DeepSeek V4 Flash 0731 leads MiMo-V2.5-Pro on coding, 51.8 to 31.6 on the Vibe Coding Index, and DeepSeek V4 Flash 0731 costs 3.3x less per output token ($0.28 vs $0.9152 per million). Updated October 21, 2026; 36 benchmarks have a result for both.
DeepSeek V4 Flash 0731 or MiMo-V2.5-Pro: which to pick
Pick DeepSeek V4 Flash 0731 for coding: it scores 51.8 on the Vibe Coding Index against 31.6 for MiMo-V2.5-Pro.
Pick MiMo-V2.5-Pro for a larger context window (1.05M against 1.05M tokens) and work measured by SciCode or TaxEval (Vals AI), where it leads.
- Shared results
- 36
- DeepSeek V4 Flash 0731 only
- 19
- MiMo-V2.5-Pro only
- 34
- 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 Flash 0731
DeepSeek V4 Flash 0731 scores 51.8 against 31.6.
4 benchmarks behind each score
Intelligence
AA Intelligence Index
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 leads, 34.3 against 26.0.
Same board, both measured
Agentic work
AA Agentic Index
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 leads, 41.0 against 21.3.
Same board, both measured
Reasoning
GPQA Diamond
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 leads, 89.9% against 82.6%.
Same board, both measured
Knowledge
MMLU Pro
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 leads, 86.2% against 84.6%.
Same board, both measured
Web design
Design Arena: websites
MiMo-V2.5-Pro
MiMo-V2.5-Pro leads, 1267 against 1238.
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
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 $0.0003, MiMo-V2.5-Pro $0.0009 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 $0.01, MiMo-V2.5-Pro $0.03.
Published attempt cost and pass rate
At a glance
- Coding index
- DeepSeek V4 Flash 0731 51.8 from 4 benchmarks, MiMo-V2.5-Pro 31.6 from 4 benchmarks.
- Widest category
- Math, 34.0 points apart on average over 1 shared benchmark.
- Widest single gap
- Vibe Code Bench (Vals AI): DeepSeek V4 Flash 0731 74.7% against MiMo-V2.5-Pro 34.1%, 40.6 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V4 Flash 0731 $0.28 against MiMo-V2.5-Pro $0.9152 per million output tokens, 3.3x apart.
- Context window
- DeepSeek V4 Flash 0731 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 Flash 0731 | Bars | MiMo-V2.5-Pro | Ties |
|---|---|---|---|---|
| Coding | 8 | 1 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 5 | 0 | ||
| Reasoning | 3 | 0 | ||
| Math | 1 | 0 | ||
| Knowledge | 4 | 1 | ||
| Web design | 1 | 7 | ||
| General | 2 | 1 | 1 tie | |
| All shared boards | 25 | 10 | 1 tie |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index81
| Benchmark | DeepSeek V4 Flash 0731 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| LMArena WebDev | Not measured | 1480 | Only MiMo-V2.5-Pro measured |
| AA Coding Index | 69.1 | 60.2 | DeepSeek V4 Flash 0731 |
| LiveCodeBench (Vals AI) | 87.3% | 81.3% | DeepSeek V4 Flash 0731 |
| SWE-bench Verified (Vals AI) | 88.8% | 74.0% | DeepSeek V4 Flash 0731 |
| Terminal-Bench 4 (Vals AI) | 18.7% | 0.5% | DeepSeek V4 Flash 0731 |
| Vibe Code Bench (Vals AI) | 74.7% | 34.1% | DeepSeek V4 Flash 0731 |
| Code migration (Vals AI) | 38.6% | 21.6% | DeepSeek V4 Flash 0731 |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| IOI (Vals AI) | 32.7% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Terminal-Bench 2.1 (Vals AI) | 67.0% | 57.3% | DeepSeek V4 Flash 0731 |
| SkillsBench (Vals AI) | 50.7% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| CyberBench (Vals AI) | 72.1% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| SciCode | 50.3% | 50.6% | MiMo-V2.5-Pro |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 43.2% | Only MiMo-V2.5-Pro measured |
| FrontierCode | 18.8% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| WeirdML | 63.0% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| ALE-Bench | 1306.1 | 899.8 | DeepSeek V4 Flash 0731 |
| LMArena Text: coding | Not measured | 1501 | Only MiMo-V2.5-Pro measured |
| LMArena Text: software and IT | Not measured | 1495 | Only MiMo-V2.5-Pro measured |
| LMArena WebDev: React | Not measured | 1469 | Only MiMo-V2.5-Pro measured |
| LMArena WebDev: HTML | Not measured | 1473 | Only MiMo-V2.5-Pro measured |
| Neither model has a result on the other 18 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | DeepSeek V4 Flash 0731 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| AA Intelligence Index | 34.3 | 26.0 | DeepSeek V4 Flash 0731 |
| Epoch Capabilities Index | 154.8 | Not measured | Only DeepSeek V4 Flash 0731 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | DeepSeek V4 Flash 0731 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| AA Agentic Index | 41.0 | 21.3 | DeepSeek V4 Flash 0731 |
| Finance Agent (Vals AI) | 49.5% | 41.5% | DeepSeek V4 Flash 0731 |
| Tax Agent Bench (Vals AI) | 28.1% | 11.5% | DeepSeek V4 Flash 0731 |
| Legal Research Bench (Vals AI) | 30.3% | 15.9% | DeepSeek V4 Flash 0731 |
| Excel Modeling Benchmark (Vals AI) | 57.0% | 55.2% | DeepSeek V4 Flash 0731 |
| BioMysteryBench (Vals AI) | 64.4% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Terminal-Bench-Science (Vals AI) | 4.3% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| τ²-Bench Telecom | Not measured | 94.2% | Only MiMo-V2.5-Pro measured |
| Neither model has a result on the other 33 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | DeepSeek V4 Flash 0731 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| GPQA Diamond | 89.9% | 82.6% | DeepSeek V4 Flash 0731 |
| GPQA Diamond (Artificial Analysis run) | 90.8% | 86.6% | DeepSeek V4 Flash 0731 |
| Humanity's Last Exam (Artificial Analysis run) | 38.6% | 35.7% | DeepSeek V4 Flash 0731 |
| GPQA Diamond (Epoch AI run) | 91.0% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| ARC-AGI | 89.0% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| ARC-AGI-2 | 61.4% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| SimpleBench | 61.1% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Chess puzzles | 32.0% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Mystery game puzzles | 34.0% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| LMArena Text: hard prompts | Not measured | 1486 | 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 10 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | DeepSeek V4 Flash 0731 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| OTIS Mock AIME | 94.4% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| FrontierMath, tiers 1 to 3 | 57.5% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| FrontierMath, tier 4 | 24.4% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| ProofBench | 56.0% | 22.0% | DeepSeek V4 Flash 0731 |
| LMArena Text: math | Not measured | 1481 | Only MiMo-V2.5-Pro measured |
| LMArena Text: mathematical work | Not measured | 1491 | Only MiMo-V2.5-Pro measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index41
| Benchmark | DeepSeek V4 Flash 0731 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| MMLU Pro | 86.2% | 84.6% | DeepSeek V4 Flash 0731 |
| LegalBench (Vals AI) | 77.7% | 77.1% | DeepSeek V4 Flash 0731 |
| CorpFin (Vals AI) | 61.9% | 61.4% | DeepSeek V4 Flash 0731 |
| TaxEval (Vals AI) | 70.7% | 73.8% | MiMo-V2.5-Pro |
| MedCode (Vals AI) | 41.4% | 32.5% | DeepSeek V4 Flash 0731 |
| SimpleQA Verified | 33.6% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| LMArena Text: science | Not measured | 1482 | Only MiMo-V2.5-Pro measured |
| LMArena Text: medicine and healthcare | Not measured | 1473 | Only MiMo-V2.5-Pro measured |
| LMArena Text: legal and government | Not measured | 1474 | Only MiMo-V2.5-Pro measured |
| LMArena Text: business and finance | Not measured | 1466 | Only MiMo-V2.5-Pro measured |
| Neither model has a result on the other 8 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index17
| Benchmark | DeepSeek V4 Flash 0731 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| Design Arena: websites | 1238 | 1267 | MiMo-V2.5-Pro |
| Design Arena: UI components | 1235 | 1249 | MiMo-V2.5-Pro |
| Design Arena: game dev | 1208 | 1262 | MiMo-V2.5-Pro |
| Design Arena: data viz | 1180 | 1257 | MiMo-V2.5-Pro |
| Design Arena: 3D | 1209 | 1244 | MiMo-V2.5-Pro |
| Design Arena: all code categories | 1230 | 1266 | MiMo-V2.5-Pro |
| Design Arena: SVG | 1185 | 1181 | DeepSeek V4 Flash 0731 |
| Design Arena: ASCII art | 1090 | 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 index21
| Benchmark | DeepSeek V4 Flash 0731 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| MedScribe (Vals AI) | 80.4% | 83.7% | MiMo-V2.5-Pro |
| IFBench | Not measured | 79.9% | Only MiMo-V2.5-Pro measured |
| Long context reasoning (AA-LCR) | 79.7% | 79.7% | Tie |
| DTBench | 90.9% | 84.5% | DeepSeek V4 Flash 0731 |
| LMCA | 41.7% | 29.5% | DeepSeek V4 Flash 0731 |
| LMArena Text | Not measured | 1464 | Only MiMo-V2.5-Pro measured |
| LMArena Text: instruction following | Not measured | 1475 | Only MiMo-V2.5-Pro measured |
| LMArena Text: creative writing | Not measured | 1438 | 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 | 1459 | Only MiMo-V2.5-Pro measured |
| LMArena Text: Japanese | Not measured | 1410 | Only MiMo-V2.5-Pro measured |
| LMArena Text: Korean | Not measured | 1435 | Only MiMo-V2.5-Pro measured |
| LMArena Text: French | Not measured | 1487 | Only MiMo-V2.5-Pro measured |
| LMArena Text: Spanish | Not measured | 1469 | Only MiMo-V2.5-Pro measured |
| LMArena Text: Russian | Not measured | 1449 | Only MiMo-V2.5-Pro measured |
| LMArena Text: Polish | Not measured | 1464 | Only MiMo-V2.5-Pro measured |
| LMArena Text: multi-turn | Not measured | 1476 | 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 | 1438 | Only MiMo-V2.5-Pro measured |
| Neither model has a result on the other 24 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V4 Flash 0731 | 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 V4 Flash 0731 costs less
Repository review
50K input + 3K output tokens
DeepSeek V4 Flash 0731 costs less
Agent loop
200K input + 10K output tokens
DeepSeek V4 Flash 0731 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 Flash 0731 | Xiaomi MiMo-V2.5-Pro |
|---|---|---|
| Maker | DeepSeek | Xiaomi |
| Weights | Open weights | Open weights |
| Released | July 31, 2026 | April 22, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $0.14 | $0.4575 |
| Output $/Mtok | $0.28 | $0.9152 |
| Coding index | 51.8 | 31.6 |
| Independent measurements behind it | 4 | 4 |
| Cost per solved task | $0.01 | $0.03 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V4 Flash 0731 better than MiMo-V2.5-Pro for coding?
Pick DeepSeek V4 Flash 0731 for coding: it scores 51.8 on the Vibe Coding Index against 31.6 for MiMo-V2.5-Pro. Pick MiMo-V2.5-Pro for a larger context window (1.05M against 1.05M tokens) and work measured by SciCode or TaxEval (Vals AI), where it leads.
Which is cheaper, DeepSeek V4 Flash 0731 or MiMo-V2.5-Pro?
DeepSeek V4 Flash 0731 costs $0.14 per million input tokens and $0.28 per million output tokens; MiMo-V2.5-Pro costs $0.4575 and $0.9152. Per solved SWE-bench Verified task, DeepSeek V4 Flash 0731 costs $0.01 and MiMo-V2.5-Pro $0.03.
Which has the bigger context window, DeepSeek V4 Flash 0731 or MiMo-V2.5-Pro?
MiMo-V2.5-Pro, with 1.05M tokens against 1.05M.
How many benchmarks is the DeepSeek V4 Flash 0731 vs MiMo-V2.5-Pro comparison based on?
36 benchmarks have a result for both models as of October 21, 2026. DeepSeek V4 Flash 0731'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.