DeepSeek V4 Pro 0813 vs MiMo-V2.6-Flash
Updated October 21, 2026. 51 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-Flash for coding: it scores 61.9 on the Vibe Coding Index against 54.6 for DeepSeek V4 Pro 0813.
Pick DeepSeek V4 Pro 0813 when what matters is Vibe Code Bench (Vals AI) or Code migration (Vals AI), where it leads.
- Shared results
- 51
- DeepSeek V4 Pro 0813 only
- 27
- MiMo-V2.6-Flash only
- 15
- Like-for-like categories
- 7 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-Flash
MiMo-V2.6-Flash scores 61.9 against 54.6.
One benchmark behind each score
Intelligence
AA Intelligence Index
MiMo-V2.6-Flash
MiMo-V2.6-Flash leads, 37.9 against 36.0.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only DeepSeek V4 Pro 0813 has a AA Agentic Index result, 41.3.
Directional only
Reasoning
GPQA Diamond
No call
Only DeepSeek V4 Pro 0813 has a GPQA Diamond result, 92.4%.
Directional only
Knowledge
MMLU Pro
No call
Only DeepSeek V4 Pro 0813 has a MMLU Pro result, 87.0%.
Directional only
General
Vals Index
MiMo-V2.6-Flash
MiMo-V2.6-Flash leads, 54.8% against 53.0%.
Same board, both measured
Long documents
Listed context window
MiMo-V2.6-Flash
MiMo-V2.6-Flash takes 1.05M tokens against 1.05M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiMo-V2.6-Flash
DeepSeek V4 Pro 0813 $0.0016, MiMo-V2.6-Flash $0.0003 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only DeepSeek V4 Pro 0813 has the number, $0.10.
Directional only
At a glance
- Coding index
- DeepSeek V4 Pro 0813 54.6 from 1 benchmark, MiMo-V2.6-Flash 61.9 from 1 benchmark.
- Widest category
- Math, 8.3 points apart on average over 3 shared benchmarks.
- Widest single gap
- Terminal-Bench 2.1 (Vals AI): DeepSeek V4 Pro 0813 54.7% against MiMo-V2.6-Flash 76.4%, 21.7 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V4 Pro 0813 $1.98 against MiMo-V2.6-Flash $0.28 per million output tokens, 7.1x apart.
- Context window
- DeepSeek V4 Pro 0813 takes 1.05M tokens, MiMo-V2.6-Flash 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 0813 | Bars | MiMo-V2.6-Flash | Ties |
|---|---|---|---|---|
| Coding | 4 | 10 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 1 | 5 | 1 tie | |
| Reasoning | 1 | 3 | ||
| Math | 0 | 3 | ||
| Knowledge | 3 | 2 | ||
| General | 7 | 10 | ||
| All shared boards | 16 | 34 | 1 tie |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index410
| Benchmark | DeepSeek V4 Pro 0813 | MiMo-V2.6-Flash | Leader |
|---|---|---|---|
| LMArena WebDev | 1582 | 1634 | MiMo-V2.6-Flash |
| AA Coding Index | 68.8 | Not measured | Only DeepSeek V4 Pro 0813 measured |
| LiveCodeBench (Vals AI) | 87.5% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| SWE-bench Verified (Vals AI) | 96.4% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| Terminal-Bench 4 (Vals AI) | 14.1% | 24.2% | MiMo-V2.6-Flash |
| Vibe Code Bench (Vals AI) | 82.3% | 79.0% | DeepSeek V4 Pro 0813 |
| Code migration (Vals AI) | 41.5% | 40.9% | DeepSeek V4 Pro 0813 |
| ProgramBench (Vals AI) | 0.0% | 0.5% | MiMo-V2.6-Flash |
| IOI (Vals AI) | 51.6% | 47.7% | DeepSeek V4 Pro 0813 |
| Terminal-Bench 2.1 (Vals AI) | 54.7% | 76.4% | MiMo-V2.6-Flash |
| Vibe Code Bench 1-100 (Vals AI) | 17.5% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| SkillsBench (Vals AI) | 53.8% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| CyberBench (Vals AI) | 72.9% | 75.4% | MiMo-V2.6-Flash |
| SciCode | 51.0% | 51.3% | MiMo-V2.6-Flash |
| FrontierCode | 28.5% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| WeirdML | 66.2% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| ALE-Bench | 1403.2 | 1244.2 | DeepSeek V4 Pro 0813 |
| LMArena Text: coding | 1469 | 1499 | MiMo-V2.6-Flash |
| LMArena Text: software and IT | 1462 | 1497 | MiMo-V2.6-Flash |
| LMArena WebDev: React | 1588 | 1648 | MiMo-V2.6-Flash |
| LMArena WebDev: HTML | 1566 | 1641 | MiMo-V2.6-Flash |
| LMArena WebDev: from an image | Not measured | 1596 | Only MiMo-V2.6-Flash measured |
| Neither model has a result on the other 16 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V4 Pro 0813 | MiMo-V2.6-Flash | Leader |
|---|---|---|---|
| AA Intelligence Index | 36.0 | 37.9 | MiMo-V2.6-Flash |
| Epoch Capabilities Index | 155.6 | Not measured | Only DeepSeek V4 Pro 0813 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index15
| Benchmark | DeepSeek V4 Pro 0813 | MiMo-V2.6-Flash | Leader |
|---|---|---|---|
| AA Agentic Index | 41.3 | Not measured | Only DeepSeek V4 Pro 0813 measured |
| SREBench (Vals AI) | 1.9% | 4.2% | MiMo-V2.6-Flash |
| Finance Agent (Vals AI) | 50.4% | 56.3% | MiMo-V2.6-Flash |
| Tax Agent Bench (Vals AI) | 26.8% | 28.5% | MiMo-V2.6-Flash |
| Legal Research Bench (Vals AI) | 40.9% | 38.0% | DeepSeek V4 Pro 0813 |
| Harvey's Legal Agent Benchmark (Vals AI) | 10.8% | 13.3% | MiMo-V2.6-Flash |
| Excel Modeling Benchmark (Vals AI) | 52.8% | 65.5% | MiMo-V2.6-Flash |
| BioMysteryBench (Vals AI) | Not measured | 69.3% | Only MiMo-V2.6-Flash measured |
| Terminal-Bench-Science (Vals AI) | 4.3% | 4.3% | Tie |
| Vals Science Index | Not measured | 31.7% | Only MiMo-V2.6-Flash measured |
| APEX-Agents | 47.3% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| Neither model has a result on the other 28 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index13
| Benchmark | DeepSeek V4 Pro 0813 | MiMo-V2.6-Flash | Leader |
|---|---|---|---|
| GPQA Diamond | 92.4% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| MysteryMechanism (Vals AI) | Not measured | 21.6% | Only MiMo-V2.6-Flash measured |
| GPQA Diamond (Artificial Analysis run) | 92.8% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| Humanity's Last Exam (Artificial Analysis run) | 41.0% | 35.1% | DeepSeek V4 Pro 0813 |
| GPQA Diamond (Epoch AI run) | 91.7% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| ARC-AGI | 90.5% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| ARC-AGI-2 | 61.3% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| Chess puzzles | 46.0% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| Mystery game puzzles | 43.0% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| LMArena Text: hard prompts | 1458 | 1475 | MiMo-V2.6-Flash |
| LMArena Text: expert | 1459 | 1496 | MiMo-V2.6-Flash |
| LMArena Text: hard prompts in English | 1463 | 1493 | MiMo-V2.6-Flash |
| LMArena Vision: diagrams | Not measured | 1276 | Only MiMo-V2.6-Flash measured |
| LMArena Vision: homework | Not measured | 1283 | Only MiMo-V2.6-Flash measured |
| Neither model has a result on the other 7 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | DeepSeek V4 Pro 0813 | MiMo-V2.6-Flash | Leader |
|---|---|---|---|
| OTIS Mock AIME | 98.6% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| FrontierMath, tiers 1 to 3 | 64.6% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| FrontierMath, tier 4 | 26.8% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| ProofBench | 50.0% | 63.0% | MiMo-V2.6-Flash |
| LMArena Text: math | 1441 | 1476 | MiMo-V2.6-Flash |
| LMArena Text: mathematical work | 1443 | 1478 | MiMo-V2.6-Flash |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index32
| Benchmark | DeepSeek V4 Pro 0813 | MiMo-V2.6-Flash | Leader |
|---|---|---|---|
| MMLU Pro | 87.0% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| LegalBench (Vals AI) | 82.4% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| CorpFin (Vals AI) | 65.4% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| TaxEval (Vals AI) | 73.1% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| MedCode (Vals AI) | 42.5% | 41.1% | DeepSeek V4 Pro 0813 |
| SimpleQA Verified | 52.9% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| LMArena Text: science | 1457 | 1462 | MiMo-V2.6-Flash |
| LMArena Text: medicine and healthcare | 1446 | 1439 | DeepSeek V4 Pro 0813 |
| LMArena Text: legal and government | 1459 | 1441 | DeepSeek V4 Pro 0813 |
| LMArena Text: business and finance | 1442 | 1454 | MiMo-V2.6-Flash |
| Neither model has a result on the other 7 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V4 Pro 0813 | MiMo-V2.6-Flash | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index710
| Benchmark | DeepSeek V4 Pro 0813 | MiMo-V2.6-Flash | Leader |
|---|---|---|---|
| Vals Index | 53.0% | 54.8% | MiMo-V2.6-Flash |
| Public Benefits Bench (Vals AI) | Not measured | 67.6% | Only MiMo-V2.6-Flash measured |
| SAGE (Vals AI) | Not measured | 43.5% | Only MiMo-V2.6-Flash measured |
| MedScribe (Vals AI) | 80.2% | 85.3% | MiMo-V2.6-Flash |
| Long context reasoning (AA-LCR) | 80.3% | 74.3% | DeepSeek V4 Pro 0813 |
| DTBench | 93.9% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| LMCA | 45.5% | Not measured | Only DeepSeek V4 Pro 0813 measured |
| LMArena Text | 1446 | 1453 | MiMo-V2.6-Flash |
| LMArena Text: instruction following | 1448 | 1452 | MiMo-V2.6-Flash |
| LMArena Text: creative writing | 1439 | 1403 | DeepSeek V4 Pro 0813 |
| LMArena Vision | Not measured | 1256 | Only MiMo-V2.6-Flash measured |
| LMArena Text: English | 1457 | 1476 | MiMo-V2.6-Flash |
| LMArena Text: non-English | 1431 | 1431 | MiMo-V2.6-Flash |
| LMArena Text: Chinese | 1481 | 1509 | MiMo-V2.6-Flash |
| LMArena Text: German | Not measured | 1458 | Only MiMo-V2.6-Flash measured |
| LMArena Text: Japanese | Not measured | 1359 | Only MiMo-V2.6-Flash measured |
| LMArena Text: Korean | 1449 | 1425 | DeepSeek V4 Pro 0813 |
| LMArena Text: French | 1446 | 1480 | MiMo-V2.6-Flash |
| LMArena Text: Spanish | 1435 | 1453 | MiMo-V2.6-Flash |
| LMArena Text: Russian | 1448 | 1409 | DeepSeek V4 Pro 0813 |
| LMArena Text: Polish | Not measured | 1455 | Only MiMo-V2.6-Flash measured |
| LMArena Text: multi-turn | 1454 | 1447 | DeepSeek V4 Pro 0813 |
| LMArena Text: longer queries | 1458 | 1459 | MiMo-V2.6-Flash |
| LMArena Text: writing and language | 1443 | 1424 | DeepSeek V4 Pro 0813 |
| LMArena Text: entertainment and media | 1424 | 1415 | DeepSeek V4 Pro 0813 |
| LMArena Vision: English | Not measured | 1269 | Only MiMo-V2.6-Flash measured |
| LMArena Vision: reading text | Not measured | 1270 | Only MiMo-V2.6-Flash measured |
| LMArena Vision: creative writing | Not measured | 1231 | Only MiMo-V2.6-Flash measured |
| Neither model has a result on the other 18 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V4 Pro 0813 | MiMo-V2.6-Flash | 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-Flash costs less
Repository review
50K input + 3K output tokens
MiMo-V2.6-Flash costs less
Agent loop
200K input + 10K output tokens
MiMo-V2.6-Flash 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 0813 | Xiaomi MiMo-V2.6-Flash |
|---|---|---|
| Maker | DeepSeek | Xiaomi |
| Weights | Open weights | Open weights |
| Released | August 12, 2026 | September 21, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $0.66 | $0.14 |
| Output $/Mtok | $1.98 | $0.28 |
| Coding index | 54.6 | 61.9 |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | $0.10 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V4 Pro 0813 better than MiMo-V2.6-Flash for coding?
Pick MiMo-V2.6-Flash for coding: it scores 61.9 on the Vibe Coding Index against 54.6 for DeepSeek V4 Pro 0813. Pick DeepSeek V4 Pro 0813 when what matters is Vibe Code Bench (Vals AI) or Code migration (Vals AI), where it leads.
Which is cheaper, DeepSeek V4 Pro 0813 or MiMo-V2.6-Flash?
DeepSeek V4 Pro 0813 costs $0.66 per million input tokens and $1.98 per million output tokens; MiMo-V2.6-Flash costs $0.14 and $0.28. Cost per solved task is known for DeepSeek V4 Pro 0813 only.
Which has the bigger context window, DeepSeek V4 Pro 0813 or MiMo-V2.6-Flash?
MiMo-V2.6-Flash, with 1.05M tokens against 1.05M.
How many benchmarks is the DeepSeek V4 Pro 0813 vs MiMo-V2.6-Flash comparison based on?
51 benchmarks have a result for both models as of October 21, 2026. DeepSeek V4 Pro 0813's coding index rests on 1 independent benchmark and MiMo-V2.6-Flash's on 1. Where only one model has a result, the page says so instead of naming a winner.