DeepSeek V3.2 vs Devstral 2 2512
DeepSeek V3.2 leads Devstral 2 2512 on the Artificial Analysis Intelligence Index, 21.5 to 8.6, and DeepSeek V3.2 costs 2.3x less per output token ($0.88 vs $2.00 per million). Updated October 21, 2026; 5 benchmarks have a result for both.
DeepSeek V3.2 or Devstral 2 2512: which to pick
Only DeepSeek V3.2 has a coding score, 30.0 on the Vibe Coding Index; Devstral 2 2512 has none, so the two cannot be ranked on coding.
Pick Devstral 2 2512 for a larger context window (262K against 164K tokens).
- Shared results
- 5
- DeepSeek V3.2 only
- 70
- Devstral 2 2512 only
- 1
- Like-for-like categories
- 2 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 DeepSeek V3.2 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
DeepSeek V3.2
DeepSeek V3.2 leads, 21.5 against 8.6.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Devstral 2 2512 has a AA Agentic Index result, 2.3.
Directional only
Reasoning
GPQA Diamond
No call
Only DeepSeek V3.2 has a GPQA Diamond result, 80.3%.
Directional only
Math
AIME
No call
Only DeepSeek V3.2 has a AIME result, 84.6%.
Directional only
Knowledge
MMLU Pro
No call
Only DeepSeek V3.2 has a MMLU Pro result, 84.9%.
Directional only
Web design
Design Arena: websites
No call
Only DeepSeek V3.2 has a Design Arena: websites result, 1175.
Directional only
Long documents
Listed context window
Devstral 2 2512
Devstral 2 2512 takes 262K tokens against 164K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V3.2
DeepSeek V3.2 $0.0007, Devstral 2 2512 $0.0014 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
DeepSeek V3.2
DeepSeek V3.2 $0.99, Devstral 2 2512 $1.19.
Published attempt cost and pass rate
At a glance
- Coding index
- DeepSeek V3.2 30.0 from 3 benchmarks, Devstral 2 2512 not benchmarked.
- Widest category
- Coding, 15.7 points apart on average over 4 shared benchmarks.
- Widest single gap
- LiveCodeBench (Vals AI): DeepSeek V3.2 80.7% against Devstral 2 2512 51.8%, 28.8 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V3.2 $0.88 against Devstral 2 2512 $2.00 per million output tokens, 2.3x apart.
- Context window
- DeepSeek V3.2 takes 164K tokens, Devstral 2 2512 262K.
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 | Devstral 2 2512 | Ties |
|---|---|---|---|---|
| Coding | 4 | 0 | ||
| Intelligence | 1 | 0 | ||
| All shared boards | 5 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index40
| Benchmark | DeepSeek V3.2 | Devstral 2 2512 | Leader |
|---|---|---|---|
| SWE-bench Verified | 70.0% | 53.8% | DeepSeek V3.2 |
| SWE-bench Multilingual | 59.0% | Not measured | Only DeepSeek V3.2 measured |
| LMArena WebDev | 1362 | Not measured | Only DeepSeek V3.2 measured |
| AA Coding Index | 44.2 | 31.3 | DeepSeek V3.2 |
| LiveCodeBench (Vals AI) | 80.7% | 51.8% | DeepSeek V3.2 |
| SWE-bench Verified (Vals AI) | 67.6% | 62.8% | DeepSeek V3.2 |
| Vibe Code Bench (Vals AI) | 5.1% | Not measured | Only DeepSeek V3.2 measured |
| LiveCodeBench (Artificial Analysis run) | 86.2% | Not measured | Only DeepSeek V3.2 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 35.6% | Not measured | Only DeepSeek V3.2 measured |
| Terminal-Bench | 39.6% | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: coding | 1453 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: software and IT | 1449 | Not measured | Only DeepSeek V3.2 measured |
| LMArena WebDev: React | 1350 | Not measured | Only DeepSeek V3.2 measured |
| LMArena WebDev: HTML | 1371 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 25 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | DeepSeek V3.2 | Devstral 2 2512 | Leader |
|---|---|---|---|
| AA Intelligence Index | 21.5 | 8.6 | DeepSeek V3.2 |
| Epoch Capabilities Index | 146.1 | Not measured | Only DeepSeek V3.2 measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | DeepSeek V3.2 | Devstral 2 2512 | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 2.3 | Only Devstral 2 2512 measured |
| τ²-Bench Telecom | 90.6% | Not measured | Only DeepSeek V3.2 measured |
| 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 37 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | DeepSeek V3.2 | Devstral 2 2512 | Leader |
|---|---|---|---|
| GPQA Diamond | 80.3% | Not measured | Only DeepSeek V3.2 measured |
| GPQA Diamond (Artificial Analysis run) | 84.0% | Not measured | Only DeepSeek V3.2 measured |
| Humanity's Last Exam (Artificial Analysis run) | 24.6% | Not measured | Only DeepSeek V3.2 measured |
| 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 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: expert | 1436 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: hard prompts in English | 1446 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 14 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | DeepSeek V3.2 | Devstral 2 2512 | 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 |
| LMArena Text: math | 1435 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: mathematical work | 1440 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index11 boards, none shared
| Benchmark | DeepSeek V3.2 | Devstral 2 2512 | Leader |
|---|---|---|---|
| MMLU Pro | 84.9% | Not measured | Only DeepSeek V3.2 measured |
| LegalBench (Vals AI) | 76.1% | Not measured | Only DeepSeek V3.2 measured |
| CaseLaw (Vals AI) | 55.4% | Not measured | Only DeepSeek V3.2 measured |
| CorpFin (Vals AI) | 51.0% | Not measured | Only DeepSeek V3.2 measured |
| TaxEval (Vals AI) | 68.2% | Not measured | Only DeepSeek V3.2 measured |
| MedQA (Vals AI) | 93.9% | Not measured | Only DeepSeek V3.2 measured |
| MMLU Pro (Artificial Analysis run) | 86.2% | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: science | 1446 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: medicine and healthcare | 1440 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: legal and government | 1425 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: business and finance | 1410 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 7 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | DeepSeek V3.2 | Devstral 2 2512 | Leader |
|---|---|---|---|
| Design Arena: websites | 1175 | Not measured | Only DeepSeek V3.2 measured |
| Design Arena: UI components | 1149 | Not measured | Only DeepSeek V3.2 measured |
| Design Arena: game dev | 1132 | Not measured | Only DeepSeek V3.2 measured |
| Design Arena: data viz | 1158 | Not measured | Only DeepSeek V3.2 measured |
| Design Arena: 3D | 1133 | Not measured | Only DeepSeek V3.2 measured |
| Design Arena: all code categories | 1164 | Not measured | Only DeepSeek V3.2 measured |
| Design Arena: SVG | 1032 | Not measured | Only DeepSeek V3.2 measured |
| Design Arena: ASCII art | 1083 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 1 board here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index23 boards, none shared
| Benchmark | DeepSeek V3.2 | Devstral 2 2512 | Leader |
|---|---|---|---|
| IFBench | 60.7% | Not measured | Only DeepSeek V3.2 measured |
| Long context reasoning (AA-LCR) | 73.3% | Not measured | Only DeepSeek V3.2 measured |
| DTBench | 85.6% | Not measured | Only DeepSeek V3.2 measured |
| LMCA | 28.8% | Not measured | Only DeepSeek V3.2 measured |
| 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 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: instruction following | 1413 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: creative writing | 1400 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: English | 1439 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: non-English | 1409 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Chinese | 1455 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: German | 1413 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Japanese | 1374 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Korean | 1370 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: French | 1429 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Spanish | 1424 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Russian | 1424 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: Polish | 1419 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: multi-turn | 1427 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: longer queries | 1428 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: writing and language | 1407 | Not measured | Only DeepSeek V3.2 measured |
| LMArena Text: entertainment and media | 1395 | Not measured | Only DeepSeek V3.2 measured |
| Neither model has a result on the other 23 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V3.2 | Devstral 2 2512 | 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 | Mistral Devstral 2 2512 |
|---|---|---|
| Maker | DeepSeek | Mistral AI |
| Weights | Open weights | Open weights |
| Released | December 1, 2025 | December 9, 2025 |
| Context window | 164K | 262K |
| Input $/Mtok | $0.29 | $0.40 |
| Output $/Mtok | $0.88 | $2.00 |
| Coding index | 30.0 | Not benchmarked |
| Independent measurements behind it | 3 | 1 |
| Cost per solved task | $0.99 | $1.19 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V3.2 better than Devstral 2 2512 for coding?
Only DeepSeek V3.2 has a coding score, 30.0 on the Vibe Coding Index; Devstral 2 2512 has none, so the two cannot be ranked on coding. Pick Devstral 2 2512 for a larger context window (262K against 164K tokens).
Which is cheaper, DeepSeek V3.2 or Devstral 2 2512?
DeepSeek V3.2 costs $0.29 per million input tokens and $0.88 per million output tokens; Devstral 2 2512 costs $0.40 and $2.00. Per solved SWE-bench Verified task, DeepSeek V3.2 costs $0.99 and Devstral 2 2512 $1.19.
Which has the bigger context window, DeepSeek V3.2 or Devstral 2 2512?
Devstral 2 2512, with 262K tokens against 164K.
How many benchmarks is the DeepSeek V3.2 vs Devstral 2 2512 comparison based on?
5 benchmarks have a result for both models as of October 21, 2026. DeepSeek V3.2's coding index rests on 3 independent benchmarks and Devstral 2 2512's on 1. Where only one model has a result, the page says so instead of naming a winner.