DeepSeek V3 0324 vs Devstral 2 2512
DeepSeek V3 0324 leads Devstral 2 2512 on the Artificial Analysis Intelligence Index, 9.7 to 8.6, and DeepSeek V3 0324 costs 1.9x less per output token ($1.07 vs $2.00 per million). Updated October 22, 2026; 5 benchmarks have a result for both.
DeepSeek V3 0324 or Devstral 2 2512: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick DeepSeek V3 0324 for output tokens 1.9x cheaper ($1.07 vs $2.00 per million) and work measured by SWE-bench Verified or AA Coding Index, where it leads.
- Shared results
- 5
- DeepSeek V3 0324 only
- 30
- Devstral 2 2512 only
- 1
- Like-for-like categories
- 3 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
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
DeepSeek V3 0324
DeepSeek V3 0324 leads, 9.7 against 8.6.
Same board, both measured
Agentic work
AA Agentic Index
Devstral 2 2512
Devstral 2 2512 leads, 2.3 against 0.8.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only DeepSeek V3 0324 has a GPQA Diamond result, 61.6%.
Directional only
Math
AIME
No call
Only DeepSeek V3 0324 has a AIME result, 52.2%.
Directional only
Knowledge
MMLU Pro
No call
Only DeepSeek V3 0324 has a MMLU Pro result, 79.5%.
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 0324
DeepSeek V3 0324 $0.0008, Devstral 2 2512 $0.0014 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Devstral 2 2512 has the number, $1.19.
Directional only
At a glance
- Coding index
- DeepSeek V3 0324 not benchmarked, Devstral 2 2512 not benchmarked.
- Widest category
- Coding, 11.8 points apart on average over 3 shared benchmarks.
- Widest single gap
- LiveCodeBench (Vals AI): DeepSeek V3 0324 65.5% against Devstral 2 2512 51.8%, 13.6 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V3 0324 $1.07 against Devstral 2 2512 $2.00 per million output tokens, 1.9x apart.
- Context window
- DeepSeek V3 0324 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 0324 | Bars | Devstral 2 2512 | Ties |
|---|---|---|---|---|
| Coding | 1 | 2 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 0 | 1 | ||
| All shared boards | 2 | 3 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index12
| Benchmark | DeepSeek V3 0324 | Devstral 2 2512 | Leader |
|---|---|---|---|
| SWE-bench Verified | 42.0% | 53.8% | Devstral 2 2512 |
| AA Coding Index | 21.2 | 31.3 | Devstral 2 2512 |
| LiveCodeBench (Vals AI) | 65.5% | 51.8% | DeepSeek V3 0324 |
| SWE-bench Verified (Vals AI) | Not measured | 62.8% | Only Devstral 2 2512 measured |
| LiveCodeBench (Artificial Analysis run) | 40.5% | Not measured | Only DeepSeek V3 0324 measured |
| SciCode | 39.0% | Not measured | Only DeepSeek V3 0324 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 15.2% | Not measured | Only DeepSeek V3 0324 measured |
| WeirdML | 36.1% | Not measured | Only DeepSeek V3 0324 measured |
| Neither model has a result on the other 31 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | DeepSeek V3 0324 | Devstral 2 2512 | Leader |
|---|---|---|---|
| AA Intelligence Index | 9.7 | 8.6 | DeepSeek V3 0324 |
| Neither model has a result on the other 1 board here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3 0324 | Devstral 2 2512 | Leader |
|---|---|---|---|
| AA Agentic Index | 0.8 | 2.3 | Devstral 2 2512 |
| τ²-Bench Telecom | 47.1% | Not measured | Only DeepSeek V3 0324 measured |
| METR time horizons | 49.6% | Not measured | Only DeepSeek V3 0324 measured |
| Neither model has a result on the other 38 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | DeepSeek V3 0324 | Devstral 2 2512 | Leader |
|---|---|---|---|
| GPQA Diamond | 61.6% | Not measured | Only DeepSeek V3 0324 measured |
| GPQA Diamond (Artificial Analysis run) | 65.5% | Not measured | Only DeepSeek V3 0324 measured |
| Humanity's Last Exam (Artificial Analysis run) | 4.7% | Not measured | Only DeepSeek V3 0324 measured |
| GPQA Diamond (Epoch AI run) | 67.6% | Not measured | Only DeepSeek V3 0324 measured |
| SimpleBench | 27.2% | Not measured | Only DeepSeek V3 0324 measured |
| Neither model has a result on the other 17 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | DeepSeek V3 0324 | Devstral 2 2512 | Leader |
|---|---|---|---|
| AIME | 52.2% | Not measured | Only DeepSeek V3 0324 measured |
| MATH 500 (Vals AI) | 88.6% | Not measured | Only DeepSeek V3 0324 measured |
| MGSM (Vals AI) | 91.7% | Not measured | Only DeepSeek V3 0324 measured |
| AA Math Index | 41.0 | Not measured | Only DeepSeek V3 0324 measured |
| AIME 2025 (Artificial Analysis run) | 41.0% | Not measured | Only DeepSeek V3 0324 measured |
| OTIS Mock AIME | 37.8% | Not measured | Only DeepSeek V3 0324 measured |
| MATH level 5 | 75.5% | Not measured | Only DeepSeek V3 0324 measured |
| Neither model has a result on the other 6 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | DeepSeek V3 0324 | Devstral 2 2512 | Leader |
|---|---|---|---|
| MMLU Pro | 79.5% | Not measured | Only DeepSeek V3 0324 measured |
| LegalBench (Vals AI) | 77.7% | Not measured | Only DeepSeek V3 0324 measured |
| CorpFin (Vals AI) | 54.7% | Not measured | Only DeepSeek V3 0324 measured |
| TaxEval (Vals AI) | 71.1% | Not measured | Only DeepSeek V3 0324 measured |
| MedQA (Vals AI) | 82.0% | Not measured | Only DeepSeek V3 0324 measured |
| MMLU Pro (Artificial Analysis run) | 81.9% | Not measured | Only DeepSeek V3 0324 measured |
| Neither model has a result on the other 12 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V3 0324 | Devstral 2 2512 | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | DeepSeek V3 0324 | Devstral 2 2512 | Leader |
|---|---|---|---|
| IFBench | 41.0% | Not measured | Only DeepSeek V3 0324 measured |
| Long context reasoning (AA-LCR) | 40.7% | Not measured | Only DeepSeek V3 0324 measured |
| DTBench | 64.8% | Not measured | Only DeepSeek V3 0324 measured |
| LMCA | 15.5% | Not measured | Only DeepSeek V3 0324 measured |
| Fiction.LiveBench | 50.0% | Not measured | Only DeepSeek V3 0324 measured |
| Creative writing (Lech Mazur) | 77.0% | Not measured | Only DeepSeek V3 0324 measured |
| Neither model has a result on the other 40 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V3 0324 | 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 0324 costs less
Repository review
50K input + 3K output tokens
DeepSeek V3 0324 costs less
Agent loop
200K input + 10K output tokens
DeepSeek V3 0324 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 0324 | Mistral Devstral 2 2512 |
|---|---|---|
| Maker | DeepSeek | Mistral AI |
| Weights | Open weights | Open weights |
| Released | March 24, 2025 | December 9, 2025 |
| Context window | 164K | 262K |
| Input $/Mtok | $0.27 | $0.40 |
| Output $/Mtok | $1.07 | $2.00 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 1 |
| Cost per solved task | Not computable | $1.19 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V3 0324 better than Devstral 2 2512 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick DeepSeek V3 0324 for output tokens 1.9x cheaper ($1.07 vs $2.00 per million) and work measured by SWE-bench Verified or AA Coding Index, where it leads.
Which is cheaper, DeepSeek V3 0324 or Devstral 2 2512?
DeepSeek V3 0324 costs $0.27 per million input tokens and $1.07 per million output tokens; Devstral 2 2512 costs $0.40 and $2.00. Cost per solved task is known for Devstral 2 2512 only.
Which has the bigger context window, DeepSeek V3 0324 or Devstral 2 2512?
Devstral 2 2512, with 262K tokens against 164K.
How many benchmarks is the DeepSeek V3 0324 vs Devstral 2 2512 comparison based on?
5 benchmarks have a result for both models as of October 22, 2026. DeepSeek V3 0324's coding index rests on 0 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.