Devstral 2 2512 vs Qwen3 235B A22B Thinking 2507
Qwen3 235B A22B Thinking 2507 leads Devstral 2 2512 on the Artificial Analysis Intelligence Index, 12.7 to 8.6, and Devstral 2 2512 costs 1.8x less per output token ($2.00 vs $3.50 per million). Updated October 22, 2026; 3 benchmarks have a result for both.
Devstral 2 2512 or Qwen3 235B A22B Thinking 2507: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Devstral 2 2512 for output tokens 1.8x cheaper ($2.00 vs $3.50 per million) and a larger context window (262K against 128K tokens).
- Shared results
- 3
- Devstral 2 2512 only
- 3
- Qwen3 235B A22B Thinking 2507 only
- 43
- 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
Qwen3 235B A22B Thinking 2507
Qwen3 235B A22B Thinking 2507 leads, 12.7 against 8.6.
Same board, both measured
Agentic work
AA Agentic Index
Devstral 2 2512
Devstral 2 2512 leads, 2.3 against 1.3.
Same board, both measured
Web design
Design Arena: websites
No call
Only Qwen3 235B A22B Thinking 2507 has a Design Arena: websites result, 1052.
Directional only
Long documents
Listed context window
Devstral 2 2512
Devstral 2 2512 takes 262K tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Devstral 2 2512
Devstral 2 2512 $0.0014, Qwen3 235B A22B Thinking 2507 $0.0022 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
- Devstral 2 2512 not benchmarked, Qwen3 235B A22B Thinking 2507 not benchmarked.
- Widest category
- Coding, 9.2 points apart on average over 1 shared benchmark.
- Widest single gap
- AA Coding Index: Devstral 2 2512 31.3 against Qwen3 235B A22B Thinking 2507 22.1, 9.2 points apart on a 0 to 100 scale.
- Output price
- Devstral 2 2512 $2.00 against Qwen3 235B A22B Thinking 2507 $3.50 per million output tokens, 1.8x apart.
- Context window
- Devstral 2 2512 takes 262K tokens, Qwen3 235B A22B Thinking 2507 128K.
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 | Devstral 2 2512 | Bars | Qwen3 235B A22B Thinking 2507 | Ties |
|---|---|---|---|---|
| Coding | 1 | 0 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 1 | 0 | ||
| All shared boards | 2 | 1 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index10
| Benchmark | Devstral 2 2512 | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| SWE-bench Verified | 53.8% | Not measured | Only Devstral 2 2512 measured |
| AA Coding Index | 31.3 | 22.1 | Devstral 2 2512 |
| LiveCodeBench (Vals AI) | 51.8% | Not measured | Only Devstral 2 2512 measured |
| SWE-bench Verified (Vals AI) | 62.8% | Not measured | Only Devstral 2 2512 measured |
| WeirdML | Not measured | 41.0% | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: coding | Not measured | 1424 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: software and IT | Not measured | 1431 | Only Qwen3 235B A22B Thinking 2507 measured |
| Neither model has a result on the other 32 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Devstral 2 2512 | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| AA Intelligence Index | 8.6 | 12.7 | Qwen3 235B A22B Thinking 2507 |
| Neither model has a result on the other 1 board here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Devstral 2 2512 | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| AA Agentic Index | 2.3 | 1.3 | Devstral 2 2512 |
| Vending-Bench 2 | Not measured | -$11 | Only Qwen3 235B A22B Thinking 2507 measured |
| Neither model has a result on the other 39 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | Devstral 2 2512 | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| GPQA Diamond (Epoch AI run) | Not measured | 80.1% | Only Qwen3 235B A22B Thinking 2507 measured |
| Mystery game puzzles | Not measured | 9.0% | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: hard prompts | Not measured | 1416 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: expert | Not measured | 1463 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: hard prompts in English | Not measured | 1432 | Only Qwen3 235B A22B Thinking 2507 measured |
| Neither model has a result on the other 17 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | Devstral 2 2512 | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| OTIS Mock AIME | Not measured | 86.7% | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: math | Not measured | 1412 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: mathematical work | Not measured | 1435 | Only Qwen3 235B A22B Thinking 2507 measured |
| Neither model has a result on the other 10 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | Devstral 2 2512 | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| SimpleQA Verified | Not measured | 40.4% | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: science | Not measured | 1433 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: medicine and healthcare | Not measured | 1456 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: legal and government | Not measured | 1415 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: business and finance | Not measured | 1413 | Only Qwen3 235B A22B Thinking 2507 measured |
| Neither model has a result on the other 13 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Devstral 2 2512 | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1052 | Only Qwen3 235B A22B Thinking 2507 measured |
| Design Arena: UI components | Not measured | 942 | Only Qwen3 235B A22B Thinking 2507 measured |
| Design Arena: game dev | Not measured | 956 | Only Qwen3 235B A22B Thinking 2507 measured |
| Design Arena: data viz | Not measured | 950 | Only Qwen3 235B A22B Thinking 2507 measured |
| Design Arena: 3D | Not measured | 997 | Only Qwen3 235B A22B Thinking 2507 measured |
| Design Arena: all code categories | Not measured | 1032 | Only Qwen3 235B A22B Thinking 2507 measured |
| Neither model has a result on the other 3 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index20 boards, none shared
| Benchmark | Devstral 2 2512 | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| DTBench | Not measured | 80.3% | Only Qwen3 235B A22B Thinking 2507 measured |
| LMCA | Not measured | 29.3% | Only Qwen3 235B A22B Thinking 2507 measured |
| Fiction.LiveBench | Not measured | 75.0% | Only Qwen3 235B A22B Thinking 2507 measured |
| Creative writing (Lech Mazur) | Not measured | 82.4% | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text | Not measured | 1415 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: instruction following | Not measured | 1386 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: creative writing | Not measured | 1384 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: English | Not measured | 1429 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: non-English | Not measured | 1397 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: Chinese | Not measured | 1481 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: German | Not measured | 1408 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: Japanese | Not measured | 1386 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: Korean | Not measured | 1375 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: Spanish | Not measured | 1389 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: Russian | Not measured | 1401 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: Polish | Not measured | 1390 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: multi-turn | Not measured | 1406 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: longer queries | Not measured | 1400 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: writing and language | Not measured | 1388 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: entertainment and media | Not measured | 1370 | Only Qwen3 235B A22B Thinking 2507 measured |
| Neither model has a result on the other 26 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Devstral 2 2512 | Qwen3 235B A22B Thinking 2507 | 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
Devstral 2 2512 costs less
Repository review
50K input + 3K output tokens
Devstral 2 2512 costs less
Agent loop
200K input + 10K output tokens
Devstral 2 2512 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 | Mistral Devstral 2 2512 | Qwen3 235B A22B Thinking 2507 |
|---|---|---|
| Maker | Mistral AI | Qwen |
| Weights | Open weights | Open weights |
| Released | December 9, 2025 | July 25, 2025 |
| Context window | 262K | 128K |
| Input $/Mtok | $0.40 | $0.45 |
| Output $/Mtok | $2.00 | $3.50 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 1 | 0 |
| Cost per solved task | $1.19 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Devstral 2 2512 better than Qwen3 235B A22B Thinking 2507 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Devstral 2 2512 for output tokens 1.8x cheaper ($2.00 vs $3.50 per million) and a larger context window (262K against 128K tokens).
Which is cheaper, Devstral 2 2512 or Qwen3 235B A22B Thinking 2507?
Devstral 2 2512 costs $0.40 per million input tokens and $2.00 per million output tokens; Qwen3 235B A22B Thinking 2507 costs $0.45 and $3.50. Cost per solved task is known for Devstral 2 2512 only.
Which has the bigger context window, Devstral 2 2512 or Qwen3 235B A22B Thinking 2507?
Devstral 2 2512, with 262K tokens against 128K.
How many benchmarks is the Devstral 2 2512 vs Qwen3 235B A22B Thinking 2507 comparison based on?
3 benchmarks have a result for both models as of October 22, 2026. Devstral 2 2512's coding index rests on 1 independent benchmark and Qwen3 235B A22B Thinking 2507's on 0. Where only one model has a result, the page says so instead of naming a winner.