Command R (08-2024) vs Devstral 2 2512
Updated October 21, 2026. 0 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
- Coding
- No data
- Overall
- No data
- Output $/M
- $0.60
- Coding
- No data
- Overall
- 8.6
- Output $/M
- $2.00
Decision reading
Neither model has a coding score yet, so the two cannot be ranked on coding.
Command R (08-2024) has the edge where output tokens cost 3.3x less.
- Shared results
- 0
- Command R (08-2024) only
- 25
- Devstral 2 2512 only
- 6
- Like-for-like categories
- 0 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, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
No call
Only Devstral 2 2512 has a AA Intelligence Index result, 8.6.
Directional only
Agentic work
AA Agentic Index
No call
Only Devstral 2 2512 has a AA Agentic Index result, 2.3.
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
Command R (08-2024)
Command R (08-2024) $0.0004, 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
- Command R (08-2024) not benchmarked, Devstral 2 2512 not benchmarked.
- Widest category
- No category has a result for both models.
- Widest single gap
- No benchmark has a result for both models.
- Output price
- Command R (08-2024) $0.60 against Devstral 2 2512 $2.00 per million output tokens, 3.3x apart.
- Context window
- Command R (08-2024) takes 128K 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.
CodingDirectional onlySix of these boards feed the Vibe Coding Index6 boards, none shared
| Benchmark | Command R (08-2024) | Devstral 2 2512 | Leader |
|---|---|---|---|
| SWE-bench Verified | Not measured | 53.8% | Only Devstral 2 2512 measured |
| AA Coding Index | Not measured | 31.3 | Only Devstral 2 2512 measured |
| LiveCodeBench (Vals AI) | Not measured | 51.8% | Only Devstral 2 2512 measured |
| SWE-bench Verified (Vals AI) | Not measured | 62.8% | Only Devstral 2 2512 measured |
| LMArena Text: coding | 1187 | Not measured | Only Command R (08-2024) measured |
| LMArena Text: software and IT | 1197 | Not measured | Only Command R (08-2024) measured |
| Neither model has a result on the other 32 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Command R (08-2024) | Devstral 2 2512 | Leader |
|---|---|---|---|
| AA Intelligence Index | Not measured | 8.6 | Only Devstral 2 2512 measured |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Command R (08-2024) | Devstral 2 2512 | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 2.3 | Only Devstral 2 2512 measured |
| Neither model has a result on the other 38 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | Command R (08-2024) | Devstral 2 2512 | Leader |
|---|---|---|---|
| LMArena Text: hard prompts | 1186 | Not measured | Only Command R (08-2024) measured |
| LMArena Text: expert | 1173 | Not measured | Only Command R (08-2024) measured |
| LMArena Text: hard prompts in English | 1194 | Not measured | Only Command R (08-2024) measured |
| Neither model has a result on the other 18 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Command R (08-2024) | Devstral 2 2512 | Leader |
|---|---|---|---|
| LMArena Text: math | 1188 | Not measured | Only Command R (08-2024) measured |
| LMArena Text: mathematical work | 1198 | Not measured | Only Command R (08-2024) measured |
| Neither model has a result on the other 11 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | Command R (08-2024) | Devstral 2 2512 | Leader |
|---|---|---|---|
| LMArena Text: science | 1252 | Not measured | Only Command R (08-2024) measured |
| LMArena Text: medicine and healthcare | 1238 | Not measured | Only Command R (08-2024) measured |
| LMArena Text: legal and government | 1268 | Not measured | Only Command R (08-2024) measured |
| LMArena Text: business and finance | 1215 | Not measured | Only Command R (08-2024) measured |
| Neither model has a result on the other 13 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Command R (08-2024) | Devstral 2 2512 | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index14 boards, none shared
| Benchmark | Command R (08-2024) | Devstral 2 2512 | Leader |
|---|---|---|---|
| LMArena Text | 1229 | Not measured | Only Command R (08-2024) measured |
| LMArena Text: instruction following | 1197 | Not measured | Only Command R (08-2024) measured |
| LMArena Text: creative writing | 1234 | Not measured | Only Command R (08-2024) measured |
| LMArena Text: English | 1238 | Not measured | Only Command R (08-2024) measured |
| LMArena Text: non-English | 1216 | Not measured | Only Command R (08-2024) measured |
| LMArena Text: Chinese | 1227 | Not measured | Only Command R (08-2024) measured |
| LMArena Text: German | 1216 | Not measured | Only Command R (08-2024) measured |
| LMArena Text: Japanese | 1166 | Not measured | Only Command R (08-2024) measured |
| LMArena Text: Korean | 1162 | Not measured | Only Command R (08-2024) measured |
| LMArena Text: Russian | 1227 | Not measured | Only Command R (08-2024) measured |
| LMArena Text: multi-turn | 1213 | Not measured | Only Command R (08-2024) measured |
| LMArena Text: longer queries | 1230 | Not measured | Only Command R (08-2024) measured |
| LMArena Text: writing and language | 1241 | Not measured | Only Command R (08-2024) measured |
| LMArena Text: entertainment and media | 1223 | Not measured | Only Command R (08-2024) measured |
| Neither model has a result on the other 32 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Command R (08-2024) | 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
Command R (08-2024) costs less
Repository review
50K input + 3K output tokens
Command R (08-2024) costs less
Agent loop
200K input + 10K output tokens
Command R (08-2024) 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 | Cohere Command R (08-2024) | Mistral Devstral 2 2512 |
|---|---|---|
| Maker | Cohere | Mistral AI |
| Weights | No public weights listed | Open weights |
| Released | August 30, 2024 | December 9, 2025 |
| Context window | 128K | 262K |
| Input $/Mtok | $0.15 | $0.40 |
| Output $/Mtok | $0.60 | $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 Command R (08-2024) better than Devstral 2 2512 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Command R (08-2024) has the edge where output tokens cost 3.3x less.
Which is cheaper, Command R (08-2024) or Devstral 2 2512?
Command R (08-2024) costs $0.15 per million input tokens and $0.60 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, Command R (08-2024) or Devstral 2 2512?
Devstral 2 2512, with 262K tokens against 128K.
How many benchmarks is the Command R (08-2024) vs Devstral 2 2512 comparison based on?
0 benchmarks have a result for both models as of October 21, 2026. Command R (08-2024)'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.