Enter opens the highlighted result. Esc closes.

Devstral 2 2512 vs Step 3.7 Flash

Updated October 21, 2026. 2 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Devstral 2 2512 Replace Step 3.7 Flash
Devstral 2 2512Mistral AI
Coding
No data
Overall
8.6
Output $/M
$2.00
0
Step 3.7 FlashStepFun
Coding
No data
Overall
19.5
Output $/M
$1.15
2
vs boards won of 2 shared

Decision reading

Neither model has a coding score yet, so the two cannot be ranked on coding.

Devstral 2 2512 has the edge where what matters is AA Coding Index or AA Intelligence Index, where it leads.

Model ADevstral 2 2512Mistral AINot benchmarked1 independent benchmark$1.19 per solved taskModel BStep 3.7 FlashStepFunNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
2
Devstral 2 2512 only
4
Step 3.7 Flash only
16
Like-for-like categories
2 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.

At a glance

Coding index
Devstral 2 2512 not benchmarked, Step 3.7 Flash not benchmarked.
Widest category
Intelligence, 10.9 points apart on average over 1 shared benchmark.
Widest single gap
AA Intelligence Index: Devstral 2 2512 8.6 against Step 3.7 Flash 19.5, 10.9 points apart on a 0 to 100 scale.
Output price
Devstral 2 2512 $2.00 against Step 3.7 Flash $1.15 per million output tokens, 1.7x apart.
Context window
Both take 262K tokens.

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.

Boards won, where both have a result
CategoryDevstral 2 2512BarsStep 3.7 FlashTies
Coding01
Intelligence01
All shared boards02
CodingLike-for-likeSix of these boards feed the Vibe Coding Index01
Coding benchmarks for Devstral 2 2512 and Step 3.7 Flash
BenchmarkDevstral 2 2512Step 3.7 FlashLeader
SWE-bench Verified53.8%Not measuredOnly Devstral 2 2512 measured
AA Coding Index31.339.6Step 3.7 Flash
LiveCodeBench (Vals AI)51.8%Not measuredOnly Devstral 2 2512 measured
SWE-bench Verified (Vals AI)62.8%Not measuredOnly Devstral 2 2512 measured
SciCodeNot measured43.9%Only Step 3.7 Flash measured
Terminal-Bench Hard (Artificial Analysis run)Not measured35.6%Only Step 3.7 Flash measured
ALE-BenchNot measured694.1Only Step 3.7 Flash measured
Neither model has a result on the other 31 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Devstral 2 2512 and Step 3.7 Flash
BenchmarkDevstral 2 2512Step 3.7 FlashLeader
AA Intelligence Index8.619.5Step 3.7 Flash
Neither model has a result on the other 1 board here
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Agentic work benchmarks for Devstral 2 2512 and Step 3.7 Flash
BenchmarkDevstral 2 2512Step 3.7 FlashLeader
AA Agentic Index2.3Not measuredOnly Devstral 2 2512 measured
τ²-Bench TelecomNot measured98.5%Only Step 3.7 Flash measured
Neither model has a result on the other 37 boards here
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Reasoning benchmarks for Devstral 2 2512 and Step 3.7 Flash
BenchmarkDevstral 2 2512Step 3.7 FlashLeader
GPQA Diamond (Artificial Analysis run)Not measured80.9%Only Step 3.7 Flash measured
Humanity's Last Exam (Artificial Analysis run)Not measured21.4%Only Step 3.7 Flash measured
Neither model has a result on the other 19 boards here
MathNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Math benchmarks for Devstral 2 2512 and Step 3.7 Flash
BenchmarkDevstral 2 2512Step 3.7 FlashLeader
Neither model has a result on 13 boards here
KnowledgeNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Knowledge benchmarks for Devstral 2 2512 and Step 3.7 Flash
BenchmarkDevstral 2 2512Step 3.7 FlashLeader
Neither model has a result on 17 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for Devstral 2 2512 and Step 3.7 Flash
BenchmarkDevstral 2 2512Step 3.7 FlashLeader
Design Arena: websitesNot measured1196Only Step 3.7 Flash measured
Design Arena: UI componentsNot measured1179Only Step 3.7 Flash measured
Design Arena: game devNot measured1158Only Step 3.7 Flash measured
Design Arena: data vizNot measured1172Only Step 3.7 Flash measured
Design Arena: 3DNot measured1129Only Step 3.7 Flash measured
Design Arena: all code categoriesNot measured1182Only Step 3.7 Flash measured
Design Arena: SVGNot measured1085Only Step 3.7 Flash measured
Design Arena: ASCII artNot measured1152Only Step 3.7 Flash measured
Neither model has a result on the other 1 board here
GeneralDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
General benchmarks for Devstral 2 2512 and Step 3.7 Flash
BenchmarkDevstral 2 2512Step 3.7 FlashLeader
IFBenchNot measured67.3%Only Step 3.7 Flash measured
Long context reasoning (AA-LCR)Not measured73.7%Only Step 3.7 Flash measured
Neither model has a result on the other 44 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Devstral 2 2512 and Step 3.7 Flash
BenchmarkDevstral 2 2512Step 3.7 FlashLeader
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$0.0014Fits in one request
Step 3.7 Flash$0.0008Fits in one request

Step 3.7 Flash costs less

Repository review

50K input + 3K output tokens

Devstral 2 2512$0.026Fits in one request
Step 3.7 Flash$0.013Fits in one request

Step 3.7 Flash costs less

Agent loop

200K input + 10K output tokens

Devstral 2 2512$0.100Fits in one request
Step 3.7 Flash$0.051Fits in one request

Step 3.7 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.

Specifications of Devstral 2 2512 and Step 3.7 Flash
SpecificationMistral Devstral 2 2512StepFun Step 3.7 Flash
MakerMistral AIStepFun
WeightsOpen weightsOpen weights
ReleasedDecember 9, 2025May 28, 2026
Context window262K262K
Input $/Mtok$0.40$0.20
Output $/Mtok$2.00$1.15
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it10
Cost per solved task$1.19Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Devstral 2 2512 better than Step 3.7 Flash for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Devstral 2 2512 has the edge where what matters is AA Coding Index or AA Intelligence Index, where it leads.

Which is cheaper, Devstral 2 2512 or Step 3.7 Flash?

Devstral 2 2512 costs $0.40 per million input tokens and $2.00 per million output tokens; Step 3.7 Flash costs $0.20 and $1.15. Cost per solved task is known for Devstral 2 2512 only.

Which has the bigger context window, Devstral 2 2512 or Step 3.7 Flash?

Neither: both take 262K tokens.

How many benchmarks is the Devstral 2 2512 vs Step 3.7 Flash comparison based on?

2 benchmarks have a result for both models as of October 21, 2026. Devstral 2 2512's coding index rests on 1 independent benchmark and Step 3.7 Flash's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next