Model comparison

Devstral Small 2505 vs Step 1o Turbo 202506

Step 1o Turbo 202506 is the stronger model overall, scoring 39.7 to 34.3 on the Noometry Index.

Last verified . 0 shared benchmarks.

Devstral Small 2505 Mistral AI

34.3

Rank #233 Reported

Step 1o Turbo 202506 StepFun

39.7

Rank #160 Confirmed

Summary

  • The widest gap is in reasoning, where Step 1o Turbo 202506 leads 26.8 to 19.7.
  • Devstral Small 2505 has downloadable open weights; the other is API-only.

Side by side

Devstral Small 2505 and Step 1o Turbo 202506 specifications
Devstral Small 2505Step 1o Turbo 202506
ProviderMistral AIStepFun
Noometry Index34.339.7
Released2025-05-07—
WeightsOpenProprietary
Context window128K—
Max output128K—
Input $ / M tokens$0.10—
Output $ / M tokens$0.30—
Results tracked414

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Too close to call

Devstral Small 2505: 38.9 (#166), Step 1o Turbo 202506: 39.2 (#160)

Coding benchmarks
BenchmarkDevstral Small 2505Step 1o Turbo 202506
SWE-bench Verified (bash only)56.4%—
SciCode28.8%—
LMArena Coding—1339

Reasoning Step 1o Turbo 202506 leads

Devstral Small 2505: 19.7 (#252), Step 1o Turbo 202506: 26.8 (#129)

Reasoning benchmarks
BenchmarkDevstral Small 2505Step 1o Turbo 202506
Kagi LLM Benchmark37.7%—
CritPt0%—
LMArena Hard Prompts—1335

Math Not comparable

Devstral Small 2505: —, Step 1o Turbo 202506: 36.6 (#164)

Math benchmarks
BenchmarkDevstral Small 2505Step 1o Turbo 202506
LMArena Math—1318

Knowledge Not comparable

Devstral Small 2505: —, Step 1o Turbo 202506: 36.1 (#176)

Knowledge benchmarks
BenchmarkDevstral Small 2505Step 1o Turbo 202506
LMArena Expert—1308

Multimodal Not comparable

Devstral Small 2505: —, Step 1o Turbo 202506: 36.1 (#80)

Multimodal benchmarks
BenchmarkDevstral Small 2505Step 1o Turbo 202506
LMArena Vision—1186

Multilingual Not comparable

Devstral Small 2505: —, Step 1o Turbo 202506: 45.3 (#173)

Multilingual benchmarks
BenchmarkDevstral Small 2505Step 1o Turbo 202506
LMArena Non-English—1313
LMArena Chinese—1380
LMArena German—1314
LMArena Russian—1327

Instruction Following Not comparable

Devstral Small 2505: —, Step 1o Turbo 202506: 69.2 (#176)

Instruction Following benchmarks
BenchmarkDevstral Small 2505Step 1o Turbo 202506
LMArena Instruction Following—1310

Long Context Not comparable

Devstral Small 2505: —, Step 1o Turbo 202506: 41.0 (#146)

Long Context benchmarks
BenchmarkDevstral Small 2505Step 1o Turbo 202506
LMArena Longer Query—1348

Writing & Preference Not comparable

Devstral Small 2505: —, Step 1o Turbo 202506: 53.1 (#160)

Writing & Preference benchmarks
BenchmarkDevstral Small 2505Step 1o Turbo 202506
LMArena Text—1336
LMArena Creative Writing—1307
LMArena Multi-Turn—1340

Frequently asked questions

Is Devstral Small 2505 better than Step 1o Turbo 202506?

Step 1o Turbo 202506 is the stronger model overall, scoring 39.7 to 34.3 on the Noometry Index.

Is Devstral Small 2505 or Step 1o Turbo 202506 better for coding?

They score almost the same on coding (38.9 vs 39.2); test both on your own repository before choosing.

How many benchmarks do Devstral Small 2505 and Step 1o Turbo 202506 share?

0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Step 1o Turbo 202506 has 14.

Related comparisons

Go deeper