Model comparison

Codestral vs Step 1o Turbo 202506

Step 1o Turbo 202506 is the stronger model overall, scoring 39.1 to 30.1 on the Noometry Index.

Last verified . 0 shared benchmarks.

Codestral Mistral AI

30.1

Rank #287 Reported

Step 1o Turbo 202506 StepFun

39.1

Rank #160 Confirmed

Summary

  • The widest gap is in coding, where Step 1o Turbo 202506 leads 38.6 to 26.9.
  • Codestral has downloadable open weights; the other is API-only.

Side by side

Codestral and Step 1o Turbo 202506 specifications
CodestralStep 1o Turbo 202506
ProviderMistral AIStepFun
Noometry Index30.139.1
Released2024-05-29—
WeightsOpenProprietary
Context window256K—
Max output4K—
Input $ / M tokens$0.30—
Output $ / M tokens$0.90—
Results tracked714

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

Category by category

Coding Step 1o Turbo 202506 leads

Codestral: 26.9 (#316), Step 1o Turbo 202506: 38.6 (#158)

Coding benchmarks
BenchmarkCodestralStep 1o Turbo 202506
Aider Polyglot11.1%—
BigCodeBench Instruct41.8%—
LMArena Coding—1339
BigCodeBench Complete52.5%—
ALE-Bench137.78—
HumanEval+73.8%—
MBPP+61.9%—

Reasoning Step 1o Turbo 202506 leads

Codestral: 19.1 (#244), Step 1o Turbo 202506: 25.7 (#127)

Reasoning benchmarks
BenchmarkCodestralStep 1o Turbo 202506
Kagi LLM Benchmark32.5%—
LMArena Hard Prompts—1336

Math Not comparable

Codestral: —, Step 1o Turbo 202506: 33.9 (#163)

Math benchmarks
BenchmarkCodestralStep 1o Turbo 202506
LMArena Math—1318

Knowledge Not comparable

Codestral: —, Step 1o Turbo 202506: 35.5 (#174)

Knowledge benchmarks
BenchmarkCodestralStep 1o Turbo 202506
LMArena Expert—1308

Multimodal Not comparable

Codestral: —, Step 1o Turbo 202506: 35.4 (#75)

Multimodal benchmarks
BenchmarkCodestralStep 1o Turbo 202506
LMArena Vision—1186

Multilingual Not comparable

Codestral: —, Step 1o Turbo 202506: 45.5 (#168)

Multilingual benchmarks
BenchmarkCodestralStep 1o Turbo 202506
LMArena Non-English—1313
LMArena Chinese—1380
LMArena German—1315
LMArena Russian—1327

Instruction Following Not comparable

Codestral: —, Step 1o Turbo 202506: 69.4 (#171)

Instruction Following benchmarks
BenchmarkCodestralStep 1o Turbo 202506
LMArena Instruction Following—1311

Long Context Not comparable

Codestral: —, Step 1o Turbo 202506: 41.1 (#141)

Long Context benchmarks
BenchmarkCodestralStep 1o Turbo 202506
LMArena Longer Query—1350

Writing & Preference Not comparable

Codestral: —, Step 1o Turbo 202506: 53.4 (#154)

Writing & Preference benchmarks
BenchmarkCodestralStep 1o Turbo 202506
LMArena Text—1336
LMArena Creative Writing—1308
LMArena Multi-Turn—1341

Frequently asked questions

Is Codestral better than Step 1o Turbo 202506?

Step 1o Turbo 202506 is the stronger model overall, scoring 39.1 to 30.1 on the Noometry Index.

Is Codestral or Step 1o Turbo 202506 better for coding?

Step 1o Turbo 202506 scores higher on coding benchmarks: 38.6 versus 26.9 in the Noometry coding category.

How many benchmarks do Codestral and Step 1o Turbo 202506 share?

0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Step 1o Turbo 202506 has 14.

Related comparisons

Go deeper