Model comparison

Codellama 70b Instruct vs Step 1o Turbo 202506

Step 1o Turbo 202506 is the stronger model overall, scoring 39.7 to 33.7 on the Noometry Index.

Last verified . 4 shared benchmarks.

Codellama 70b Instruct Meta

33.7

Rank #237 Confirmed

Step 1o Turbo 202506 StepFun

39.7

Rank #160 Confirmed

Summary

  • They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 0 categories and Step 1o Turbo 202506 in 5 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in multilingual, where Step 1o Turbo 202506 leads 45.3 to 24.8.
  • Codellama 70b Instruct has downloadable open weights; the other is API-only.

Side by side

Codellama 70b Instruct and Step 1o Turbo 202506 specifications
Codellama 70b InstructStep 1o Turbo 202506
ProviderMetaStepFun
Noometry Index33.739.7
Released——
WeightsOpenProprietary
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked714

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

Category by category

Coding Step 1o Turbo 202506 leads

Codellama 70b Instruct: 37.6 (#193), Step 1o Turbo 202506: 39.2 (#160)

Coding benchmarks
BenchmarkCodellama 70b InstructStep 1o Turbo 202506
BigCodeBench Instruct40.7%—
LMArena Coding—1339
BigCodeBench Complete49.6%—
HumanEval+65.9%—

Reasoning Step 1o Turbo 202506 leads

Codellama 70b Instruct: 20.1 (#242), Step 1o Turbo 202506: 26.8 (#129)

Reasoning benchmarks
BenchmarkCodellama 70b InstructStep 1o Turbo 202506
LMArena Hard Prompts10521335

Math Not comparable

Codellama 70b Instruct: —, Step 1o Turbo 202506: 36.6 (#164)

Math benchmarks
BenchmarkCodellama 70b InstructStep 1o Turbo 202506
LMArena Math—1318

Knowledge Not comparable

Codellama 70b Instruct: —, Step 1o Turbo 202506: 36.1 (#176)

Knowledge benchmarks
BenchmarkCodellama 70b InstructStep 1o Turbo 202506
LMArena Expert—1308

Multimodal Not comparable

Codellama 70b Instruct: —, Step 1o Turbo 202506: 36.1 (#80)

Multimodal benchmarks
BenchmarkCodellama 70b InstructStep 1o Turbo 202506
LMArena Vision—1186

Multilingual Step 1o Turbo 202506 leads

Codellama 70b Instruct: 24.8 (#288), Step 1o Turbo 202506: 45.3 (#173)

Multilingual benchmarks
BenchmarkCodellama 70b InstructStep 1o Turbo 202506
LMArena Non-English9921313
LMArena Chinese—1380
LMArena German—1314
LMArena Russian—1327

Instruction Following Step 1o Turbo 202506 leads

Codellama 70b Instruct: 51.9 (#293), Step 1o Turbo 202506: 69.2 (#176)

Instruction Following benchmarks
BenchmarkCodellama 70b InstructStep 1o Turbo 202506
LMArena Instruction Following10241310

Long Context Not comparable

Codellama 70b Instruct: —, Step 1o Turbo 202506: 41.0 (#146)

Long Context benchmarks
BenchmarkCodellama 70b InstructStep 1o Turbo 202506
LMArena Longer Query—1348

Writing & Preference Step 1o Turbo 202506 leads

Codellama 70b Instruct: 33.4 (#277), Step 1o Turbo 202506: 53.1 (#160)

Writing & Preference benchmarks
BenchmarkCodellama 70b InstructStep 1o Turbo 202506
LMArena Text10571336
LMArena Creative Writing—1307
LMArena Multi-Turn—1340

Frequently asked questions

Is Codellama 70b Instruct better than Step 1o Turbo 202506?

Step 1o Turbo 202506 is the stronger model overall, scoring 39.7 to 33.7 on the Noometry Index.

Is Codellama 70b Instruct or Step 1o Turbo 202506 better for coding?

Step 1o Turbo 202506 scores higher on coding benchmarks: 39.2 versus 37.6 in the Noometry coding category.

How many benchmarks do Codellama 70b Instruct and Step 1o Turbo 202506 share?

4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Step 1o Turbo 202506 has 14.

Related comparisons

Go deeper