Model comparison

Codellama 70b Instruct vs Step 2 16k Exp 202412

Step 2 16k Exp 202412 is the stronger model overall, scoring 39.2 to 33.7 on the Noometry Index.

Last verified . 4 shared benchmarks.

Codellama 70b Instruct Meta

33.7

Rank #237 Confirmed

Step 2 16k Exp 202412 StepFun

39.2

Rank #171 Confirmed

Summary

  • They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 0 categories and Step 2 16k Exp 202412 in 5 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in multilingual, where Step 2 16k Exp 202412 leads 43.7 to 24.8.
  • Codellama 70b Instruct has downloadable open weights; the other is API-only.

Side by side

Codellama 70b Instruct and Step 2 16k Exp 202412 specifications
Codellama 70b InstructStep 2 16k Exp 202412
ProviderMetaStepFun
Noometry Index33.739.2
Released——
WeightsOpenProprietary
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked712

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

Category by category

Coding Too close to call

Codellama 70b Instruct: 37.6 (#193), Step 2 16k Exp 202412: 38.5 (#174)

Coding benchmarks
BenchmarkCodellama 70b InstructStep 2 16k Exp 202412
BigCodeBench Instruct40.7%—
LMArena Coding—1316
BigCodeBench Complete49.6%—
HumanEval+65.9%—

Reasoning Step 2 16k Exp 202412 leads

Codellama 70b Instruct: 20.1 (#242), Step 2 16k Exp 202412: 25.9 (#142)

Reasoning benchmarks
BenchmarkCodellama 70b InstructStep 2 16k Exp 202412
LMArena Hard Prompts10521299

Math Not comparable

Codellama 70b Instruct: —, Step 2 16k Exp 202412: 36.3 (#169)

Math benchmarks
BenchmarkCodellama 70b InstructStep 2 16k Exp 202412
LMArena Math—1304

Knowledge Not comparable

Codellama 70b Instruct: —, Step 2 16k Exp 202412: 35.2 (#187)

Knowledge benchmarks
BenchmarkCodellama 70b InstructStep 2 16k Exp 202412
LMArena Expert—1279

Multilingual Step 2 16k Exp 202412 leads

Codellama 70b Instruct: 24.8 (#288), Step 2 16k Exp 202412: 43.7 (#181)

Multilingual benchmarks
BenchmarkCodellama 70b InstructStep 2 16k Exp 202412
LMArena Non-English9921290
LMArena Chinese—1331
LMArena Russian—1324

Instruction Following Step 2 16k Exp 202412 leads

Codellama 70b Instruct: 51.9 (#293), Step 2 16k Exp 202412: 67.9 (#192)

Instruction Following benchmarks
BenchmarkCodellama 70b InstructStep 2 16k Exp 202412
LMArena Instruction Following10241287

Long Context Not comparable

Codellama 70b Instruct: —, Step 2 16k Exp 202412: 39.7 (#170)

Long Context benchmarks
BenchmarkCodellama 70b InstructStep 2 16k Exp 202412
LMArena Longer Query—1307

Writing & Preference Step 2 16k Exp 202412 leads

Codellama 70b Instruct: 33.4 (#277), Step 2 16k Exp 202412: 52.3 (#173)

Writing & Preference benchmarks
BenchmarkCodellama 70b InstructStep 2 16k Exp 202412
LMArena Text10571321
LMArena Creative Writing—1328
LMArena Multi-Turn—1292

Frequently asked questions

Is Codellama 70b Instruct better than Step 2 16k Exp 202412?

Step 2 16k Exp 202412 is the stronger model overall, scoring 39.2 to 33.7 on the Noometry Index.

Is Codellama 70b Instruct or Step 2 16k Exp 202412 better for coding?

They score almost the same on coding (37.6 vs 38.5); test both on your own repository before choosing.

How many benchmarks do Codellama 70b Instruct and Step 2 16k Exp 202412 share?

4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Step 2 16k Exp 202412 has 12.

Related comparisons

Go deeper