Model comparison

StarCoder 2 15B vs Step 1o Turbo 202506

Step 1o Turbo 202506 has enough public results to be ranked (#160); StarCoder 2 15B does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

StarCoder 2 15B NVIDIA

37.5

Unranked Sparse

Step 1o Turbo 202506 StepFun

39.1

Rank #160 Confirmed

Summary

  • StarCoder 2 15B has downloadable open weights; the other is API-only.

Side by side

StarCoder 2 15B and Step 1o Turbo 202506 specifications
StarCoder 2 15BStep 1o Turbo 202506
ProviderNVIDIAStepFun
Noometry Index37.539.1
Released2024-02-20—
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

StarCoder 2 15B: 36.0, Step 1o Turbo 202506: 38.6 (#158)

Coding benchmarks
BenchmarkStarCoder 2 15BStep 1o Turbo 202506
LMArena Coding—1339
BigCodeBench Complete38.4%—
HumanEval+37.8%—

Reasoning Not comparable

StarCoder 2 15B: —, Step 1o Turbo 202506: 25.7 (#127)

Reasoning benchmarks
BenchmarkStarCoder 2 15BStep 1o Turbo 202506
LMArena Hard Prompts—1336
Epoch Capabilities Index104.61—
WinoGrande64.3%—

Math Not comparable

StarCoder 2 15B: —, Step 1o Turbo 202506: 33.9 (#163)

Math benchmarks
BenchmarkStarCoder 2 15BStep 1o Turbo 202506
LMArena Math—1318
GSM8K57.7%—

Knowledge Not comparable

StarCoder 2 15B: —, Step 1o Turbo 202506: 35.5 (#174)

Knowledge benchmarks
BenchmarkStarCoder 2 15BStep 1o Turbo 202506
LMArena Expert—1308
ARC (AI2) Challenge47.2%—
MMLU64.1%—

Multimodal Not comparable

StarCoder 2 15B: —, Step 1o Turbo 202506: 35.4 (#75)

Multimodal benchmarks
BenchmarkStarCoder 2 15BStep 1o Turbo 202506
LMArena Vision—1186

Multilingual Not comparable

StarCoder 2 15B: —, Step 1o Turbo 202506: 45.5 (#168)

Multilingual benchmarks
BenchmarkStarCoder 2 15BStep 1o Turbo 202506
LMArena Non-English—1313
LMArena Chinese—1380
LMArena German—1315
LMArena Russian—1327

Instruction Following Not comparable

StarCoder 2 15B: —, Step 1o Turbo 202506: 69.4 (#171)

Instruction Following benchmarks
BenchmarkStarCoder 2 15BStep 1o Turbo 202506
LMArena Instruction Following—1311

Long Context Not comparable

StarCoder 2 15B: —, Step 1o Turbo 202506: 41.1 (#141)

Long Context benchmarks
BenchmarkStarCoder 2 15BStep 1o Turbo 202506
LMArena Longer Query—1350

Writing & Preference Not comparable

StarCoder 2 15B: —, Step 1o Turbo 202506: 53.4 (#154)

Writing & Preference benchmarks
BenchmarkStarCoder 2 15BStep 1o Turbo 202506
LMArena Text—1336
LMArena Creative Writing—1308
LMArena Multi-Turn—1341

Frequently asked questions

Is StarCoder 2 15B better than Step 1o Turbo 202506?

Step 1o Turbo 202506 has enough public results to be ranked (#160); StarCoder 2 15B does not yet, so treat this comparison as directional.

Is StarCoder 2 15B or Step 1o Turbo 202506 better for coding?

Step 1o Turbo 202506 scores higher on coding benchmarks: 38.6 versus 36.0 in the Noometry coding category.

How many benchmarks do StarCoder 2 15B and Step 1o Turbo 202506 share?

0 benchmarks have published results for both models. StarCoder 2 15B has 7 scored results on Noometry and Step 1o Turbo 202506 has 14.

Related comparisons

Go deeper