Model comparison

Claude 2.1 vs StarCoder 2 15B

Claude 2.1 has enough public results to be ranked (#345); StarCoder 2 15B does not yet, so treat this comparison as directional.

Last verified . 2 shared benchmarks.

Claude 2.1 Anthropic

25.2

Rank #345 Reported

StarCoder 2 15B NVIDIA

38.1

Unranked Sparse

Summary

  • They share 2 benchmarks with published results for both. Claude 2.1 scores higher in 0 categories and StarCoder 2 15B in 1 category; one gap is clear of the uncertainty.
  • The widest gap is in coding, where StarCoder 2 15B leads 36.6 to 26.2.
  • StarCoder 2 15B has downloadable open weights; the other is API-only.

Side by side

Claude 2.1 and StarCoder 2 15B specifications
Claude 2.1StarCoder 2 15B
ProviderAnthropicNVIDIA
Noometry Index25.238.1
Released2023-11-212024-02-20
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked77

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

Category by category

Coding StarCoder 2 15B leads

Claude 2.1: 26.2 (#327), StarCoder 2 15B: 36.6

Coding benchmarks
BenchmarkClaude 2.1StarCoder 2 15B
WeirdML7.1%—
BigCodeBench Complete—38.4%
HumanEval+—37.8%

Reasoning Not comparable

Claude 2.1: 21.4 (#221), StarCoder 2 15B: —

Reasoning benchmarks
BenchmarkClaude 2.1StarCoder 2 15B
Epoch Capabilities Index119.27105
DTBench51%—
ForecastBench54.2—
WinoGrande—64.3%

Math Not comparable

Claude 2.1: 10.2 (#315), StarCoder 2 15B: —

Math benchmarks
BenchmarkClaude 2.1StarCoder 2 15B
OTIS Mock AIME 2024-20251.9%—
GSM8K—57.7%

Knowledge Not comparable

Claude 2.1: 15.4 (#292), StarCoder 2 15B: —

Knowledge benchmarks
BenchmarkClaude 2.1StarCoder 2 15B
MMLU73.5%64.1%
GPQA Diamond33%—
ARC (AI2) Challenge—47.2%

Frequently asked questions

Is Claude 2.1 better than StarCoder 2 15B?

Claude 2.1 has enough public results to be ranked (#345); StarCoder 2 15B does not yet, so treat this comparison as directional.

Is Claude 2.1 or StarCoder 2 15B better for coding?

StarCoder 2 15B scores higher on coding benchmarks: 36.6 versus 26.2 in the Noometry coding category.

How many benchmarks do Claude 2.1 and StarCoder 2 15B share?

2 benchmarks have published results for both models. Claude 2.1 has 7 scored results on Noometry and StarCoder 2 15B has 7.

Related comparisons

Go deeper