Noometry

Model comparison

Claude Sonnet 5.5 vs StarCoder 2 15B

Claude Sonnet 5.5 has enough public results to be ranked (#10); StarCoder 2 15B does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

Claude Sonnet 5.5 Anthropic

61.9

Rank #10 Confirmed

StarCoder 2 15B NVIDIA

38.1

Unranked Sparse

Summary

  • They share 1 benchmark with published results for both. Claude Sonnet 5.5 scores higher in 1 category and StarCoder 2 15B in 0 categories; one gap is clear of the uncertainty.
  • The widest gap is in coding, where Claude Sonnet 5.5 leads 67.3 to 36.6.
  • StarCoder 2 15B has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 5.5StarCoder 2 15B
ProviderAnthropicNVIDIA
Noometry Index61.938.1
Released2026-09-282024-02-20
WeightsProprietaryOpen
Context window1M—
Max output128K—
Input $ / M tokens$2—
Output $ / M tokens$10—
Results tracked327

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

Category by category

Coding Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 67.3 (#6), StarCoder 2 15B: 36.6

BenchmarkClaude Sonnet 5.5StarCoder 2 15B
FrontierCode52.1%—
CursorBench55.5%—
LMArena WebDev1774—
FrontierSWE61.9%—
SciCode61%—
LMArena Coding1513—
BigCodeBench Complete—38.4%
ALE-Bench1,819—
HumanEval+—37.8%

Agentic & Tool Use Not comparable

Claude Sonnet 5.5: 45.0 (#16), StarCoder 2 15B: —

BenchmarkClaude Sonnet 5.5StarCoder 2 15B
APEX-Agents75.5%—

Reasoning Not comparable

Claude Sonnet 5.5: 54.0 (#28), StarCoder 2 15B: —

BenchmarkClaude Sonnet 5.5StarCoder 2 15B
Epoch Capabilities Index165.03105
NYT Connections (extended)80.5%—
CritPt31.4%—
LMArena Hard Prompts1495—
Mystery Game Puzzles65%—
WinoGrande—64.3%

Math Not comparable

Claude Sonnet 5.5: 87.9 (#6), StarCoder 2 15B: —

BenchmarkClaude Sonnet 5.5StarCoder 2 15B
FrontierMath (Tiers 1-3)88.8%—
FrontierMath Tier 480.5%—
OTIS Mock AIME 2024-2025100%—
ProofBench100%—
LMArena Math1510—
FrontierMath Erdős2.9%—
GSM8K—57.7%

Knowledge Not comparable

Claude Sonnet 5.5: 66.0 (#12), StarCoder 2 15B: —

BenchmarkClaude Sonnet 5.5StarCoder 2 15B
GPQA Diamond95.6%—
SimpleQA Verified46.5%—
LMArena Expert1540—
ARC (AI2) Challenge—47.2%
MMLU—64.1%

Multimodal Not comparable

Claude Sonnet 5.5: 51.5 (#6), StarCoder 2 15B: —

BenchmarkClaude Sonnet 5.5StarCoder 2 15B
LMArena Vision1289—
Furniture Assembly75%—

Multilingual Not comparable

Claude Sonnet 5.5: 55.3 (#30), StarCoder 2 15B: —

BenchmarkClaude Sonnet 5.5StarCoder 2 15B
LMArena Non-English1452—
LMArena Chinese1522—
LMArena Russian1451—

Instruction Following Not comparable

Claude Sonnet 5.5: 78.3 (#11), StarCoder 2 15B: —

BenchmarkClaude Sonnet 5.5StarCoder 2 15B
LMArena Instruction Following1495—

Long Context Not comparable

Claude Sonnet 5.5: 45.9 (#28), StarCoder 2 15B: —

BenchmarkClaude Sonnet 5.5StarCoder 2 15B
LMArena Longer Query1498—

Writing & Preference Not comparable

Claude Sonnet 5.5: 66.0 (#40), StarCoder 2 15B: —

BenchmarkClaude Sonnet 5.5StarCoder 2 15B
LMArena Text1471—
LMArena Creative Writing1465—
LMArena Multi-Turn1474—

Frequently asked questions

Is Claude Sonnet 5.5 better than StarCoder 2 15B?

Claude Sonnet 5.5 has enough public results to be ranked (#10); StarCoder 2 15B does not yet, so treat this comparison as directional.

Is Claude Sonnet 5.5 or StarCoder 2 15B better for coding?

Claude Sonnet 5.5 scores higher on coding benchmarks: 67.3 versus 36.6 in the Noometry coding category.

How many benchmarks do Claude Sonnet 5.5 and StarCoder 2 15B share?

1 benchmark has published results for both models. Claude Sonnet 5.5 has 32 scored results on Noometry and StarCoder 2 15B has 7.

Related comparisons

Go deeper