Noometry

Model comparison

Claude 3.5 Haiku vs StarCoder 2 3B

Claude 3.5 Haiku has enough public results to be ranked (#315); StarCoder 2 3B does not yet, so treat this comparison as directional.

Last verified . 3 shared benchmarks.

Claude 3.5 Haiku Anthropic

29.2

Rank #315 Confirmed

StarCoder 2 3B NVIDIA

36.3

Unranked Sparse

Summary

  • They share 3 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 0 categories and StarCoder 2 3B in 1 category, but none of those gaps is larger than the uncertainty.
  • The biggest single-benchmark swing is BigCodeBench Complete: 59% for Claude 3.5 Haiku and 21.4% for StarCoder 2 3B.
  • StarCoder 2 3B has downloadable open weights; the other is API-only.

Side by side

Claude 3.5 HaikuStarCoder 2 3B
ProviderAnthropicNVIDIA
Noometry Index29.236.3
Released2024-10-222024-02-22
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked497

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

Category by category

Coding Too close to call

Claude 3.5 Haiku: 32.9 (#265), StarCoder 2 3B: 33.5

BenchmarkClaude 3.5 HaikuStarCoder 2 3B
BigCodeBench Complete59%21.4%
Aider Polyglot28%—
SciCode27.4%—
WeirdML30.7%—
BigCodeBench Instruct46.1%—
LiveBench Coding51.4%—
LMArena Coding1286—
CadEval32%—
HumanEval+—27.4%

Agentic & Tool Use Not comparable

Claude 3.5 Haiku: 28.0 (#95), StarCoder 2 3B: —

BenchmarkClaude 3.5 HaikuStarCoder 2 3B
BALROG19.3%—

Reasoning Not comparable

Claude 3.5 Haiku: 17.7 (#290), StarCoder 2 3B: —

BenchmarkClaude 3.5 HaikuStarCoder 2 3B
Epoch Capabilities Index127.1588.76
CritPt0%—
LiveBench Reasoning28.1%—
LMArena Hard Prompts1251—
DTBench56.7%—
LiveBench Data Analysis48.5%—
LiveBench43.5%—
WinoGrande—57.1%

Math Not comparable

Claude 3.5 Haiku: 14.7 (#300), StarCoder 2 3B: —

BenchmarkClaude 3.5 HaikuStarCoder 2 3B
OTIS Mock AIME 2024-20254.3%—
Omni-MATH22.4%—
LiveBench Math35.5%—
LMArena Math1244—
MATH Level 546.4%—
FrontierMath (Feb 2025 set)0.3%—
GSM8K—21.6%

Knowledge Not comparable

Claude 3.5 Haiku: 18.7 (#281), StarCoder 2 3B: —

BenchmarkClaude 3.5 HaikuStarCoder 2 3B
MMLU74.3%36.6%
GPQA Diamond38.1%—
MMLU-Pro60.5%—
Confabulations36.7%—
GPQA (HELM)36.3%—
LMArena Expert1208—
ARC (AI2) Challenge—34.2%

Multimodal Not comparable

Claude 3.5 Haiku: 26.8 (#117), StarCoder 2 3B: —

BenchmarkClaude 3.5 HaikuStarCoder 2 3B
LMArena Vision1092—
GeoBench34%—

Multilingual Not comparable

Claude 3.5 Haiku: 40.0 (#218), StarCoder 2 3B: —

BenchmarkClaude 3.5 HaikuStarCoder 2 3B
LMArena Non-English1238—
LMArena Chinese1229—
LMArena French1264—
LMArena German1237—
LMArena Japanese1175—
LMArena Korean1173—
LMArena Russian1253—
LMArena Spanish1261—

Instruction Following Not comparable

Claude 3.5 Haiku: 62.9 (#234), StarCoder 2 3B: —

BenchmarkClaude 3.5 HaikuStarCoder 2 3B
LiveBench Instruction Following61.9%—
IFEval79.2%—
LMArena Instruction Following1241—

Long Context Not comparable

Claude 3.5 Haiku: 38.3 (#200), StarCoder 2 3B: —

BenchmarkClaude 3.5 HaikuStarCoder 2 3B
LMArena Longer Query1261—

Writing & Preference Not comparable

Claude 3.5 Haiku: 42.7 (#234), StarCoder 2 3B: —

BenchmarkClaude 3.5 HaikuStarCoder 2 3B
LMArena Text1255—
LMArena Creative Writing1233—
Short-Story Creative Writing73.5%—
EQ-Bench Creative Writing1146—
WildBench76%—
LMArena Multi-Turn1265—
LiveBench Language35.4%—

Frequently asked questions

Is Claude 3.5 Haiku better than StarCoder 2 3B?

Claude 3.5 Haiku has enough public results to be ranked (#315); StarCoder 2 3B does not yet, so treat this comparison as directional.

Is Claude 3.5 Haiku or StarCoder 2 3B better for coding?

They score almost the same on coding (32.9 vs 33.5); test both on your own repository before choosing.

How many benchmarks do Claude 3.5 Haiku and StarCoder 2 3B share?

3 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and StarCoder 2 3B has 7.

Related comparisons

Go deeper