Noometry

Model comparison

Gemini 1.5 Flash 8B vs StarCoder 2 3B

Gemini 1.5 Flash 8B has enough public results to be ranked (#292); StarCoder 2 3B does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

Gemini 1.5 Flash 8B Google

29.7

Rank #292 Confirmed

StarCoder 2 3B NVIDIA

35.8

Unranked Sparse

Summary

  • StarCoder 2 3B has downloadable open weights; the other is API-only.

Side by side

Gemini 1.5 Flash 8BStarCoder 2 3B
ProviderGoogleNVIDIA
Noometry Index29.735.8
Released2024-10-032024-02-22
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked217

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

Category by category

Coding Gemini 1.5 Flash 8B leads

Gemini 1.5 Flash 8B: 34.9 (#221), StarCoder 2 3B: 32.9

BenchmarkGemini 1.5 Flash 8BStarCoder 2 3B
LMArena Coding1218—
BigCodeBench Complete—21.4%
HumanEval+—27.4%

Reasoning Not comparable

Gemini 1.5 Flash 8B: 19.2 (#242), StarCoder 2 3B: —

BenchmarkGemini 1.5 Flash 8BStarCoder 2 3B
LMArena Hard Prompts1210—
DTBench50%—
Epoch Capabilities Index—88.01
WinoGrande—57.1%

Math Not comparable

Gemini 1.5 Flash 8B: 13.3 (#296), StarCoder 2 3B: —

BenchmarkGemini 1.5 Flash 8BStarCoder 2 3B
OTIS Mock AIME 2024-20254.6%—
LMArena Math1207—
GSM8K—21.6%

Knowledge Not comparable

Gemini 1.5 Flash 8B: 16.0 (#285), StarCoder 2 3B: —

BenchmarkGemini 1.5 Flash 8BStarCoder 2 3B
GPQA Diamond33%—
LMArena Expert1185—
ARC (AI2) Challenge—34.2%
MMLU—36.6%

Multimodal Not comparable

Gemini 1.5 Flash 8B: 27.6 (#110), StarCoder 2 3B: —

BenchmarkGemini 1.5 Flash 8BStarCoder 2 3B
LMArena Vision1044—

Multilingual Not comparable

Gemini 1.5 Flash 8B: 38.6 (#224), StarCoder 2 3B: —

BenchmarkGemini 1.5 Flash 8BStarCoder 2 3B
LMArena Non-English1215—
LMArena Chinese1231—
LMArena French1233—
LMArena German1206—
LMArena Japanese1150—
LMArena Korean1140—
LMArena Russian1236—
LMArena Spanish1212—

Instruction Following Not comparable

Gemini 1.5 Flash 8B: 63.1 (#231), StarCoder 2 3B: —

BenchmarkGemini 1.5 Flash 8BStarCoder 2 3B
LMArena Instruction Following1199—

Long Context Not comparable

Gemini 1.5 Flash 8B: 36.9 (#220), StarCoder 2 3B: —

BenchmarkGemini 1.5 Flash 8BStarCoder 2 3B
LMArena Longer Query1219—

Writing & Preference Not comparable

Gemini 1.5 Flash 8B: 43.0 (#227), StarCoder 2 3B: —

BenchmarkGemini 1.5 Flash 8BStarCoder 2 3B
LMArena Text1226—
LMArena Creative Writing1218—
LMArena Multi-Turn1185—

Frequently asked questions

Is Gemini 1.5 Flash 8B better than StarCoder 2 3B?

Gemini 1.5 Flash 8B has enough public results to be ranked (#292); StarCoder 2 3B does not yet, so treat this comparison as directional.

Is Gemini 1.5 Flash 8B or StarCoder 2 3B better for coding?

Gemini 1.5 Flash 8B scores higher on coding benchmarks: 34.9 versus 32.9 in the Noometry coding category.

How many benchmarks do Gemini 1.5 Flash 8B and StarCoder 2 3B share?

0 benchmarks have published results for both models. Gemini 1.5 Flash 8B has 21 scored results on Noometry and StarCoder 2 3B has 7.

Related comparisons

Go deeper