Model comparison

Qwen2.5-VL 72B Instruct vs StarCoder 2 3B

Qwen2.5-VL 72B Instruct has enough public results to be ranked (#298); StarCoder 2 3B does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

StarCoder 2 3B NVIDIA

35.8

Unranked Sparse

Side by side

Qwen2.5-VL 72B Instruct and StarCoder 2 3B specifications
Qwen2.5-VL 72B InstructStarCoder 2 3B
ProviderAlibaba (Qwen)NVIDIA
Noometry Index29.435.8
Released2024-092024-02-22
WeightsOpenOpen
Context window131K—
Max output8K—
Input $ / M tokens$2.80—
Output $ / M tokens$8.40—
Results tracked67

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

Category by category

Coding Not comparable

Qwen2.5-VL 72B Instruct: —, StarCoder 2 3B: 32.9

Coding benchmarks
BenchmarkQwen2.5-VL 72B InstructStarCoder 2 3B
BigCodeBench Complete—21.4%
HumanEval+—27.4%

Agentic & Tool Use Not comparable

Qwen2.5-VL 72B Instruct: 18.4 (#136), StarCoder 2 3B: —

Agentic & Tool Use benchmarks
BenchmarkQwen2.5-VL 72B InstructStarCoder 2 3B
OSWorld5%—

Reasoning Not comparable

Qwen2.5-VL 72B Instruct: 20.0 (#228), StarCoder 2 3B: —

Reasoning benchmarks
BenchmarkQwen2.5-VL 72B InstructStarCoder 2 3B
Kagi LLM Benchmark36%—
Epoch Capabilities Index—88.01
WinoGrande—57.1%

Math Not comparable

Qwen2.5-VL 72B Instruct: —, StarCoder 2 3B: —

Math benchmarks
BenchmarkQwen2.5-VL 72B InstructStarCoder 2 3B
GSM8K—21.6%

Knowledge Not comparable

Qwen2.5-VL 72B Instruct: —, StarCoder 2 3B: —

Knowledge benchmarks
BenchmarkQwen2.5-VL 72B InstructStarCoder 2 3B
ARC (AI2) Challenge—34.2%
MMLU—36.6%

Multimodal Not comparable

Qwen2.5-VL 72B Instruct: 32.9 (#92), StarCoder 2 3B: —

Multimodal benchmarks
BenchmarkQwen2.5-VL 72B InstructStarCoder 2 3B
LMArena Vision1107—
Video-MME73.5%—
GeoBench62%—
SpatialViz-Bench33.3%—

Frequently asked questions

Is Qwen2.5-VL 72B Instruct better than StarCoder 2 3B?

Qwen2.5-VL 72B Instruct has enough public results to be ranked (#298); StarCoder 2 3B does not yet, so treat this comparison as directional.

How many benchmarks do Qwen2.5-VL 72B Instruct and StarCoder 2 3B share?

0 benchmarks have published results for both models. Qwen2.5-VL 72B Instruct has 6 scored results on Noometry and StarCoder 2 3B has 7.

Related comparisons

Go deeper