Model comparison

GLM-4.5V vs StarCoder 2 15B

GLM-4.5V has enough public results to be ranked (#158); StarCoder 2 15B does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

GLM-4.5V Z.ai (Zhipu)

39.2

Rank #158 Confirmed

StarCoder 2 15B NVIDIA

37.5

Unranked Sparse

Side by side

GLM-4.5V and StarCoder 2 15B specifications
GLM-4.5VStarCoder 2 15B
ProviderZ.ai (Zhipu)NVIDIA
Noometry Index39.237.5
Released2025-08-112024-02-20
WeightsOpenOpen
Context window64K—
Max output16K—
Input $ / M tokens$0.60—
Output $ / M tokens$1.80—
Results tracked157

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

Category by category

Coding GLM-4.5V leads

GLM-4.5V: 38.9 (#152), StarCoder 2 15B: 36.0

Coding benchmarks
BenchmarkGLM-4.5VStarCoder 2 15B
LMArena Coding1347—
BigCodeBench Complete—38.4%
HumanEval+—37.8%

Reasoning Not comparable

GLM-4.5V: 26.5 (#118), StarCoder 2 15B: —

Reasoning benchmarks
BenchmarkGLM-4.5VStarCoder 2 15B
Kagi LLM Benchmark59.8%—
LMArena Hard Prompts1335—
Epoch Capabilities Index—104.61
WinoGrande—64.3%

Math Not comparable

GLM-4.5V: 34.7 (#157), StarCoder 2 15B: —

Math benchmarks
BenchmarkGLM-4.5VStarCoder 2 15B
LMArena Math1353—
GSM8K—57.7%

Knowledge Not comparable

GLM-4.5V: 36.8 (#155), StarCoder 2 15B: —

Knowledge benchmarks
BenchmarkGLM-4.5VStarCoder 2 15B
LMArena Expert1353—
ARC (AI2) Challenge—47.2%
MMLU—64.1%

Multimodal Not comparable

GLM-4.5V: 33.6 (#86), StarCoder 2 15B: —

Multimodal benchmarks
BenchmarkGLM-4.5VStarCoder 2 15B
LMArena Vision1154—

Multilingual Not comparable

GLM-4.5V: 44.9 (#172), StarCoder 2 15B: —

Multilingual benchmarks
BenchmarkGLM-4.5VStarCoder 2 15B
LMArena Non-English1304—
LMArena Chinese1338—
LMArena Russian1299—
LMArena Spanish1335—

Instruction Following Not comparable

GLM-4.5V: 69.4 (#170), StarCoder 2 15B: —

Instruction Following benchmarks
BenchmarkGLM-4.5VStarCoder 2 15B
LMArena Instruction Following1311—

Long Context Not comparable

GLM-4.5V: 39.6 (#166), StarCoder 2 15B: —

Long Context benchmarks
BenchmarkGLM-4.5VStarCoder 2 15B
LMArena Longer Query1305—

Writing & Preference Not comparable

GLM-4.5V: 52.7 (#162), StarCoder 2 15B: —

Writing & Preference benchmarks
BenchmarkGLM-4.5VStarCoder 2 15B
LMArena Text1333—
LMArena Creative Writing1295—
LMArena Multi-Turn1333—

Frequently asked questions

Is GLM-4.5V better than StarCoder 2 15B?

GLM-4.5V has enough public results to be ranked (#158); StarCoder 2 15B does not yet, so treat this comparison as directional.

Is GLM-4.5V or StarCoder 2 15B better for coding?

GLM-4.5V scores higher on coding benchmarks: 38.9 versus 36.0 in the Noometry coding category.

How many benchmarks do GLM-4.5V and StarCoder 2 15B share?

0 benchmarks have published results for both models. GLM-4.5V has 15 scored results on Noometry and StarCoder 2 15B has 7.

Related comparisons

Go deeper