LLM Benchmarks

llm.l.gaz.codes

Compare Models

Select models to compare benchmark results side by side

Compare Controls

Models (1)

glm-4.5-air-mlx

Benchmarks (8/8)

Selected Models (1)

glm-4.5-air-mlx
Loading catalog...
Quick add loaded models:

Compare models at different quantization levels with RAM/VRAM/speed tradeoffs

Benchmarks (8/8)

Benchmark Comparison

Sort:
Benchmark
glm-4.5-air-mlx
ARC-ChallengereasoningHF Leaderboard
88.0%
GSM8KreasoningHF Leaderboard
95.9%
HellaSwaglanguageHF Leaderboard
91.9%
HumanEvalcodingAider
84.6%
MBPPcodingAider
80.1%
MMLUknowledgeHF Leaderboard
92.6%
TruthfulQAsafetyHF Leaderboard
71.9%
WinoGrandelanguageHF Leaderboard
86.9%
Average
86.5%
Model Specs
Parameters
-
VRAM
-
Est. Speed
-