AI Benchmark Model

GLM-4.5 (Reasoning)

Benchmark scores, pricing, speed, and model comparisons for GLM-4.5 (Reasoning).

Key scores

Intelligence26.4Index score
Coding26.3Index score
Math73.7Index score
Speed47.8Tokens/sec
Blended Cost$1.00Per 1M tokens

Review benchmark scores, pricing, performance data, and generated comparisons for this AI model.

Benchmark results

12 tracked benchmark rows for GLM-4.5 (Reasoning).

MATH 500 Math
97.9%
AIME Math
87.3%
MMLU Pro Knowledge
83.5%
GPQA Reasoning
78.2%
LiveCodeBench Code
73.8%
AIME 2025 Math
73.7%
LCR Other
48.3%
IFBench Other
44.1%
TAU2 Other
43.0%
SciCode Other
34.8%
TerminalBench Hard Other
22.0%
HLE Other
12.2%

Comments (0)

No comments yet

Be the first to share your thoughts!