AI Benchmark Model

GLM-4.6 (Reasoning)

Benchmark scores, pricing, speed, and model comparisons for GLM-4.6 (Reasoning).

Key scores

Intelligence32.5Index score
Coding29.5Index score
Math86.0Index score
Speed39.0Tokens/sec
Blended Cost$0.96Per 1M tokens

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

Benchmark results

10 tracked benchmark rows for GLM-4.6 (Reasoning).

AIME 2025 Math
86.0%
MMLU Pro Knowledge
82.9%
GPQA Reasoning
78.0%
TAU2 Other
70.5%
LiveCodeBench Code
69.5%
LCR Other
54.3%
IFBench Other
43.4%
SciCode Other
38.4%
TerminalBench Hard Other
25.0%
HLE Other
13.3%

Comments (0)

No comments yet

Be the first to share your thoughts!