GLM-5.2 Benchmark Details

GLM-5.2 currently shows benchmark results led by IMO-AnswerBench (1 / 20, score 91), HLE (8 / 159, score 54.70), AIME 2026 (1 / 15, score 99.20).

Benchmark Results

GLM-5.2

Benchmark Results

General Knowledge

3 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Thinking Enabled

91.20

15 / 179

HLE

Thinking Enabled

40.50

51 / 159

HLE

Thinking EnabledTools

54.70

8 / 159

Coding and Software Engineer

1 evaluations

Benchmark / mode

Score

Rank/total

SWE-Bench Pro - Public

Thinking EnabledTools

62.10

5 / 44

Math and Reasoning

2 evaluations

Benchmark / mode

Score

Rank/total

AIME 2026

Thinking Enabled

99.20

1 / 15

IMO-AnswerBench

Thinking Enabled

1 / 20

AI Agent - Tool Usage

1 evaluations

Benchmark / mode

Score

Rank/total

TerminalBench 2.1

HighTools

4 / 14

Compare with other models