GLM-4.7-Flash Benchmark Details

GLM-4.7-Flash currently shows benchmark results led by τ²-Bench - Telecom (12 / 35, score 96), AIME2025 (37 / 106, score 91.60), τ²-Bench (16 / 40, score 79.50).

Benchmark Results

GLM-4.7-Flash

Benchmark Results

综合评估

4 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Standard Mode

124 / 175

GPQA Diamond

Thinking Enabled

75.20

89 / 175

HLE

Standard Mode

6.10

139 / 149

HLE

Thinking Enabled

14.40

113 / 149

编程与软件工程

1 evaluations

Benchmark / mode

Score

Rank/total

SWE-bench Verified

Thinking Enabled

59.20

73 / 103

数学推理

1 evaluations

Benchmark / mode

Score

Rank/total

AIME2025

Thinking Enabled

91.60

37 / 106

Agent能力评测

5 evaluations

Benchmark / mode

Score

Rank/total

τ²-Bench - Telecom

Standard ModeTools

16 / 35

τ²-Bench - Telecom

Thinking EnabledTools

12 / 35

τ²-Bench

Thinking EnabledTools

79.50

16 / 40

Terminal Bench Hard

Standard ModeTools

11 / 13

Terminal Bench Hard

Thinking EnabledTools

9 / 13

指令跟随

2 evaluations

Benchmark / mode

Score

Rank/total

IF Bench

Standard ModeTools

20 / 27

IF Bench

Thinking EnabledTools

15 / 27

AI Agent - 信息收集

1 evaluations

Benchmark / mode

Score

Rank/total

BrowseComp

Thinking EnabledTools

42.80

38 / 43

Compare with other models