DataLearner logo

GLM-4.7-Flash Benchmark Details

GLM-4.7-Flash currently shows benchmark results led by AIME2025 (36 / 106, score 91.60), τ²-Bench - Telecom (12 / 35, score 96), τ²-Bench (16 / 43, score 79.50).

Benchmark Results

GLM-4.7-Flash

Benchmark Results

Thinking
Tool usage

General Knowledge

2 evaluations
Benchmark / mode
Score
Rank/total
HLE
Standard Mode
6.10
171 / 181
HLE
Thinking Mode
14.40
145 / 181

Other

2 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Standard Mode
66
170 / 224
GPQA Diamond
Thinking Mode
75.20
135 / 224

Coding and Software Engineer

1 evaluations
Benchmark / mode
Score
Rank/total
SWE-bench Verified
Thinking Mode
59.20
84 / 114

Math and Reasoning

1 evaluations
Benchmark / mode
Score
Rank/total
AIME2025
Thinking Mode
91.60
36 / 106

Agent Level Benchmark

5 evaluations
Benchmark / mode
Score
Rank/total
τ²-Bench - Telecom
Standard ModeTools
94
16 / 35
τ²-Bench - Telecom
Thinking ModeTools
96
12 / 35
τ²-Bench
Thinking ModeTools
79.50
16 / 43
Terminal Bench Hard
Standard ModeTools
30
11 / 13
Terminal Bench Hard
Thinking ModeTools
32
9 / 13

Instruction Following

2 evaluations
Benchmark / mode
Score
Rank/total
IF Bench
Standard ModeTools
55
26 / 33
IF Bench
Thinking ModeTools
68
20 / 33

AI Agent - Information Search

1 evaluations
Benchmark / mode
Score
Rank/total
BrowseComp
Thinking ModeTools
42.80
48 / 54
Compare with other models