DataLearner logo

GLM-4.7-Flash Benchmark Details

GLM-4.7-Flash currently shows benchmark results led by AIME2025 (36 / 107, score 91.60), τ²-Bench - Telecom (13 / 36, score 96), τ²-Bench (16 / 44, 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
187 / 197
HLE
Thinking Mode
14.40
159 / 197

Other

2 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Standard Mode
66
213 / 274
GPQA Diamond
Thinking Mode
75.20
172 / 274

Coding and Software Engineer

1 evaluations
Benchmark / mode
Score
Rank/total
SWE-bench Verified
Thinking Mode
59.20
84 / 116

Math and Reasoning

1 evaluations
Benchmark / mode
Score
Rank/total
AIME2025
Thinking Mode
91.60
36 / 107

Writing and Creative Capabilities

1 evaluations
Benchmark / mode
Score
Rank/total
Creative Writing
Standard Mode
1122.60
86 / 106

Agent Level Benchmark

5 evaluations
Benchmark / mode
Score
Rank/total
τ²-Bench - Telecom
Standard ModeTools
94
17 / 36
τ²-Bench - Telecom
Thinking ModeTools
96
13 / 36
τ²-Bench
Thinking ModeTools
79.50
16 / 44
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
29 / 36
IF Bench
Thinking ModeTools
68
22 / 36

AI Agent - Information Search

1 evaluations
Benchmark / mode
Score
Rank/total
BrowseComp
Thinking ModeTools
42.80
50 / 57
Compare with other models