DataLearner logo

GLM-4.6 Benchmark Details

GLM-4.6 currently shows benchmark results led by AIME2025 (15 / 107, score 98.60), LiveCodeBench (18 / 123, score 84.50), MMLU Pro (45 / 132, score 83).

Benchmark Results

GLM-4.6

Benchmark Results

Thinking

General Knowledge

9 evaluations
Benchmark / mode
Score
Rank/total
MMLU Pro
83
45 / 132
MMLU Pro
78
72 / 132
GPQA Diamond
82.90
67 / 188
GPQA Diamond
81
76 / 188
GPQA Diamond
63
142 / 188
LiveBench
Standard Mode
55.19
81 / 115
HLE
30.40
87 / 173
HLE
17.20
132 / 173
HLE
5.20
166 / 173

Coding and Software Engineer

5 evaluations
Benchmark / mode
Score
Rank/total
LiveCodeBench
84.50
18 / 123
LiveCodeBench
82.80
24 / 123
LiveCodeBench
56
80 / 123
SWE-bench Verified
68
70 / 113
SWE-bench Verified
68
70 / 113

Math and Reasoning

4 evaluations
Benchmark / mode
Score
Rank/total
AIME2025
98.60
15 / 107
AIME2025
98.60
15 / 107
AIME2025
44
93 / 107
FrontierMath - Tier 4
Standard Mode
2.10
56 / 80

AI Agent - Tool Usage

1 evaluations
Benchmark / mode
Score
Rank/total
Terminal-Bench
40.50
12 / 35

Agent Level Benchmark

2 evaluations
Benchmark / mode
Score
Rank/total
τ²-Bench
75.90
21 / 43
τ²-Bench - Telecom
71
27 / 35

Instruction Following

1 evaluations
Benchmark / mode
Score
Rank/total
IF Bench
43
31 / 31

AI Agent - Information Search

1 evaluations
Benchmark / mode
Score
Rank/total
BrowseComp
45.10
45 / 53
Compare with other models