DataLearner logo

GLM-4.6 Benchmark Details

GLM-4.6 currently shows benchmark results led by AIME2025 (15 / 106, score 98.60), LiveCodeBench (18 / 120, score 84.50), MMLU Pro (43 / 126, score 83).

Benchmark Results

GLM-4.6

Benchmark Results

Thinking

General Knowledge

9 evaluations
Benchmark / mode
Score
Rank/total
MMLU Pro
83
43 / 126
MMLU Pro
78
69 / 126
GPQA Diamond
82.90
62 / 179
GPQA Diamond
81
70 / 179
GPQA Diamond
63
136 / 179
LiveBench
Standard Mode
55.19
81 / 115
HLE
30.40
76 / 159
HLE
17.20
118 / 159
HLE
5.20
152 / 159

Coding and Software Engineer

5 evaluations
Benchmark / mode
Score
Rank/total
LiveCodeBench
84.50
18 / 120
LiveCodeBench
82.80
24 / 120
LiveCodeBench
56
79 / 120
SWE-bench Verified
68
65 / 108
SWE-bench Verified
68
65 / 108

Math and Reasoning

4 evaluations
Benchmark / mode
Score
Rank/total
AIME2025
98.60
15 / 106
AIME2025
98.60
15 / 106
AIME2025
44
92 / 106
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
20 / 40
τ²-Bench - Telecom
71
27 / 35

Instruction Following

1 evaluations
Benchmark / mode
Score
Rank/total
IF Bench
43
29 / 29

AI Agent - Information Search

1 evaluations
Benchmark / mode
Score
Rank/total
BrowseComp
45.10
38 / 45
Compare with other models