GLM 5.1 Thinking
Zhipu AI
Parameters
—
Architecture
—
Released
—
License
—
About
No detailed description available for this model.
Benchmark Scores
| Benchmark | Score | Date | Standing |
|---|---|---|---|
|
Terminal Bench 2.1
coding_agent
|
53.10%
|
11.06.2026 |
#33/44
better than 26%
|
|
VIBE-V2
coding_agent
|
72.40%
|
11.06.2026 |
#4/9
better than 62%
|
|
SVG-Bench
coding_agent
|
55.28%
|
11.06.2026 |
#8/9
better than 12%
|
|
GDPVal
general_agent
|
67.13%
|
11.06.2026 |
#7/20
better than 68%
|
|
SpreadSheetBench-v1
general_agent
|
92.31%
|
11.06.2026 |
#4/9
better than 62%
|
|
MCP-Atlas
general_agent
|
77.28%
|
11.06.2026 |
#25/54
better than 53%
|
|
Claw-Eval Avg
coding_agent
|
75.28%
|
11.06.2026 |
#17/40
better than 59%
|
|
BrowseComp
general_agent
|
85.62%
|
11.06.2026 |
#12/45
better than 73%
|
|
SWE-bench Pro
coding_agent
|
65.11%
|
11.06.2026 |
#23/77
better than 70%
|
|
NL2Repo-Bench
coding_agent
|
36.13%
|
11.06.2026 |
#20/23
better than 14%
|
What is a good Terminal Bench 2.1 score? What is a good VIBE-V2 score? What is a good SVG-Bench score?
No comments yet
Be the first to share your thoughts!