Models / GLM 4.6

Z.ai

GLM 4.6

23 published results from 4 sources. Each card shows where the number comes from and what it does not measure. Results are never combined into one score.

Provider
Z.ai
Sources
4
Our benchmarks
0
Price
Not yet published

Reported by others

Reported by Arena (formerly LMArena)
1,447
Overall · rank 54 of 177
Unit
Arena rating, higher is better
Range
1,443 to 1,451
Sample
28607 votes
Configuration
GLM 4.6
Measured
25 Sep 2026
Not shown
Not an error rate: claims that cannot be checked on the web are skipped, and preference still carries most of the weight.
Reported by Arena (formerly LMArena)
1,412
Business, management and finance · rank 108 of 402
Unit
Arena rating, higher is better
Range
1,404 to 1,420
Sample
6889 votes
Configuration
GLM 4.6
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,400
Creative writing · rank 79 of 407
Unit
Arena rating, higher is better
Range
1,392 to 1,409
Sample
5112 votes
Configuration
GLM 4.6
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,439
Expert prompts · rank 91 of 359
Unit
Arena rating, higher is better
Range
1,426 to 1,452
Sample
2043 votes
Configuration
GLM 4.6
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,412
Instruction following · rank 100 of 409
Unit
Arena rating, higher is better
Range
1,406 to 1,419
Sample
10236 votes
Configuration
GLM 4.6
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,424
Overall · rank 105 of 409
Unit
Arena rating, higher is better
Range
1,420 to 1,428
Sample
35678 votes
Configuration
GLM 4.6
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Arena (formerly LMArena)
1,405
Writing, literature and language · rank 91 of 408
Unit
Arena rating, higher is better
Range
1,398 to 1,412
Sample
8044 votes
Configuration
GLM 4.6
Measured
25 Sep 2026
Not shown
Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
55.7%
Memory · rank 5 of 109
Unit
% correct, higher is better
Configuration
glm-4.6
Measured
16 Dec 2025
Not shown
Not long-term personal memory in a product: sessions are BFCL's scripted ones.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
68.0%
Multi-turn tasks · rank 5 of 109
Unit
% correct, higher is better
Configuration
glm-4.6
Measured
16 Dec 2025
Not shown
Not open-ended agent work: the tools and tasks are BFCL's simulated APIs.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
72.4%
Overall accuracy · rank 4 of 109
Unit
% correct, higher is better
Configuration
glm-4.6
Measured
16 Dec 2025
Not shown
Not a neutral average: the weighting is BFCL's. Not reliability on your own tools: BFCL's functions and queries are a fixed test set, and a correct call is judged by its form, not by what it achieved.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
75.0%
Relevance detection · rank 62 of 109
Unit
% correct, higher is better
Configuration
glm-4.6
Measured
16 Dec 2025
Not shown
Not whether the call itself was right; only that one was attempted.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
87.6%
Single-turn calls (curated) · rank 25 of 109
Unit
% correct, higher is better
Configuration
glm-4.6
Measured
16 Dec 2025
Not shown
Not reliability on your own tools: BFCL's functions and queries are a fixed test set, and a correct call is judged by its form, not by what it achieved.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
80.9%
Single-turn calls (user-contributed) · rank 8 of 109
Unit
% correct, higher is better
Configuration
glm-4.6
Measured
16 Dec 2025
Not shown
Not reliability on your own tools: BFCL's functions and queries are a fixed test set, and a correct call is judged by its form, not by what it achieved.
Reported by Berkeley Function Calling Leaderboard (BFCL) V4
77.5%
Web search · rank 8 of 109
Unit
% correct, higher is better
Configuration
glm-4.6
Measured
16 Dec 2025
Not shown
Not general research quality: questions have short, checkable answers.
Reported by UGI Leaderboard
18.0%
Requested-length error · rank 150 of 370
Unit
% off the requested word count, lower is better
Configuration
glm-4.6
Measured
2 Oct 2025
Not shown
Not other format limits such as character counts or bullet counts.
Reported by UGI Leaderboard
13.0%
Requested-length error · rank 103 of 370
Unit
% off the requested word count, lower is better
Configuration
glm-4.6
Measured
2 Oct 2025
Not shown
Not other format limits such as character counts or bullet counts.
Reported by UGI Leaderboard
0.37
Style adherence · rank 81 of 370
Unit
score from 0 to 1, higher is better
Configuration
glm-4.6
Measured
2 Oct 2025
Not shown
Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
Reported by UGI Leaderboard
0.38
Style adherence · rank 67 of 370
Unit
score from 0 to 1, higher is better
Configuration
glm-4.6
Measured
2 Oct 2025
Not shown
Not brand voice on your own examples: UGI's prompts are private and lean towards creative writing.
Reported by UGI Leaderboard
50.0
Writing score · rank 157 of 370
Unit
score out of 100, higher is better
Configuration
glm-4.6
Measured
2 Oct 2025
Not shown
Not business copy quality: UGI's prompts are private and lean towards creative writing, and models that often refuse get no score.
Reported by UGI Leaderboard
53.3
Writing score · rank 140 of 370
Unit
score out of 100, higher is better
Configuration
glm-4.6
Measured
2 Oct 2025
Not shown
Not business copy quality: UGI's prompts are private and lean towards creative writing, and models that often refuse get no score.
Reported by Vectara Hallucination Leaderboard
94.5%
Answer rate · rank 93 of 108
Unit
% of documents, higher is better
Configuration
GLM 4.6
Measured
22 Sep 2026
Not shown
Not a quality score: a low rate usually means content filters were triggered, and hallucination rates are measured on answered documents only.
Reported by Vectara Hallucination Leaderboard
9.5%
Hallucination rate · rank 53 of 108
Unit
% of summaries, lower is better
Configuration
GLM 4.6
Measured
22 Sep 2026
Not shown
Not errors in open questions or other tasks: only summarisation, judged by Vectara's own model (HHEM-2.3), not by people, on news-style documents rather than your data.

Compare GLM 4.6 with