Scores from glm-5

Roleplay combines public evaluations of emotional understanding, creative writing and story-related skills. It is a comparative reference, not a direct roleplay test.

Each benchmark is rescaled to 1–10 within its own leaderboard. We average results from the same publisher first, then give each publisher equal weight. Only verified model matches are included.

EQ-Bench 3
zai-org/GLM-5: 1,495
83 Models · 2026-10-25

Creative Writing v3
zai-org/GLM-5: 1,600.6
145 Models · 2026-10-25

Roleplay combines public evaluations of emotional understanding, creative writing and story-related skills. It is a comparative reference, not a direct roleplay test.

Each benchmark is rescaled to 1–10 within its own leaderboard. We average results from the same publisher first, then give each publisher equal weight. Only verified model matches are included.

EQ-Bench 3
zai-org/GLM-4.7: 1,462.6
83 Models · 2026-10-25

Creative Writing v3
zai-org/GLM-4.7: 1,413.6
145 Models · 2026-10-25

LiveBench · Story constraint following (2025-12-23)
glm-4.7: 37.85
65 Models · 2026-10-25

LiveBench · Theory of mind (2025-12-23)
glm-4.7: 76.92
65 Models · 2026-10-25

Roleplay combines public evaluations of emotional understanding, creative writing and story-related skills. It is a comparative reference, not a direct roleplay test.

Each benchmark is rescaled to 1–10 within its own leaderboard. We average results from the same publisher first, then give each publisher equal weight. Only verified model matches are included.

Creative Writing v3
GLM-5.3: 2,076.7
145 Models · 2026-10-25

LiveBench · Story constraint following
glm-5.3: 72.13
71 Models · 2026-10-25

LiveBench · Theory of mind
glm-5.3: 88.46
71 Models · 2026-10-25

Roleplay combines public evaluations of emotional understanding, creative writing and story-related skills. It is a comparative reference, not a direct roleplay test.

Each benchmark is rescaled to 1–10 within its own leaderboard. We average results from the same publisher first, then give each publisher equal weight. Only verified model matches are included.

EQ-Bench 3
zai-org/GLM-5.1: 1,538.6
83 Models · 2026-10-25

Creative Writing v3
zai-org/GLM-5.1: 1,593.9
145 Models · 2026-10-25

Roleplay combines public evaluations of emotional understanding, creative writing and story-related skills. It is a comparative reference, not a direct roleplay test.

Each benchmark is rescaled to 1–10 within its own leaderboard. We average results from the same publisher first, then give each publisher equal weight. Only verified model matches are included.

EQ-Bench 3
zai-org/GLM-5.2: 1,563.2
83 Models · 2026-10-25

Creative Writing v3
zai-org/GLM-5.2: 1,759.3
145 Models · 2026-10-25

LiveBench · Story constraint following
glm-5.2: 62.88
71 Models · 2026-10-25

LiveBench · Theory of mind
glm-5.2: 75
71 Models · 2026-10-25

Roleplay combines public evaluations of emotional understanding, creative writing and story-related skills. It is a comparative reference, not a direct roleplay test.

Each benchmark is rescaled to 1–10 within its own leaderboard. We average results from the same publisher first, then give each publisher equal weight. Only verified model matches are included.

LiveBench · Story constraint following (2025-05-30)
glm-4.5-air: 82.92
70 Models · 2026-10-25

Roleplay combines public evaluations of emotional understanding, creative writing and story-related skills. It is a comparative reference, not a direct roleplay test.

Each benchmark is rescaled to 1–10 within its own leaderboard. We average results from the same publisher first, then give each publisher equal weight. Only verified model matches are included.

LiveBench · Story constraint following
glm-5.3-flash: 59.88
71 Models · 2026-10-25

LiveBench · Theory of mind
glm-5.3-flash: 73.08
71 Models · 2026-10-25

Roleplay combines public evaluations of emotional understanding, creative writing and story-related skills. It is a comparative reference, not a direct roleplay test.

Each benchmark is rescaled to 1–10 within its own leaderboard. We average results from the same publisher first, then give each publisher equal weight. Only verified model matches are included.

Creative Writing v3
zai-org/GLM-4.6: 1,411.4
145 Models · 2026-10-25

LiveBench · Story constraint following (2025-12-23)
glm-4.6: 29.37
65 Models · 2026-10-25

LiveBench · Theory of mind (2025-12-23)
glm-4.6: 50
65 Models · 2026-10-25

Roleplay combines public evaluations of emotional understanding, creative writing and story-related skills. It is a comparative reference, not a direct roleplay test.

Each benchmark is rescaled to 1–10 within its own leaderboard. We average results from the same publisher first, then give each publisher equal weight. Only verified model matches are included.

Creative Writing v3
GLM-5.3: 2,076.7
145 Models · 2026-10-25

LiveBench · Story constraint following
glm-5.3: 72.13
71 Models · 2026-10-25

LiveBench · Theory of mind
glm-5.3: 88.46
71 Models · 2026-10-25

No matching public benchmark is available for this model.

Roleplay combines public evaluations of emotional understanding, creative writing and story-related skills. It is a comparative reference, not a direct roleplay test.

Each benchmark is rescaled to 1–10 within its own leaderboard. We average results from the same publisher first, then give each publisher equal weight. Only verified model matches are included.

EQ-Bench 3
zai-org/GLM-4.5: 1,322
83 Models · 2026-10-25

Creative Writing v3
zai-org/GLM-4.5: 1,343.9
145 Models · 2026-10-25

LiveBench · Story constraint following (2025-05-30)
glm-4.5: 82.17
70 Models · 2026-10-25

Roleplay combines public evaluations of emotional understanding, creative writing and story-related skills. It is a comparative reference, not a direct roleplay test.

Each benchmark is rescaled to 1–10 within its own leaderboard. We average results from the same publisher first, then give each publisher equal weight. Only verified model matches are included.

EQ-Bench 3
zai-org/GLM-5: 1,495
83 Models · 2026-10-25

Creative Writing v3
zai-org/GLM-5: 1,600.6
145 Models · 2026-10-25

Roleplay combines public evaluations of emotional understanding, creative writing and story-related skills. It is a comparative reference, not a direct roleplay test.

Each benchmark is rescaled to 1–10 within its own leaderboard. We average results from the same publisher first, then give each publisher equal weight. Only verified model matches are included.

LiveBench · Story constraint following
glm-5.3-flash: 59.88
71 Models · 2026-10-25

LiveBench · Theory of mind
glm-5.3-flash: 73.08
71 Models · 2026-10-25