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
moonshotai/Kimi-K2.6: 1,548.3
83 Models · 2026-10-25

Creative Writing v3
moonshotai/Kimi-K2.6: 1,721.1
145 Models · 2026-10-25

LiveBench · Story constraint following
kimi-k2.6-thinking: 66.88
71 Models · 2026-10-25

LiveBench · Theory of mind
kimi-k2.6-thinking: 75
71 Models · 2026-10-25

No matching public benchmark is available for this model.

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.

LiveBench · Story constraint following
kimi-k2.7-code: 68.57
71 Models · 2026-10-25

LiveBench · Theory of mind
kimi-k2.7-code: 69.23
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
moonshotai/Kimi-K2.5: 1,530.2
83 Models · 2026-10-25

Creative Writing v3
moonshotai/Kimi-K2.5: 1,578.8
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.

Creative Writing v3
kimi-k3: 2,083.5
145 Models · 2026-10-25

LiveBench · Story constraint following
kimi-k3: 75.37
71 Models · 2026-10-25

LiveBench · Theory of mind
kimi-k3: 82.69
71 Models · 2026-10-25