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
gpt-5.5: 1,553.9
83 Models · 2026-10-25

Creative Writing v3
gpt-5.5: 1,844.6
145 Models · 2026-10-25

LiveBench · Story constraint following
gpt-5.5-xhigh: 72.55
71 Models · 2026-10-25

LiveBench · Theory of mind
gpt-5.5-xhigh: 84.62
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
gpt-5.6-luna: 1,831.7
145 Models · 2026-10-25

LiveBench · Story constraint following
gpt-5.6-luna-max: 69.07
71 Models · 2026-10-25

LiveBench · Theory of mind
gpt-5.6-luna-max: 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
gpt-5.6-sol: 1,973.5
145 Models · 2026-10-25

LiveBench · Story constraint following
gpt-5.6-sol-max: 75.92
71 Models · 2026-10-25

LiveBench · Theory of mind
gpt-5.6-sol-max: 84.62
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
gpt-6-astra: 2,174
145 Models · 2026-10-25

LiveBench · Story constraint following
gpt-6-astra-max: 73.98
71 Models · 2026-10-25

LiveBench · Theory of mind
gpt-6-astra-max: 84.62
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
openai/gpt-oss-20b: 985
83 Models · 2026-10-25

Creative Writing v3
openai/gpt-oss-20b: 664.4
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
gpt-5.4: 1,536.7
83 Models · 2026-10-25

Creative Writing v3
gpt-5.4: 1,840.9
145 Models · 2026-10-25

LiveBench · Story constraint following
gpt-5.4-xhigh: 79.02
71 Models · 2026-10-25

LiveBench · Theory of mind
gpt-5.4-xhigh: 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.

LiveBench · Story constraint following
gpt-6-luna-max: 63.28
71 Models · 2026-10-25

LiveBench · Theory of mind
gpt-6-luna-max: 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.

LiveBench · Story constraint following
gpt-6.1-sol-max: 70.82
gpt-6.1-sol-xhigh: 70.57
71 Models · 2026-10-25

LiveBench · Theory of mind
gpt-6.1-sol-max: 86.54
gpt-6.1-sol-xhigh: 86.54
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
gpt-5.6-terra: 1,856.3
145 Models · 2026-10-25

LiveBench · Story constraint following
gpt-5.6-terra-max: 66.83
71 Models · 2026-10-25

LiveBench · Theory of mind
gpt-5.6-terra-max: 86.54
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
gpt-6-sol: 2,124.6
145 Models · 2026-10-25

LiveBench · Story constraint following
gpt-6-sol-max: 66.93
71 Models · 2026-10-25

LiveBench · Theory of mind
gpt-6-sol-max: 84.62
71 Models · 2026-10-25