TokenReply

Loading…

Reload
74
Classic UIClassic
ClassicSign in

Qwen

Qwen models · 7

Roleplay

No matching public benchmark is available for this model.

Not measured
Input / 1M tokens
$0.2

qwen3.8-27b

Qwen3.8 27B is an open-weight dense multimodal Qwen model with text, image, and video input, a 256K-token context window, tool use, and adjustable reasoning.

Roleplay

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
Qwen/Qwen3.8-27B: 1,670.5
145 Models · 2026-10-25

LiveBench · Story constraint following
qwen3.8-27b: 73.1
71 Models · 2026-10-25

LiveBench · Theory of mind
qwen3.8-27b: 59.62
71 Models · 2026-10-25

6.5/ 10
Input / 1M tokens
$0.45

qwen3.8-flash

Alibaba Qwen3.8 Flash, a 125B-parameter multimodal MoE reasoning model with a 1M-token context window, built for agentic workflows, coding and long-video analysis.

Roleplay

No matching public benchmark is available for this model.

Not measured
Input / 1M tokens
$0.16
Roleplay

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
qwen3.7-max: 76.28
71 Models · 2026-10-25

LiveBench · Theory of mind
qwen3.7-max: 78.85
71 Models · 2026-10-25

7.9/ 10
Input / 1M tokens
$1.25

qwen3.8-omni-flash

Alibaba Qwen3.8 Omni Flash, an omni-modal reasoning model with native audio and video understanding and a 1M-token context.

Roleplay

No matching public benchmark is available for this model.

Not measured
Input / 1M tokens
$0.15

qwen3.7-flash

Qwen3.7 Flash is a fast multimodal Qwen model with text, image, and video input, a 1M-token context window, tool use, and optional reasoning.

Roleplay

No matching public benchmark is available for this model.

Not measured
Input / 1M tokens
$0.03–$0.2Variable pricing
Roleplay

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
qwen3.6-plus: 56.87
71 Models · 2026-10-25

LiveBench · Theory of mind
qwen3.6-plus: 67.31
71 Models · 2026-10-25

3.3/ 10
Input / 1M tokens
$0.5