Skip to content

Models Bundles Runs Playground Leaderboard Compare Judges Settings

@2026·Made by MiMs

RUN #26e3

mini-benchmark-v1COMPLETED

Show judge streams

32/32 tasks · 28:21 elapsedSpend $0.9604 ($2.00 cap)

Model

Roleplay

Coding

Math

Research

Mktg

Poster

Story

Judging

avg

qwen3.6-plusqwen/qwen3.6-plus

1.3 1.3 0.0 0.0 1.3 0.0 1.3 0.5

0.7

qwen3.7-maxqwen/qwen3.7-max

1.3 2.8 10.0 1.3 0.0 0.5 1.3 0.5

2.2

qwen3.7-plusqwen/qwen3.7-plus

1.3 3.5 10.0 1.3 1.3 1.3 1.3 9.4

3.6

qwen3.8-maxqwen/qwen3.8-max

0.0 0.0 5.0 9.5 0.0 1.3 0.3 3.0

2.4