Comparing across prompt versions
The selected runs span multiple prompt versions (v1.1, v1.3, v1.5). Scores from different versions may not be directly comparable.
qwen3.7-flash85very good
111.9s17,690 tokensv1.3
muse-spark-1.185very good
18.2s5,338 tokensv1.3
gemini-3.6-flash85very good
21.1s4,570 tokensv1.3
mimo-v2.530bad
19.9s7,521 tokensv1.3
seed-2.0-lite30bad
60.1s11,523 tokensv1.3
glm-5v-turbo30bad
78.4s11,718 tokensv1.3
seed-2-1-turboUnscored
99.3s9,239 tokensv1.5
muse-spark-1.2Unscored
18.1s5,500 tokensv1.5
gemini-3.7-flashUnscored
17.7s3,029 tokensv1.5
mimo-v2.5Unscored
26.2s6,145 tokensv1.5
muse-spark-1.2Unscored
19.5s5,559 tokensv1.5
gemini-3.7-flashUnscored
11.3s2,914 tokensv1.5
muse-spark-1.2Unscored
19.8s5,283 tokensv1.5
gemini-3.7-flashUnscored
16.2s3,065 tokensv1.5
muse-spark-1.2Unscored
23.8s8,508 tokensv1.5
gemini-3.7-flashUnscored
17.5s4,457 tokensv1.5
gemini-3.1-flash-liteUnscored
16.8s1,646 tokensv1.1
qwen3.7-flashUnscored
100.3s6,349 tokensv1.1
gemini-3.6-flashUnscored
21.8s2,634 tokensv1.1