Comparing across prompt versions
The selected runs span multiple prompt versions (v1.0, v2.1). Scores from different versions may not be directly comparable.
gemini-3.6-flash95excellent
20.7s7,111 tokensv2.1
solar-pro430bad
82.2s4,329 tokensv2.1
nemotron-3.5-lightning10very bad
291.9s49,935 tokensv2.1
mistral-large-4-0Unscored
78.5s4,474 tokensv2.1
granite-4.2-8bUnscored
20.5s4,780 tokensv2.1
gpt-5.6-sol-proUnscored
41,110 tokensv2.1
hy-mt2-30b-a3bUnscored
17.3s4,587 tokensv2.1
hy-mt2-1.8bUnscored
11.2s4,763 tokensv2.1
glm-5.3Unscored
47.0s4,866 tokensv2.1
gemini-3.7-flashUnscored
32.6s8,903 tokensv2.1
muse-spark-1.2Unscored
22.6s9,859 tokensv2.1
deepseek-v4-pro-0813Unscored
395.1s32,850 tokensv2.1
muse-glimmer-30bUnscored
301.7s17,013 tokensv2.1
grok-4.6Unscored
197.4s12,998 tokensv2.1
gpt-5.6-terraUnscored
52.4s6,408 tokensv2.1
qwen3.8-maxUnscored
580.3s31,456 tokensv2.1
solar-pro4Unscored
22.6s4,824 tokensv1.0
muse-spark-1.2Unscored
31.0s10,803 tokensv1.0
gemini-3.5-flashUnscored
37.1s10,913 tokensv1.0
gpt-5.6-terraUnscored
73.0s8,701 tokensv1.0
qwen3.8-maxUnscored
169.6s11,099 tokensv1.0