Comparing across prompt versions
The selected runs span multiple prompt versions (v1.0, v1.1). Scores from different versions may not be directly comparable.
gpt-6.1-terra-pro95excellent
27,385 tokensv1.1
kimi-k3.1-pro95excellent
1925.9s55,156 tokensv1.1
claude-opus-5.595excellent
68,865 tokensv1.1
gemini-4-carbon78very good
22,552 tokensv1.1
gemini-4-hydrogen70good
53,685 tokensv1.1
crouton-alpha70good
149.0s4,673 tokensv1.1
crouton-alpha70good
72.5s3,993 tokensv1.1
nex-n2.650mediocre
1184.7s125,573 tokensv1.1
gpt-6.1-terra50mediocre
8,766 tokensv1.1
muse-wonder30bad
206.9s18,754 tokensv1.1
deepseek-v4.1-flash-101730bad
197.0s59,219 tokensv1.1
ernie-5.5-flash-preview:freeUnscored
267.4s131,573 tokensv1.1
ernie-5.5-flash-previewUnscored
236.7s131,573 tokensv1.1
glm-5.3-flashUnscored
1164.2s200,485 tokensv1.1
muse-emberUnscored
30.4s16,692 tokensv1.1
hy4Unscored
761.5s66,036 tokensv1.1
hy4Unscored
854.5s66,036 tokensv1.1
muse-spark-1.3Unscored
210.7s22,066 tokensv1.1
claude-haiku-5.5Unscored
317.6s72,106 tokensv1.1
particle-1Unscored
110.6s41,853 tokensv1.1
gpt-6.1-sol-proUnscored
21,756 tokensv1.1
deepseek-v4.1-flash-1017Unscored
176.7s42,758 tokensv1.0