Qwen/Qwen3.5-27B
hle · 48.5 source-defined score; unit unspecified
Source-qualified evaluations, report statistics and safety observations.
hle · 48.5 source-defined score; unit unspecified
text_content · 89.7 source-defined score; unit unspecified
lhtb_solved · 0 source-defined score; unit unspecified
hi · 72.2 source-defined score; unit unspecified
es · 69.3 source-defined score; unit unspecified
macos_common_macos · 53.8 source-defined score; unit unspecified
diamond · 92.6 source-defined score; unit unspecified
mmlu_pro · 47.87 source-defined score; unit unspecified
terminalbench_2_1 · 84.3 source-defined score; unit unspecified
diamond · 75.57 source-defined score; unit unspecified
es · 54.7 source-defined score; unit unspecified
ale-cli-score · 44.15980756094993 source-defined score; unit unspecified
overall · 48.0152 source-defined score; unit unspecified
apex-agents · 3.1 source-defined score; unit unspecified
multimodal · 46.83 source-defined score; unit unspecified
nl · 61.4 source-defined score; unit unspecified
long_tiny_text · 83.5 source-defined score; unit unspecified
deep_swe · 22 source-defined score; unit unspecified
These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.