Qwen/Qwen3.5-122B-A10B
diamond · 86.6 source-defined score; unit unspecified
Source-qualified evaluations, report statistics and safety observations.
diamond · 86.6 source-defined score; unit unspecified
photographed · 76.3 source-defined score; unit unspecified
full-spectrum-pass-rate · 18.181818181818183 source-defined score; unit unspecified
mmlu_pro · 35.3 source-defined score; unit unspecified
terminalbench_2_1 · 51.7 source-defined score; unit unspecified
warping · 88.86 source-defined score; unit unspecified
swe_bench_multilingual_%_resolved · 81 source-defined score; unit unspecified
mmlu_pro · 11.95 source-defined score; unit unspecified
mmlu_pro · 82 source-defined score; unit unspecified
hi · 39.6 source-defined score; unit unspecified
OmniCompass-VL · 43.5 source-defined score; unit unspecified
deep_swe · 73.7 source-defined score; unit unspecified
table · 74.9 source-defined score; unit unspecified
prompt_level_loose · 82.8 source-defined score; unit unspecified
skew · 92.66 source-defined score; unit unspecified
care_management · 6.7 source-defined score; unit unspecified
MathArena/aime_2026 · 97.1 source-defined score; unit unspecified
hle · 43.4 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.