Qwen3.5 2B (Reasoning)

qwen3-5-2b · 4 samples · combined / raw

Scoring

Choose the quality benchmark and final score formula for this model.

Cost adjustment

Tune formulas that account for benchmark cost.

Score over time

15.2 13.2 #1 · 14.2 · 2026-05-11 23:17:33#2 · 14.2 · 2026-05-12 00:00:09#3 · 14.2 · 2026-05-12 01:00:09#4 · 14.2 · 2026-05-12 02:00:11

Cost over time

$46.6 $44.6 #1 · $45.6 · 2026-05-11 23:17:33#2 · $45.6 · 2026-05-12 00:00:09#3 · $45.6 · 2026-05-12 01:00:09#4 · $45.6 · 2026-05-12 02:00:11
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#4 2026-05-12 02:00:11 14.2 14.2 $45.6 16.3 3.5 23.0 43.0
#3 2026-05-12 01:00:09 14.2 14.2 $45.6 16.3 3.5 23.0 43.0
#2 2026-05-12 00:00:09 14.2 14.2 $45.6 16.3 3.5 23.0 43.0
#1 2026-05-11 23:17:33 14.2 14.2 $45.6 16.3 3.5 23.0 43.0