Gemini 2.5 Flash (Reasoning)

gemini-2-5-flash-reasoning · 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

23.7 21.7 #1 · 22.7 · 2026-05-11 23:17:33#2 · 22.7 · 2026-05-12 00:00:09#3 · 22.7 · 2026-05-12 01:00:09#4 · 22.7 · 2026-05-12 02:00:11

Cost over time

$173 $171 #1 · $172 · 2026-05-11 23:17:33#2 · $172 · 2026-05-12 00:00:09#3 · $172 · 2026-05-12 01:00:09#4 · $172 · 2026-05-12 02:00:11
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#4 2026-05-12 02:00:11 22.7 22.7 $172 27.0 22.2 18.8 69.1
#3 2026-05-12 01:00:09 22.7 22.7 $172 27.0 22.2 18.8 69.1
#2 2026-05-12 00:00:09 22.7 22.7 $172 27.0 22.2 18.8 69.1
#1 2026-05-11 23:17:33 22.7 22.7 $172 27.0 22.2 18.8 69.1