Llama 3.1 Instruct 70B

llama-3-1-instruct-70b · 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

10.5 8.5 #1 · 9.5 · 2026-05-11 23:17:33#2 · 9.5 · 2026-05-12 00:00:09#3 · 9.5 · 2026-05-12 01:00:09#4 · 9.5 · 2026-05-12 02:00:11

Cost over time

$139 $137 #1 · $138 · 2026-05-11 23:17:33#2 · $138 · 2026-05-12 00:00:09#3 · $138 · 2026-05-12 01:00:09#4 · $138 · 2026-05-12 02:00:11
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#4 2026-05-12 02:00:11 9.5 9.5 $138 12.5 10.9 5.1 -
#3 2026-05-12 01:00:09 9.5 9.5 $138 12.5 10.9 5.1 -
#2 2026-05-12 00:00:09 9.5 9.5 $138 12.5 10.9 5.1 -
#1 2026-05-11 23:17:33 9.5 9.5 $138 12.5 10.9 5.1 -