Codesota · Models · Whisper-v3-large + LLaMA-3.1-8B (cascade)OpenAI / Meta1 results · 1 benchmarks

Model card

Whisper-v3-large + LLaMA-3.1-8B (cascade).

OpenAI / Metaopen-source

§ 02 · Benchmarks

Every benchmark Whisper-v3-large + LLaMA-3.1-8B (cascade) has a recorded score for.

#	Benchmark	Area · Task	Metric	Value	Rank	Date	Source
01	voicebench	—	overall-score	77.5%	#4/13	2026-04-20	source ↗

Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.

§ 05 · Related models

Other OpenAI / Meta models scored on Codesota.

Whisper+LLaMA-3 (cascade)

0 results

§ 06 · Sources & freshness

Where these numbers come from.

codesota-api

result

1 of 1 rows marked verified.