live
weekly refresh
basedagi.org
benchmark evidence

AlpacaEval 2.0 LC Win Rate

Instruction following evaluated via length-controlled win rate.

winner on AlpacaEval 2.0 LC Win Rate
direct benchmark result, not a broad vertical composite | source row dated 2026-05-08
scored on 2026-05-08
latest mapped results | top 20
#ModelScoreEvidenceTested
1Meta: Llama 3.3 70B Instruct
Meta Llama
34.4
model-only
independent_benchmark
2026-05-08
what this result means

Instruction following evaluated via length-controlled win rate.

This benchmark contributes direct public evidence. Read its scope before generalizing the result.

A win here is a win on AlpacaEval 2.0 LC Win Rate. Broad task pages require independent corroboration before naming a general winner.

source record
category: writing
metric: lc_win_rate
matched models: 1
latest source date: 2026-05-08
direction: higher is better
inspect upstream source ->