Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

LLM Alignment on AlpacaEval ULTRA 2.0 (test)

31.58LC WR (%)

COALA

5.16412.02218.8825.738May 22, 2026
Updated 9d ago

Evaluation Results

MethodLinks
2026.05
31.5830.21445
2026.05
26.4124.86476
2026.05
22.9425.93452
2026.05
20.8420.91459
2026.05
20.6418.32552
2026.05
18.8915.81503
2026.05
17.6815.56453
2026.05
16.0412.28350
2026.05
14.8812.76459
2026.05
12.9110.95354
2026.05
7.415.62546
2026.05
6.186.11463