List your company

Question Answering on NarrativeQA No Trun. latest (test)

23.96Average ScoreCoA
-0.9003685.55376612.007918.462034Jun 4, 2024

Evaluation results

MethodLinks
CoABackbone=Claude-3-Opus, Context Window=8k2024.0623.96
CoABackbone=Claude-3-Haiku, Context Window=8k2024.0618.8
CoABackbone=Claude-3-Sonnet, Context Window=8k2024.0616.51
RAGBackbone=Claude-3-Sonnet, Context Window=8k2024.068.5
VanillaBackbone=Claude-3-Haiku, Context Window=200k2024.067.17
VanillaBackbone=Claude-3-Opus, Context Window=200k2024.066.56
RAGBackbone=Claude-3-Opus, Context Window=8k2024.065.86
RAGBackbone=Claude-3-Haiku, Context Window=8k2024.065.71
VanillaBackbone=Claude-3-Sonnet, Context Window=200k2024.065.15
CoABackbone=Claude-3-Opus, Context Window=8k2024.060.2438
CoABackbone=Claude-3-Haiku, Context Window=8k2024.060.1831
CoABackbone=Claude-3-Sonnet, Context Window=8k2024.060.1663
RAGBackbone=Claude-3-Sonnet, Context Window=8k2024.060.0909
VanillaBackbone=Claude-3-Haiku, Context Window=200k2024.060.08
VanillaBackbone=Claude-3-Opus, Context Window=200k2024.060.0723
RAGBackbone=Claude-3-Opus, Context Window=8k2024.060.0613
RAGBackbone=Claude-3-Haiku, Context Window=8k2024.060.0594
VanillaBackbone=Claude-3-Sonnet, Context Window=200k2024.060.0558