List your company

Reading Comprehension on ReCoRD

93.8AccuracyPaLM 2-L
66.822473.826280.8387.8338Apr 5, 2022Jul 14, 2022Oct 22, 2022Jan 31, 2023May 11, 2023Aug 19, 2023Nov 28, 2023

Evaluation results

MethodLinks
PaLM 2-Lprompting=1-shot2023.0593.8—
PaLM-2 Lprotocol=1-shot2023.1193.8—
Falcon-180Bprotocol=1-shot2023.1193.2—
PaLM 540BEvaluation Protocol=0-shot2022.0492.9—
PaLM 540BEvaluation Protocol=Few-shot, Number of Shots=22022.0492.9—
PaLMprompting=1-shot2023.0592.8—
PaLMprotocol=1-shot2023.1192.8—
PaLM 540BEvaluation Protocol=1-shot2022.0492.8—
PaLM 2-Mprompting=1-shot2023.0592.4—
PaLM-2 Mprotocol=1-shot2023.1192.4—
PaLM 2-Sprompting=1-shot2023.0592.1—
PaLM-2 Sprotocol=1-shot2023.1192.1—
LLaMA# of params=7B2023.0491.4—
Prior SOTAEvaluation Protocol=Few-shot, Number of Shots=22022.0490.6—
GLaM 62B/64EEvaluation Protocol=0-shot2022.0490.3—
GLaM 62B/64EEvaluation Protocol=1-shot2022.0490.3—
GPT-3Shots=12023.0390.2—
GPT-J# of params=6B2023.0488.6—
Alpaca# of params=7B2023.0487.4—
BloombergGPTShots=12023.0382.79—
OPT66BShots=12023.0382.53—
LaMini-LLaMA# of params=7B2023.0480.8—
BLOOM176BShots=12023.0378.01—
LaMini-GPT-J# of params=6B2023.0469.2—
GPT-NeoXShots=12023.0367.86—
MHF (H3B10K)Model Scale=100M, Embedding Parameters (Emb)=25M, Decoder Parameters (Dec)=87M, Evaluation Protocol=Zero-shot2026.06—48.21
MHF (H3B10K)Model Scale=1B, Embedding Parameters (Emb)=65M, Decoder Parameters (Dec)=0.9B, Evaluation Protocol=Zero-shot2026.06—64.51
MHF (H4B16K)Model Scale=100M, Embedding Parameters (Emb)=52M, Decoder Parameters (Dec)=87M, Evaluation Protocol=Zero-shot2026.06—50.11
MHF (H4B16K)Model Scale=1B, Embedding Parameters (Emb)=138M, Decoder Parameters (Dec)=0.9B, Evaluation Protocol=Zero-shot2026.06—64.9
MHF (H4B16K)Model Scale=3B, Embedding Parameters (Emb)=138M, Decoder Parameters (Dec)=2.8B, Evaluation Protocol=Zero-shot2026.06—64.13
Rnd. GuessModel Scale=N/A, Embedding Parameters (Emb)=-, Decoder Parameters (Dec)=-, Evaluation Protocol=Random Guessing2026.06—19.1
StandardModel Scale=100M, Embedding Parameters (Emb)=25M, Decoder Parameters (Dec)=87M, Evaluation Protocol=Zero-shot2026.06—49.47
StandardModel Scale=1B, Embedding Parameters (Emb)=65M, Decoder Parameters (Dec)=0.9B, Evaluation Protocol=Zero-shot2026.06—63.2
StandardModel Scale=3B, Embedding Parameters (Emb)=65M, Decoder Parameters (Dec)=2.8B, Evaluation Protocol=Zero-shot2026.06—62.26
Standard+2LModel Scale=1B, Embedding Parameters (Emb)=65M, Decoder Parameters (Dec)=1.0B, Evaluation Protocol=Zero-shot2026.06—63.78
Standard+4LModel Scale=100M, Embedding Parameters (Emb)=25M, Decoder Parameters (Dec)=116M, Evaluation Protocol=Zero-shot2026.06—53.08