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

Coreference Resolution on OntoNotes

93.7MUC

GPT-4

Updated 26d ago

Evaluation Results

Method
GPT-4 2025.12	93.7	88.8	82.8	88.4
GPT-4 2025.10	93.7	88.8	82.8	88.4
ImCoref-CeCogpt4o 2025.12	91.2	84.9	81.8	86
ImCoref-CeSgpt4 2025.10	91.2	84.9	81.8	86
ImCoref-CeSdpsk 2025.10	90.8	84.6	81.6	85.7
MEIC-DT 2025.12	90.5	84.4	80.2	85.1
ImCoref-CeSqwen 2025.10	89.6	84.1	81	84.9
InstructGPT 2025.12	89.2	79.4	73.7	80.8
InstructGPT 2025.10	89.2	79.4	73.7	80.8
ImCorefmes 2025.12	88.2	83.6	81	84.3
ImCoref 2025.10	88.2	83.6	81	84.3
CorefQA 2025.12	88	82.2	79.1	83.1
Maverickmes 2025.12	88	82.8	79.9	83.6
CorefQA 2025.10	88	82.2	79.1	83.1
Maverickmes 2025.10	88	82.8	79.9	83.6
Maverickincr 2025.12	87.9	82.7	79.8	83.5
Link-Append 2025.12	87.8	82.6	79.5	83.3
Link-Append 2025.10	87.8	82.6	79.5	83.3
seq2seq 2025.12	87.6	82.4	79.5	83.2
seq2seq 2025.10	87.6	82.4	79.5	83.2
ASP 2025.12	87.2	81.7	78.6	82.5
ASP 2025.10	87.2	81.7	78.6	82.5
LingMess 2025.12	86.6	80.5	77.3	81.4
LingMess 2025.10	86.6	80.5	77.3	81.4
wl-coref 2025.12	86.3	79.9	76.6	81
Dual-cache 2025.12	86.3	80.3	76.8	81.1
wl-coref 2025.10	86.3	79.9	76.6	81
Dual cache 2025.10	86.3	80.3	76.8	81.1
GPT-3.5-turbo 2025.12	86.2	79.3	68.3	77.9
GPT-3.5-turbo 2025.10	86.2	79.3	68.3	77.9
s2e-coref 2025.12	85.8	79.1	76.1	80.3
s2e-coref 2025.10	85.8	79.1	76.1	80.3
c2f-coref 2025.12	85.3	78.1	75.3	79.6
Icoref 2025.12	85.3	77.8	75.2	79.4
longdoc 2025.12	85.3	78	75.3	79.6
c2f-coref 2025.10	85.3	78.1	75.3	79.6
Icoref 2025.10	85.3	77.8	75.2	79.4
longdoc 2025.10	85.3	78	75.3	79.6
f-coref 2025.12	84.4	76.6	74.5	78.5
f-coref 2025.10	84.4	76.6	74.5	78.5
GPT-4 2025.12	73.7	62.7	52.3	62.9
GPT-4 2025.10	73.7	62.7	52.3	62.9
InstructGPT 2025.12	70.4	58.4	51.7	60.1
InstructGPT 2025.10	70.4	58.4	51.7	60.1
GPT-3.5-turbo 2025.12	66.9	55.5	46.5	56.3
GPT-3.5-turbo 2025.10	66.9	55.5	46.5	56.3