Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Question Answering on MedQA-USMLE (test)

94.34Accuracy

Kimi-K2-Thinking-1TB

22.11240.863559.61578.3665Apr 13, 2021Feb 1, 2022Nov 22, 2022Sep 12, 2023Jul 2, 2024Apr 22, 2025Feb 11, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.01
94.34-
2026.01
93.72-
2026.01
92.22-
2026.01
88.22-
2026.01
88.14-
2026.01
87.9-
2026.01
87.52-
2026.01
87.27-
2023.08
87-
2022.07
87-
2023.05
86.5-
2022.07
86.5-
2023.05
86.1-
2022.07
86.1-
2026.01
86.02-
2023.05
85.4-
2026.01
84.68-
2026.01
83.5-
2026.01
83.27-
2026.01
82.17-
2023.05
81.4-
2026.01
80.8-
2026.02
78.142,732
2026.01
77.17-
2026.02
77.13388
2026.02
77.1645
2026.02
76.831,693
2026.02
76.83549
2026.01
76.7-
2026.02
76.61,472
2026.02
76.61,325
2026.02
76.4987
2026.01
76.05-
2026.01
75.3-
2026.01
71.56-
2026.01
68.4-
2026.01
68.31-
2022.12
67.6-
2023.05
67.6-
2026.01
67.29-
2026.02
66.2315
2026.01
65.61-
2026.01
65.05-
2022.07
62.5-
2022.07
60.2-
2026.01
60.02-
2022.07
60-
2023.08
57-
2023.08
50.4-
2022.12
50.3-
2022.07
50.3-
2023.08
50-
2022.10
47.5-
2022.12
47.5-
2023.08
46-
2026.01
45.89-
2023.08
45.3-
2022.10
45.1-
2022.12
45.1-
2022.10
45-
2023.08
44.7-
2022.03
44.6-
2022.10
44.6-
2023.08
44.6-
2022.12
44.4-
2026.01
41.71-
2026.01
40.29-
2022.03
40-
2026.01
39.35-
2022.03
38.5-
2022.03
38.1-
2022.10
38.1-
2022.12
38.1-
2022.03
38-
2021.04
38-
2026.01
37.84-
2026.01
37.65-
2021.04
37.2-
2022.03
36.7-
2022.10
36.7-
2021.04
36.7-
2026.01
36.39-
2026.01
35.04-
2021.04
35-
2023.08
34.4-
2021.04
34.3-
2026.01
34.27-
2021.04
34.1-
2026.01
33.62-
2022.12
33.3-
2026.01
33.15-
2026.01
32.81-
2026.01
31.31-
2026.01
31.22-
2026.01
28.2-
2023.08
27.2-
2023.08
27.1-
2026.02
25.27-
2026.02
25.06-
2026.02
24.89-
Showing 100 of 101 rows