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

Fact Checking on RealHitBench

70.91Exact Match

DeepSeek-R1

-2.836416.309335.45554.6007Jun 16, 2025Aug 5, 2025Sep 24, 2025Nov 14, 2025Jan 3, 2026Feb 22, 2026Apr 14, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2025.06
70.9179.45
2026.04
70.9179.45
69.177.18
2026.04
67.373.06
2026.04
67.1373.14
2026.04
66.874.03
2026.04
66.6473.44
2026.04
66.4774.46
2025.12
66.31-
2025.06
65.8273.32
2026.04
65.7471.94
2026.04
65.7472.93
2025.12
65.08-
2025.12
65-
2025.06
64.572.41
64.0969.22
2025.12
63.85-
62.768.55
2025.06
62.4569.01
2025.12
62.36-
2025.06
62.0468.08
2025.06
60.3168.97
2026.04
60.3168.97
2025.12
60.23-
2025.06
59.6566.34
2025.06
59.0866.14
2026.04
59.0866.14
2025.12
58.83-
2026.03
58.2264.47
2026.04
58.1862.75
57.8565.87
2026.04
57.2762.54
57.2153.42
2026.04
56.9462.6
2025.12
56.53-
2026.04
56.5361.14
2025.06
55.665.19
2025.12
55.22-
2025.06
53.0864.53
2026.04
53.0864.53
52.161.84
2025.06
51.9362.15
2026.04
51.9362.15
2026.04
51.2757.56
2026.04
51.1957.45
2025.06
50.3757.62
48.7353.64
2026.04
48.5654.7
2026.03
48.1956.49
46.1852.44
2025.06
46.153.8
46.153.8
2026.04
45.1150.12
2025.06
44.1352.41
2025.06
43.3951.87
2026.03
43.3951.87
2025.12
43.06-
2026.04
42.8148.54
38.2544.12
2026.04
37.6345.03
2026.04
36.2442.31
2026.04
34.5147.68
2025.06
33.5340.41
2025.12
33.44-
2025.06
33.4439.49
2026.04
33.244.15
2025.06
32.7945.19
2026.04
32.3744.93
2026.03
30.4237.44
2025.12
30.32-
2025.06
30.3244.93
2026.04
30.3244.93
2025.06
28.9543.13
2025.06
28.538.34
2025.06
28.134.53
2026.03
25.432.15
23.7536.08
2025.06
22.4333.29
2025.06
19.3932.54
2025.06
18.6538.39
2026.04
18.6538.39
18.4138.44
2026.03
17.9323.5
2026.03
16.6119.76
15.8426.55
2025.06
15.6131.88
2025.06
14.319.35
2025.06
11.1817.75
2025.06
8.7114.34
2026.03
6.917.65
2025.06
5.519.37
2025.06
4.197.05
2025.06
3.467.23
2025.12
0-