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

Hallucination Evaluation on CHAIR

72.8CHAIR_s

M3ID

45.55252.62659.766.774May 24, 2024Sep 7, 2024Dec 22, 2024Apr 7, 2025Jul 22, 2025Nov 5, 2025Feb 19, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2026.01
72.821.1
2026.01
7120.1
2025.06
66.812.7
2026.01
62.318.2
2026.01
60.817.6
2026.01
60.817.9
2026.01
60.417.2
2026.02
6020.1
2026.02
59.317.5
2026.01
57.816.3
2026.01
57.616.7
2026.01
57.417.6
2026.02
5715.9
2026.02
5717
2026.01
56.615.8
2025.06
56.311.4
2026.01
56.315.4
2026.02
56.216.3
2026.01
56.216.4
2026.01
55.616.6
2026.01
55.216.2
2026.01
55.217.6
2026.01
55.116.4
2026.01
55.115.7
2026.02
5516.3
2026.01
54.816.2
2026.01
54.615.4
2026.02
54.416.6
2026.01
54.215.6
2026.01
54.214.8
2025.06
549.3
2026.02
5418.1
2026.02
5415.78
2026.01
53.815.7
2026.02
53.712.8
2026.01
53.415.8
2026.01
53.415.1
2026.01
53.115.1
52.9314.99
2026.01
52.414.2
2026.01
52.414.6
2026.01
52.314.7
2026.01
52.215.2
2026.01
52.214.2
2026.01
52.215.5
2026.01
52.116.7
2026.02
5216.13
2026.01
51.815.3
2026.01
51.816.3
2026.01
51.614.2
2026.01
51.414.1
2026.01
51.214.8
2026.01
51.214.6
2026.01
5114.8
2026.02
5113.64
2026.01
50.913.5
2024.05
50.811.7
2026.01
50.413.6
2026.01
50.414.7
2026.01
50.113.7
2026.01
50.114.2
2026.02
50.0914.77
2026.02
5014.03
2026.02
49.8113.69
2026.02
49.814.3
2026.01
49.814.3
2026.01
49.816.2
2026.01
49.817.4
2026.01
49.815.6
2026.01
49.614.1
2026.01
49.614.1
2026.01
49.615.4
2026.01
49.415.6
2026.01
49.115.6
2026.02
4912.1
2026.02
4913.78
2026.01
48.814.2
2026.01
48.714.2
2026.01
48.714.4
2024.05
48.610.8
2026.01
48.614.3
2026.01
48.614.6
2026.01
48.614.1
2024.05
48.411.3
2026.01
48.413.2
2026.01
48.413.9
2026.01
48.212.6
2026.01
48.215.4
2026.01
4814.3
2026.02
47.814.6
2026.01
47.813.6
2026.02
47.711.3
2026.01
47.613.4
2024.05
47.311.2
2026.01
47.313.2
2024.05
47.210.8
2026.01
47.213.2
2026.02
4712.8
2026.01
46.912.3
2025.06
46.623.1
Showing 100 of 166 rows