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

Multi-modal Reasoning on M3CoT

82.68Accuracy

Gemini-3.0-Flash

18.210434.947751.68568.4223Jul 27, 2025Sep 15, 2025Nov 4, 2025Dec 25, 2025Feb 13, 2026Apr 4, 2026May 25, 2026
Updated 8d ago

Evaluation Results

MethodLinks
2025.07
82.68-
2025.07
81.76-
2025.07
81.46-
2025.07
81.4-
2025.07
81.17-
2025.07
80.5-
2025.07
80.02-
2025.07
80-
2025.07
78.3-
2025.07
76.06-
2025.07
71-
2025.07
70.46-
2025.07
69.22-
2025.07
68.34-
2026.04
66.9479.13
2025.07
66.75-
2025.07
66.25-
2025.07
65.32-
2025.07
65.1-
2025.07
63-
2025.07
62.82-
2025.07
62-
2026.04
60.5770.97
2026.04
60.3272.24
2025.07
60.15-
2025.07
59.12-
2025.07
57.23-
2025.07
56.54-
2025.07
55.32-
2025.07
54.78-
2026.04
51.0159.18
2026.04
50.9659.71
2025.07
50-
2025.07
50-
2025.07
48.7-
2026.04
48.2558.73
2025.07
48.1-
2025.07
46.45-
2026.04
44.1157.96
2025.07
42.08-
2026.05
41.99-
2026.04
41.951.46
2025.07
40.72-
2026.05
40.38-
2026.05
39.82-
2026.05
39.6-
2026.05
39.23-
2026.04
39.251.01
2025.07
38.78-
2026.05
38.47-
2026.05
38.35-
2026.05
38.06-
2026.05
37.94-
2026.05
37.68-
2026.05
37.39-
2026.05
37.26-
2026.05
37.16-
2026.05
36.83-
2025.07
36.8-
2026.05
36.66-
2026.05
36.43-
2026.05
36.2-
2026.05
35.86-
2026.05
35.86-
2026.05
34.81-
2026.05
34.57-
2026.05
34.56-
2026.05
34.24-
2026.05
34.11-
2026.05
33.48-
2026.04
33.4344.2
2026.05
32.95-
2026.05
29.31-
2026.05
29.09-
2026.05
28.82-
2026.05
28.72-
2026.05
28.42-
2026.05
28.24-
2026.05
28.03-
2026.05
27.91-
2026.04
27.7133.81
2026.05
27.61-
2026.05
26.85-
2026.05
26.33-
2026.05
26.19-
2026.05
26.01-
2026.05
25.5-
2026.05
24.68-
2026.05
24.42-
2026.04
20.6932.04