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

Visual Reasoning on MathVerse

61.29Accuracy

Vanilla

18.410829.542940.67551.8071Apr 14, 2026Apr 16, 2026Apr 19, 2026Apr 21, 2026Apr 24, 2026Apr 26, 2026Apr 29, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
61.29-100-
2026.04
59.84---
2026.04
59.84---
2026.04
59.82---
2026.04
59.71---
2026.04
59.5---
2026.04
59.34---
2026.04
58.93---
2026.04
58.88---
2026.04
58.41---
2026.04
58.41---
2026.04
58.16---
2026.04
57.82---
2026.04
57.82---
2026.04
57.81---
2026.04
52.5485.782.9-
2026.04
50.7682.881.04-
2026.04
50.258283.8-
2026.04
46.1975.473.34-
2026.04
42.7669.871.48-
2026.04
42-100-
2026.04
40.466668.74-
2026.04
40.2295.892.44-
2026.04
39.5994.390.09-
2026.04
38.9492.787-
2026.04
37.5689.487.83-
2026.04
36.86060.42-
2026.04
36.548782.98-
2026.04
34.1381.381.01-
2026.04
33.955.355.24-
2026.04
32.2352.655.68-
2026.04
26.5963.363.55-
2026.04
26.1442.647.4-
2026.04
25.9842.446.4-
2026.04
25.8842.245.18-
2026.04
24.8459.159.54-
2026.04
23.6456.357.61-
2026.04
21.5751.456.66-
2026.04
20.5548.951.04-
2026.04
20.0647.849.42-
2025.10
---17.6
2025.10
---16.2
2025.10
---33.9
2025.10
---22.8
2025.10
---20.4
2025.10
---48.2
2025.10
---34.1
2025.10
---25.4
2025.10
---41.4
2025.10
---40
2025.10
---38.1
2025.10
---40
2025.10
---42
2025.10
---43.9