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

Multimodal Mathematical Reasoning on MATH-Vision (testmini)

21.05Alg Score

ToT

-0.8424.841510.52516.2085Jun 10, 2025
Updated 3d ago

Evaluation Results

MethodLinks
2025.06
21.0526.3215.7921.0521.0515.7915.7915.795.2631.5836.8421.0515.7942.1110.5310.5320.39
2025.06
21.0531.5821.0521.0515.7910.5310.5342.1142.1115.7936.8410.5326.3231.5852.6336.8426.64
2025.06
15.7915.7910.5321.0505.265.2621.0515.7957.8915.7936.8415.7915.7915.7926.3218.42
2025.06
15.7910.5315.7910.5315.7910.5326.3215.7915.7910.53010.5315.7926.3221.0510.5314.47
2025.06
10.5342.1115.7931.5821.0521.0536.8426.3242.1126.3231.5815.7931.5836.8426.3226.3228.29
2025.06
5.2631.58021.0521.0526.3226.3215.7915.7936.8426.3221.0510.5321.0515.7910.5319.08
2025.06
5.2621.0510.5315.7915.7910.53010.5321.0515.7910.5305.2615.795.2615.7911.18
2025.06
026.3221.0515.7942.1126.325.2626.3215.7921.0531.5810.5321.0531.5831.5821.0521.71