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

Complex Reasoning on BIG-bench Hard (Subtask Breakdown)

88Abstract Algebra Score

InfiGFusion

64.0870.2976.582.71May 20, 2025
Updated 9d ago

Evaluation Results

MethodLinks
2025.05
8895.390.9173.9754.2274.681.2287.7388.496.896.897.69489.296.499.64070.0584.16
2025.05
8692.7490.9174.7553.6178.5779.5987.73889095.696.492.488.896.86213.235.8377.94
2025.05
8589.3282.6473.4154.2291.2778.3785.2839.680.882.883.28683.287.681.69.645.3573.29
2025.05
8292.7491.7475.7553.0177.7877.1486.588.894.496.898.485.688.496.46411.232.9977.43
2025.05
7390.1781.8271.9652.4168.2577.9685.2882.880.479.297.680.468.893.696.435.643.8575.53
2025.05
6592.3181.8268.649.466.6778.7884.6676.896.499.298.88262.89093.237.268.9877.37