Visual Reasoning on CLEVRER

13개 결과 · ⬇ CSV · JSON

Rank	Model	Average-per ques.	Descriptive	Explanatory-per opt.	Explanatory-per ques.	Predictive-per opt.	Predictive-per ques.	Counterfactual-per opt.	Counterfactual-per ques.	Paper	Code	Year
1	AI Core	95.24	96.46	99.94	99.81	93.96	93.96	96.61	90.72	Think before You Simulate: Symbolic Reasoning to Orchestrate Neural Computation for Counterfactual Question Answering	azreasoners/CRCG	2025
2	redherring	91.14	95.76	98.88	96.98	95.69	91.75	92.97	80.05
3	VRDP	90.24	93.4	96.3	91.94	95.68	91.35	94.83	84.29
4	Fighttttt	88.71	94.77	98.25	95.46	94.16	89.25	91.25	75.35
5	neural	88.27	94.01	98.47	95.99	93.49	87.48	91.42	75.61
6	NERV	88.05	95.04	98.18	94.98	93.11	87.28	91.12	74.89
7	DCL	75.52	90.7	89.58	82.82	90.52	82.03	80.38	46.52
8	troublesolver	73.3	88.37	89.19	81.56	84.83	72.38	79.96	50.89
9	v0.1	73.1	88.79	89.16	81.24	84.95	72.6	79.6	49.77
10	First_test	69.65	88.08	87.64	79.6	82.86	68.7	74.05	42.23
11	TS_NS_IMPERIAL	69.21	89.95	95.94	91.98	74.73	50.34	78.08	44.6
12	rnn_dyn	67.57	74.98	90.81	75.62	82.9	68.61	81.01	51.07
13	epoch 9 pgd_25_0.1_eps	60.25	81.39	83.42	72.78	78.5	60.95	66.65	25.89