OpenCompass/configs/datasets/bbh

BBH

python3 run.py --models hf_internlm2_7b --datasets bbh_gen_98fba6 --debug
python3 run.py --models hf_internlm2_chat_7b --datasets bbh_gen_5b92b0 --debug

Base Models

model	bbh
llama-7b-turbomind	33.34
llama-13b-turbomind	37.99
llama-30b-turbomind	49.86
llama-65b-turbomind	58.26
llama-2-7b-turbomind	38.27
llama-2-13b-turbomind	45.68
llama-2-70b-turbomind	64.78
llama-3-8b-turbomind	59.69
llama-3-70b-turbomind	79.16
internlm2-1.8b-turbomind	36.03
internlm2-7b-turbomind	63.56
internlm2-20b-turbomind	71.29
qwen-1.8b-turbomind	22.53
qwen-7b-turbomind	45.89
qwen-14b-turbomind	56.75
qwen-72b-turbomind	63.35
qwen1.5-0.5b-hf	20.54
qwen1.5-1.8b-hf	27.01
qwen1.5-4b-hf	34.81
qwen1.5-7b-hf	39.87
qwen1.5-14b-hf	50.38
qwen1.5-32b-hf	67.47
qwen1.5-72b-hf	58.81
qwen1.5-moe-a2-7b-hf	39.46
mistral-7b-v0.1-hf	56.71
mistral-7b-v0.2-hf	57.32
mixtral-8x7b-v0.1-hf	68.46
mixtral-8x22b-v0.1-hf	79.48
yi-6b-hf	44.82
yi-34b-hf	66.37
deepseek-7b-base-hf	42.88
deepseek-67b-base-hf	71.86

Details

model	temporal_sequences	disambiguation_qa	date_understanding	tracking_shuffled_objects_three_objects	penguins_in_a_table	geometric_shapes	snarks	ruin_names	tracking_shuffled_objects_seven_objects
llama-7b-turbomind	23.60	46.00	44.80	36.40	30.14	0.00	46.07	21.60	15.20
llama-13b-turbomind	16.80	50.00	56.80	36.40	43.15	0.00	60.67	29.20	15.20
llama-30b-turbomind	33.60	60.00	76.40	29.20	57.53	0.00	59.55	62.40	17.20
llama-65b-turbomind	84.00	76.00	84.40	50.00	65.75	0.00	62.92	69.60	31.60
llama-2-7b-turbomind	12.00	46.80	60.00	34.00	32.19	0.00	49.44	32.80	18.40
llama-2-13b-turbomind	24.00	40.80	73.20	36.00	45.89	0.00	55.06	37.60	22.40
llama-2-70b-turbomind	75.60	66.80	88.80	73.60	69.86	0.00	73.60	60.80	57.60
llama-3-8b-turbomind	65.60	42.00	78.80	56.80	69.86	0.00	56.18	66.00	30.80
llama-3-70b-turbomind	100.00	82.80	91.60	100.00	86.30	0.00	81.46	77.20	94.40
internlm2-1.8b-turbomind	31.20	44.00	60.00	36.00	35.62	0.00	44.94	27.20	12.80
internlm2-7b-turbomind	94.80	75.60	86.40	53.60	69.18	0.00	59.55	68.00	46.00
internlm2-20b-turbomind	98.40	83.60	84.00	72.00	71.92	0.00	81.46	78.40	74.40
qwen-1.8b-turbomind	26.40	39.60	33.20	28.40	28.08	0.00	44.94	21.60	12.40
qwen-7b-turbomind	38.80	42.80	64.40	30.80	45.89	0.00	55.62	44.00	14.40
qwen-14b-turbomind	57.60	59.20	67.20	46.40	67.12	0.00	51.12	63.60	30.40
qwen-72b-turbomind	72.00	66.80	77.60	81.20	84.93	0.00	78.09	67.20	63.60
qwen1.5-0.5b-hf	15.20	37.20	20.40	30.40	18.49	8.40	44.94	11.20	14.00
qwen1.5-1.8b-hf	27.60	40.80	36.00	24.40	32.19	0.00	50.56	20.80	11.20
qwen1.5-4b-hf	10.40	44.40	47.20	36.80	44.52	24.80	46.63	20.80	14.80
qwen1.5-7b-hf	37.20	42.40	52.00	52.40	56.85	6.80	48.31	23.60	18.40
qwen1.5-14b-hf	38.80	62.80	73.60	24.80	69.86	26.80	66.29	52.80	2.00
qwen1.5-32b-hf	93.60	77.20	68.40	70.00	82.88	36.80	47.75	70.40	71.20
qwen1.5-72b-hf	75.60	66.00	78.80	72.80	80.82	0.00	75.84	64.80	44.40
qwen1.5-moe-a2-7b-hf	23.20	59.60	43.20	27.60	46.58	25.20	48.88	16.80	13.20
mistral-7b-v0.1-hf	73.60	53.60	76.40	45.20	56.85	28.00	64.04	66.00	21.60
mistral-7b-v0.2-hf	76.80	42.00	73.20	47.20	60.27	26.00	66.85	60.80	26.40
mixtral-8x7b-v0.1-hf	89.60	70.80	84.80	81.20	70.55	25.60	66.29	71.20	58.80
mixtral-8x22b-v0.1-hf	98.80	77.60	92.00	98.80	83.56	35.60	80.34	79.20	82.00
yi-6b-hf	32.80	46.40	64.40	34.40	47.26	28.80	60.11	45.60	14.00
yi-34b-hf	86.00	76.00	84.80	54.80	67.81	24.80	73.60	66.00	65.60
deepseek-7b-base-hf	27.60	42.00	64.40	31.20	40.41	33.60	52.25	46.00	13.20
deepseek-67b-base-hf	95.60	75.60	86.40	86.40	76.71	39.20	76.40	77.20	82.00

model	tracking_shuffled_objects_five_objects	logical_deduction_three_objects	hyperbaton	logical_deduction_five_objects	logical_deduction_seven_objects	movie_recommendation	salient_translation_error_detection	reasoning_about_colored_objects	multistep_arithmetic_two
llama-7b-turbomind	18.40	42.80	58.00	23.20	13.20	40.00	16.40	30.40	0.00
llama-13b-turbomind	16.00	48.80	53.60	30.40	16.40	61.60	11.20	44.80	0.80
llama-30b-turbomind	22.40	66.40	73.20	43.60	31.60	84.40	43.60	57.60	2.80
llama-65b-turbomind	41.60	79.20	74.40	48.40	39.20	91.20	40.40	67.20	20.00
llama-2-7b-turbomind	17.20	54.80	51.60	32.80	23.60	74.40	19.60	45.60	1.20
llama-2-13b-turbomind	23.20	63.60	52.40	46.00	42.00	68.00	21.60	62.00	2.00
llama-2-70b-turbomind	72.40	86.40	84.40	55.20	43.20	95.60	50.80	76.80	20.80
llama-3-8b-turbomind	40.80	76.40	93.20	45.20	36.80	88.80	53.60	72.80	30.80
llama-3-70b-turbomind	99.20	94.00	98.00	58.40	42.80	93.60	63.60	88.40	79.20
internlm2-1.8b-turbomind	16.80	47.60	63.60	21.60	12.00	69.20	16.80	45.20	5.60
internlm2-7b-turbomind	51.20	78.80	90.40	52.00	41.20	95.60	58.80	74.40	44.40
internlm2-20b-turbomind	81.20	95.60	83.60	62.40	48.00	94.80	57.60	75.60	72.80
qwen-1.8b-turbomind	14.80	35.60	51.20	22.40	15.20	31.20	12.40	22.00	3.20
qwen-7b-turbomind	20.80	54.80	76.00	37.60	27.60	74.80	41.20	57.60	23.60
qwen-14b-turbomind	35.60	81.20	78.40	45.20	40.80	80.00	44.80	70.40	65.60
qwen-72b-turbomind	66.40	89.20	90.40	60.00	50.80	81.60	56.40	88.00	70.40
qwen1.5-0.5b-hf	20.00	34.80	46.80	18.80	15.60	24.40	15.20	16.00	1.20
qwen1.5-1.8b-hf	18.00	32.80	66.00	18.80	11.20	24.80	13.60	27.60	4.80
qwen1.5-4b-hf	18.40	56.40	56.80	30.00	20.80	40.80	46.80	44.80	41.20
qwen1.5-7b-hf	32.40	58.40	67.20	36.00	28.00	62.80	49.20	60.40	48.00
qwen1.5-14b-hf	7.20	78.40	75.20	41.20	27.60	74.40	46.00	81.60	8.00
qwen1.5-32b-hf	71.60	88.40	97.60	58.80	46.40	68.00	51.60	88.40	66.80
qwen1.5-72b-hf	61.20	88.40	96.00	60.40	49.20	86.40	34.80	86.80	53.60
qwen1.5-moe-a2-7b-hf	22.80	49.20	68.00	28.40	22.40	58.40	40.80	42.00	33.60
mistral-7b-v0.1-hf	30.40	79.60	70.80	54.40	42.80	77.60	47.20	70.00	30.40
mistral-7b-v0.2-hf	32.80	74.00	77.60	48.00	40.40	84.00	49.20	76.00	35.20
mixtral-8x7b-v0.1-hf	66.80	86.00	94.80	50.40	40.40	86.40	53.20	82.80	60.80
mixtral-8x22b-v0.1-hf	87.60	95.20	99.60	70.00	54.00	95.20	58.40	95.20	82.00
yi-6b-hf	17.20	49.20	72.40	34.40	28.00	76.80	32.40	56.80	9.20
yi-34b-hf	67.20	85.60	79.60	49.20	39.60	86.80	56.00	81.20	33.20
deepseek-7b-base-hf	17.60	51.20	72.40	28.80	20.00	78.40	28.80	46.80	1.60
deepseek-67b-base-hf	82.40	90.00	78.80	60.40	44.80	88.80	56.80	86.40	38.00

model	navigate	dyck_languages	word_sorting	sports_understanding	boolean_expressions	object_counting	formal_fallacies	causal_judgement	web_of_lies
llama-7b-turbomind	45.20	1.60	8.40	81.60	66.00	47.20	46.00	40.64	57.20
llama-13b-turbomind	59.20	0.80	14.40	76.40	69.20	46.40	47.20	53.48	66.80
llama-30b-turbomind	64.80	2.40	17.20	93.60	78.40	71.20	43.20	55.61	98.40
llama-65b-turbomind	72.40	6.80	21.60	98.80	81.60	70.00	40.80	55.61	99.60
llama-2-7b-turbomind	54.40	1.20	10.80	88.80	68.40	49.20	48.40	52.41	53.20
llama-2-13b-turbomind	74.40	2.80	18.80	97.60	74.40	52.80	46.40	54.55	96.00
llama-2-70b-turbomind	82.40	13.60	30.40	98.40	81.60	83.20	43.60	63.64	100.00
llama-3-8b-turbomind	90.00	9.20	38.80	95.20	87.60	84.80	51.20	50.27	100.00
llama-3-70b-turbomind	96.80	48.40	48.80	99.60	92.40	99.60	62.40	58.29	100.00
internlm2-1.8b-turbomind	64.40	0.40	3.20	66.40	54.00	50.00	49.20	48.13	46.80
internlm2-7b-turbomind	78.80	2.40	35.20	95.60	85.60	75.60	48.00	63.10	92.00
internlm2-20b-turbomind	88.80	15.60	36.00	96.80	88.80	76.00	50.40	56.68	100.00
qwen-1.8b-turbomind	50.00	0.00	0.80	62.80	29.20	2.40	6.00	12.83	1.60
qwen-7b-turbomind	62.80	1.60	18.00	81.60	75.20	68.80	50.00	63.64	66.80
qwen-14b-turbomind	75.60	1.20	26.80	88.80	80.40	74.40	50.00	53.48	96.80
qwen-72b-turbomind	56.00	14.40	35.20	87.60	91.60	81.60	5.60	31.55	62.40
qwen1.5-0.5b-hf	25.60	0.00	0.40	41.60	51.60	16.80	4.40	1.07	20.00
qwen1.5-1.8b-hf	55.60	0.00	1.60	63.60	55.20	47.60	4.40	28.88	11.20
qwen1.5-4b-hf	61.60	0.40	8.80	0.80	76.00	54.40	0.80	28.34	62.40
qwen1.5-7b-hf	63.60	2.40	20.80	72.40	69.60	26.80	0.00	40.64	0.00
qwen1.5-14b-hf	82.40	1.20	27.60	78.40	87.20	48.00	54.00	24.06	100.00
qwen1.5-32b-hf	86.80	5.60	36.80	90.00	86.40	66.40	35.60	62.57	95.60
qwen1.5-72b-hf	48.40	13.20	34.40	87.60	8.00	67.60	13.60	39.57	99.60
qwen1.5-moe-a2-7b-hf	56.80	2.00	8.80	79.60	73.60	66.80	4.00	53.48	50.40
mistral-7b-v0.1-hf	73.60	4.00	26.40	97.20	82.00	67.60	43.20	48.66	100.00
mistral-7b-v0.2-hf	72.80	4.00	30.40	97.20	81.20	66.80	46.00	52.41	100.00
mixtral-8x7b-v0.1-hf	85.60	18.80	33.60	98.00	90.80	85.20	49.60	55.61	90.80
mixtral-8x22b-v0.1-hf	92.80	51.60	40.00	98.40	91.60	95.60	54.80	56.15	100.00
yi-6b-hf	66.40	1.20	16.00	92.80	59.60	53.20	53.20	52.41	65.20
yi-34b-hf	81.20	18.80	36.40	97.60	85.60	84.00	51.20	59.89	99.60
deepseek-7b-base-hf	59.20	3.20	6.40	92.00	73.20	49.60	50.80	52.41	74.80
deepseek-67b-base-hf	85.20	30.00	33.20	99.60	84.80	82.40	46.80	56.68	99.60

Chat Models

model	bbh
qwen1.5-0.5b-chat-hf	24.12
qwen1.5-1.8b-chat-hf	26.82
qwen1.5-4b-chat-hf	43.15
qwen1.5-7b-chat-hf	38.12
qwen1.5-14b-chat-hf	55.38
qwen1.5-32b-chat-hf	69.28
qwen1.5-72b-chat-hf	72.97
qwen1.5-110b-chat-hf	71.04
internlm2-chat-1.8b-hf	37.69
internlm2-chat-1.8b-sft-hf	37.12
internlm2-chat-7b-hf	57.83
internlm2-chat-7b-sft-hf	57.19
internlm2-chat-20b-hf	68.24
internlm2-chat-20b-sft-hf	69.38
llama-3-8b-instruct-hf	52.85
llama-3-70b-instruct-hf	82.42
llama-3-8b-instruct-lmdeploy	53.54
llama-3-70b-instruct-lmdeploy	82.58
mistral-7b-instruct-v0.1-hf	32.88
mistral-7b-instruct-v0.2-hf	48.84
mixtral-8x7b-instruct-v0.1-hf	59.64

Details

model	temporal_sequences	disambiguation_qa	date_understanding	tracking_shuffled_objects_three_objects	penguins_in_a_table	geometric_shapes	snarks	ruin_names	tracking_shuffled_objects_seven_objects
qwen1.5-0.5b-chat-hf	25.60	42.00	20.00	31.20	15.07	14.40	46.07	24.80	13.20
qwen1.5-1.8b-chat-hf	28.80	36.00	30.40	35.20	19.18	7.60	46.63	24.00	9.60
qwen1.5-4b-chat-hf	8.00	56.00	64.80	28.40	48.63	19.60	60.67	34.00	14.40
qwen1.5-7b-chat-hf	39.60	37.60	62.40	36.80	60.96	30.80	54.49	38.00	20.00
qwen1.5-14b-chat-hf	61.60	63.60	70.00	54.00	74.66	33.60	67.42	61.20	35.60
qwen1.5-32b-chat-hf	94.40	77.60	78.00	66.00	93.84	46.00	82.58	73.60	61.60
qwen1.5-72b-chat-hf	70.40	72.40	84.40	67.20	89.73	52.00	79.21	86.40	68.80
qwen1.5-110b-chat-hf	74.80	71.20	82.80	74.80	89.04	48.00	90.45	87.60	73.60
internlm2-chat-1.8b-hf	35.60	52.40	48.80	29.60	39.73	24.40	51.69	27.20	13.20
internlm2-chat-1.8b-sft-hf	37.20	53.60	44.00	30.00	34.93	22.40	56.74	28.00	12.00
internlm2-chat-7b-hf	72.00	66.40	73.60	65.20	60.27	50.00	62.92	52.40	44.40
internlm2-chat-7b-sft-hf	67.20	66.80	58.00	63.20	48.63	45.60	64.04	59.60	42.80
internlm2-chat-20b-hf	80.40	76.00	77.60	88.80	78.08	36.40	71.91	71.60	77.20
internlm2-chat-20b-sft-hf	80.00	70.80	78.00	87.60	82.88	41.20	76.40	72.80	71.60
llama-3-8b-instruct-hf	70.40	42.80	28.40	81.20	13.01	49.20	44.94	73.20	42.40
llama-3-70b-instruct-hf	100.00	84.00	91.60	95.60	78.08	52.40	87.08	89.60	97.60
llama-3-8b-instruct-lmdeploy	73.20	45.60	34.00	79.60	31.51	48.40	47.75	76.80	47.60
llama-3-70b-instruct-lmdeploy	100.00	84.00	90.00	96.80	83.56	56.00	87.08	89.20	97.20
mistral-7b-instruct-v0.1-hf	32.00	22.40	52.40	35.20	30.82	23.20	38.76	46.00	18.40
mistral-7b-instruct-v0.2-hf	66.00	58.40	50.40	48.40	48.63	37.20	65.73	40.40	29.20
mixtral-8x7b-instruct-v0.1-hf	63.20	68.40	65.20	60.00	78.08	40.40	74.16	64.00	46.00

model	tracking_shuffled_objects_five_objects	logical_deduction_three_objects	hyperbaton	logical_deduction_five_objects	logical_deduction_seven_objects	movie_recommendation	salient_translation_error_detection	reasoning_about_colored_objects	multistep_arithmetic_two
qwen1.5-0.5b-chat-hf	20.40	34.40	51.60	21.20	13.20	26.00	20.80	17.20	1.20
qwen1.5-1.8b-chat-hf	18.00	34.80	48.40	21.20	16.40	34.80	24.00	28.80	4.40
qwen1.5-4b-chat-hf	19.20	56.80	65.20	36.40	35.60	51.60	40.40	55.20	29.20
qwen1.5-7b-chat-hf	31.60	58.80	53.20	35.60	27.20	56.00	44.80	62.00	50.00
qwen1.5-14b-chat-hf	43.20	75.20	52.80	52.40	50.80	76.40	48.80	83.60	65.20
qwen1.5-32b-chat-hf	68.40	84.00	81.20	57.20	46.00	78.80	54.40	86.00	86.00
qwen1.5-72b-chat-hf	76.80	94.40	85.20	62.80	54.00	78.40	63.60	86.40	82.80
qwen1.5-110b-chat-hf	79.20	91.60	88.80	61.20	50.00	82.40	59.60	88.80	78.00
internlm2-chat-1.8b-hf	20.00	48.40	56.00	24.40	26.80	65.20	18.00	39.60	7.60
internlm2-chat-1.8b-sft-hf	18.40	48.00	51.20	20.40	25.20	63.20	22.00	38.80	6.00
internlm2-chat-7b-hf	48.40	75.20	84.80	42.00	36.80	79.60	53.20	65.60	26.40
internlm2-chat-7b-sft-hf	44.00	72.40	85.60	41.60	37.20	82.40	55.60	52.80	32.00
internlm2-chat-20b-hf	88.00	88.80	88.80	52.80	50.40	85.20	56.80	79.60	40.00
internlm2-chat-20b-sft-hf	83.20	90.00	90.40	55.60	48.80	84.40	57.60	79.20	38.40
llama-3-8b-instruct-hf	49.60	85.60	76.00	54.00	29.20	57.60	46.00	44.80	52.00
llama-3-70b-instruct-hf	99.20	96.80	95.20	77.20	65.20	80.00	69.60	94.80	84.00
llama-3-8b-instruct-lmdeploy	57.20	78.00	75.60	36.00	13.20	59.20	53.60	54.80	52.80
llama-3-70b-instruct-lmdeploy	98.80	96.40	96.80	75.20	68.80	79.60	67.60	94.00	84.80
mistral-7b-instruct-v0.1-hf	26.00	46.00	60.00	38.00	24.00	59.20	1.20	6.00	12.40
mistral-7b-instruct-v0.2-hf	39.60	63.60	64.00	44.00	33.20	56.00	42.40	68.40	14.00
mixtral-8x7b-instruct-v0.1-hf	46.40	71.60	88.80	48.00	36.80	60.00	50.00	81.20	59.20

model	navigate	dyck_languages	word_sorting	sports_understanding	boolean_expressions	object_counting	formal_fallacies	causal_judgement	web_of_lies
qwen1.5-0.5b-chat-hf	45.60	0.00	1.20	17.20	50.40	16.40	11.60	42.78	27.60
qwen1.5-1.8b-chat-hf	58.40	0.00	2.00	34.00	44.80	30.40	11.60	24.60	50.00
qwen1.5-4b-chat-hf	64.00	3.20	6.80	80.40	77.60	48.80	41.20	55.61	63.20
qwen1.5-7b-chat-hf	54.40	0.40	8.00	55.60	47.60	31.20	0.00	2.14	30.00
qwen1.5-14b-chat-hf	74.40	6.40	26.40	72.40	76.40	61.60	0.80	25.67	81.20
qwen1.5-32b-chat-hf	90.00	10.40	28.40	82.40	92.80	76.80	32.40	41.71	100.00
qwen1.5-72b-chat-hf	81.20	18.40	37.60	95.20	92.80	76.00	50.40	63.64	100.00
qwen1.5-110b-chat-hf	91.60	18.00	39.60	82.80	80.80	75.20	22.40	35.83	100.00
internlm2-chat-1.8b-hf	63.20	0.00	6.00	58.00	56.80	48.80	54.80	52.94	48.40
internlm2-chat-1.8b-sft-hf	63.20	0.00	5.60	58.00	56.80	50.00	52.40	56.68	47.60
internlm2-chat-7b-hf	73.60	3.60	18.00	55.20	83.60	62.80	50.00	58.29	97.20
internlm2-chat-7b-sft-hf	71.60	4.40	20.00	82.00	84.00	60.00	51.60	52.94	98.00
internlm2-chat-20b-hf	82.40	8.00	36.00	55.60	84.40	78.00	50.40	59.36	100.00
internlm2-chat-20b-sft-hf	81.60	10.40	36.40	89.20	82.40	80.40	48.40	55.61	100.00
llama-3-8b-instruct-hf	82.80	8.80	37.20	94.40	78.80	89.60	45.20	24.06	25.60
llama-3-70b-instruct-hf	95.20	18.80	49.20	98.00	94.00	90.00	73.20	68.98	100.00
llama-3-8b-instruct-lmdeploy	83.60	10.00	40.40	96.00	77.20	89.20	43.60	37.43	3.20
llama-3-70b-instruct-lmdeploy	95.60	22.40	48.80	96.80	91.60	87.20	72.00	69.52	100.00
mistral-7b-instruct-v0.1-hf	70.80	0.80	5.20	68.80	69.60	51.60	3.20	12.30	33.60
mistral-7b-instruct-v0.2-hf	62.40	4.00	15.60	81.20	70.40	50.40	32.00	34.76	98.40
mixtral-8x7b-instruct-v0.1-hf	76.40	12.80	23.20	55.20	85.60	83.60	40.00	43.32	88.80