AI BenchMark (LiveBench); 為啥世界雞凍

Model	Organization	Global Average	Reasoning Average	Coding Average	Mathematics Average	Data Analysis Average	Language Average	IF Average
o1-2024-12-17	OpenAI	75.67	91.58	69.69	80.32	65.47	65.39	81.55
deepseek-r1	DeepSeek	71.38	83.17	66.74	79.54	69.78	48.53	80.51
gemini-2.0-flash-thinking-exp-01-21	Google	66.89	78.17	53.49	75.69	69.37	42.18	82.47
o1-preview-2024-09-12	OpenAI	65.79	67.42	50.85	65.49	67.69	68.72	74.60
gemini-exp-1206	Google	64.09	57.00	63.41	72.36	63.16	51.29	77.34
gemini-2.0-flash-thinking-exp-1219	Google	61.83	64.58	53.13	69.03	68.11	36.83	79.32
deepseek-v3	DeepSeek	60.45	56.75	61.77	60.54	60.94	47.48	75.25
gemini-2.0-flash-exp	Google	59.26	59.08	54.36	60.39	61.67	38.22	81.86
claude-3-5-sonnet-20241022	Anthropic	59.03	56.67	67.13	52.28	55.03	53.76	69.30
claude-3-5-sonnet-20240620	Anthropic	58.74	57.17	60.85	54.32	58.87	53.21	68.01
o1-mini-2024-09-12	OpenAI	57.76	72.33	48.05	61.99	57.92	40.89	65.40
gemini-exp-1121	Google	57.36	49.92	49.75	63.75	60.29	40.30	80.15
step-2-16k-202411	StepFun	56.02	52.17	47.19	48.77	63.72	44.39	79.88
gpt-4o-2024-08-06	OpenAI	55.33	53.92	51.44	49.54	60.91	47.59	68.58
gpt-4o-2024-05-13	OpenAI	54.41	49.67	50.00	46.98	61.57	50.05	68.21
gemini-1.5-pro-002	Google	54.33	49.08	48.80	59.07	54.97	43.29	70.78
grok-2-1212	xAI	54.30	54.83	46.44	54.88	54.45	45.58	69.63
gemini-1.5-pro-exp-0827	Google	53.29	50.92	41.43	58.50	53.50	46.15	69.26
meta-llama-3.1-405b-instruct-turbo	Meta	52.36	53.25	42.65	41.05	55.85	45.46	75.90
gpt-4o-2024-11-20	OpenAI	52.19	55.75	46.08	42.87	56.15	47.37	64.94
learnlm-1.5-pro-experimental	Google	52.19	43.42	46.87	57.77	54.97	41.98	68.16
chatgpt-4o-latest-0903	OpenAI	51.66	50.50	47.44	42.45	57.93	45.30	66.37
qwen2.5-72b-instruct-turbo	Alibaba	51.44	45.42	57.64	54.29	51.91	34.99	64.39
dracarys2-72b-instruct	AbacusAI	51.05	45.83	56.64	53.98	51.14	33.48	65.22
gpt-4-turbo-2024-04-09	OpenAI	50.40	50.92	49.00	43.02	54.36	44.26	60.85
llama-3.3-70b-instruct-turbo	Meta	50.16	50.75	36.59	42.24	49.49	39.20	82.67
grok-beta	xAI	49.18	37.00	45.15	45.84	54.27	43.16	69.62
claude-3-opus-20240229	Anthropic	49.12	40.58	38.59	43.36	57.89	50.39	63.89
gemini-1.5-flash-002	Google	48.59	47.00	41.87	47.63	48.35	27.92	78.76
mistral-large-2411	Mistral AI	48.43	43.50	47.08	42.55	50.15	39.39	67.93
mistral-large-2407	Mistral AI	48.31	41.67	47.08	44.69	53.16	39.52	63.73
qwen2.5-coder-32b-instruct	Alibaba	46.23	42.08	56.85	46.61	49.87	23.25	58.69
deepseek-v2.5-1210	DeepSeek	45.98	40.17	46.09	51.60	48.45	31.14	58.40
gpt-4-0125-preview	OpenAI	45.71	47.17	41.80	32.05	56.83	39.22	57.19
gemini-1.5-flash-exp-0827	Google	45.21	46.33	40.35	30.60	51.40	29.60	72.97
meta-llama-3.1-70b-instruct-turbo	Meta	44.89	43.00	33.49	34.72	53.75	35.42	68.98
gemini-1.5-pro-001	Google	44.22	37.00	32.31	40.33	55.07	40.36	60.24
amazon.nova-pro-v1:0	Amazon	43.55	32.58	38.15	38.14	48.31	36.96	67.13
claude-3-5-haiku-20241022	Anthropic	43.45	28.08	51.36	35.54	48.45	35.37	61.88
deepseek-r1-distill-qwen-32b	DeepSeek	42.89	52.25	32.85	59.12	45.41	26.82	40.92
phi-4	Microsoft	41.61	47.83	30.67	41.98	45.17	25.61	58.38
gpt-4o-mini-2024-07-18	OpenAI	41.26	32.75	43.15	36.31	49.96	28.61	56.80
qwq-32b-preview	Alibaba	39.90	57.71	37.20	56.21	31.62	21.09	35.59
gemini-1.5-flash-001	Google	39.22	34.25	34.31	32.59	49.87	31.71	52.58
gemma-2-27b-it	Google	38.19	28.08	35.95	26.52	47.87	32.62	58.10
gemini-1.5-flash-8b-exp-0827	Google	36.67	35.00	28.74	28.12	37.32	20.80	70.02
amazon.nova-lite-v1:0	Amazon	36.35	36.67	27.46	36.70	37.23	25.93	54.13
gemini-1.5-flash-8b-exp-0924	Google	36.01	23.75	28.67	31.66	42.28	19.13	70.55
qwen2.5-7b-instruct-turbo	Alibaba	34.90	28.42	38.37	39.49	35.22	15.80	52.11
claude-3-haiku-20240307	Anthropic	33.85	26.33	24.46	23.37	44.47	29.13	55.32
mistral-small-2409	Mistral AI	33.39	29.92	25.74	24.25	42.73	24.49	53.23
mixtral-8x22b-instruct-v0.1	Mistral AI	32.45	26.33	32.03	26.57	35.67	21.81	52.32
command-r-plus-08-2024	Cohere	31.76	24.75	19.14	21.27	38.06	29.73	57.61
amazon.nova-micro-v1:0	Amazon	29.56	25.08	20.18	34.35	33.95	15.78	48.04
gemma-2-9b-it	Google	28.66	15.17	22.46	19.80	36.39	25.53	52.62
mistral-small-2402	Mistral AI	28.36	19.17	21.18	19.92	34.59	18.89	56.40
command-r-08-2024	Cohere	27.31	21.92	17.90	18.36	33.34	16.72	55.62
command-r-plus-04-2024	Cohere	27.11	20.58	19.46	17.99	25.48	19.70	59.47
meta-llama-3.1-8b-instruct-turbo	Meta	25.97	13.33	18.74	18.31	32.82	17.71	54.90
phi-3-small-8k-instruct	Microsoft	24.03	15.92	20.26	17.58	30.29	12.94	47.20
phi-3-mini-128k-instruct	Microsoft	22.36	20.50	15.04	15.72	34.69	9.15	39.08
olmo-2-1124-13b-instruct	AllenAI	22.09	16.33	10.41	13.51	20.60	11.16	60.56
phi-3-mini-4k-instruct	Microsoft	22.08	26.83	15.54	14.96	30.21	8.56	36.36