AlpacaEval

chat · alpacaeval · 136 scores

https://huggingface.co/spaces/alpacaeval

rank	variant	root	org	score	conf	context
1	Starling-LM-7B-alpha-GGUF	berkeley-nest/Starling-LM-7B-alpha	TheBloke	97.7	low
2	Starling-LM-alpha-8x7B-MoE-GGUF	perlthoughts/Starling-LM-alpha-8x7B-MoE	TheBloke	97.7	low
3	Starling-LM-7B-alpha-AWQ	berkeley-nest/Starling-LM-7B-alpha	TheBloke	97.7	low
4	Starling-LM-7B-alpha-GPTQ	berkeley-nest/Starling-LM-7B-alpha	TheBloke	97.7	low
5	Xwin-LM-70B-V0.1-GGUF	Xwin-LM/Xwin-LM-70b-V0.1	TheBloke	95.57	low
6	Xwin-LM-13B-V0.1-GGUF	Xwin-LM/Xwin-LM-13B-V0.1	TheBloke	95.57	low
7	Xwin-LM-13B-v0.2-GGUF	Xwin-LM/Xwin-LM-13B-V0.2	TheBloke	95.57	low
8	Xwin-LM-7B-V0.2-GGUF	Xwin-LM/Xwin-LM-7B-V0.2	TheBloke	95.57	low
9	Xwin-LM-7B-V0.1-GGUF	Xwin-LM/Xwin-LM-7b-V0.1	TheBloke	95.57	low
10	Xwin-LM-13B-V0.1-GPTQ	Xwin-LM/Xwin-LM-13B-V0.1	TheBloke	95.57	low
11	Xwin-LM-70B-V0.1-AWQ	Xwin-LM/Xwin-LM-70b-V0.1	TheBloke	95.57	low
12	openchat_v3.2_super-GGUF	openchat/openchat_v3.2_super	TheBloke	95.3	low
13	OpenChat_v3.2-GPTQ	openchat/openchat_v3.2	TheBloke	95.3	low
14	llama-3-tulu-2-8b	meta-llama/Meta-Llama-3-8B	allenai	94.65	low	GSM8k 8-shot cot \| BBH 3-shot cot
15	llama-3-tulu-2-70b	meta-llama/Meta-Llama-3-70B	allenai	94.65	low	GSM8k 8-shot cot \| BBH 3-shot cot
16	deita-7B-v1.0-sft-GGUF	hkust-nlp/deita-7b-v1.0-sft	TheBloke	90.06	high
17	zephyr-7B-beta-GGUF	HuggingFaceH4/zephyr-7b-beta	TheBloke	87.83	low
18	zephyr-7B-beta-AWQ	HuggingFaceH4/zephyr-7b-beta	TheBloke	87.83	low
19	zephyr-7B-beta-GPTQ	HuggingFaceH4/zephyr-7b-beta	TheBloke	87.83	low
20	stablelm-zephyr-3b-GGUF	stabilityai/stablelm-zephyr-3b	TheBloke	76.0	low
21	tulu-2-7b	meta-llama/Llama-2-7b-hf	allenai	73.9	low
22	tulu-2-13B-GGUF	allenai/tulu-2-13b	TheBloke	73.9	low
23	tulu-2-dpo-7b	meta-llama/Llama-2-7b-hf	allenai	73.9	low
24	tulu-2-dpo-13b	meta-llama/Llama-2-13b-hf	allenai	73.9	low
25	tulu-2-dpo-70b	meta-llama/Llama-2-70b-hf	allenai	73.9	low
26	tulu-2-dpo-13B-GGUF	allenai/tulu-2-dpo-13b	TheBloke	73.9	low
27	tulu-2-dpo-70B-GGUF	allenai/tulu-2-dpo-70b	TheBloke	73.9	low
28	tulu-2-7B-GGUF	allenai/tulu-2-7b	TheBloke	73.9	low
29	tulu-2-13b	meta-llama/Llama-2-13b-hf	allenai	73.9	low
30	tulu-2-70B-GGUF	allenai/tulu-2-70b	TheBloke	73.9	low
31	tulu-2-dpo-7B-GGUF	allenai/tulu-2-dpo-7b	TheBloke	73.9	low
32	tulu-2-dpo-13B-AWQ	allenai/tulu-2-dpo-13b	TheBloke	73.9	low
33	claude2-alpaca-13B-GGUF	umd-zhou-lab/claude2-alpaca-13B	TheBloke	71.37	low
34	claude2-alpaca-7B-GGUF	umd-zhou-lab/claude2-alpaca-7B	TheBloke	71.37	low
35	OLMo-7B-0724-Instruct-hf	allenai/OLMo-7B-0724-Instruct-hf	allenai	70.9	low
36	OLMo-7B-0724-SFT-hf	allenai/OLMo-7B-0724-SFT-hf	allenai	70.9	low
37	OLMo-7B-0424-Instruct-hf	allenai/OLMo-7B-0424-Instruct-hf	allenai	70.4	low
38	DeepSeek-V3	deepseek-ai/DeepSeek-V2	deepseek-ai	70.0	high
39	DeepSeek-V3-Base	deepseek-ai/DeepSeek-V2	deepseek-ai	70.0	high
40	DeepSeek-V3	deepseek-ai/DeepSeek-V3	unsloth	70.0	high
41	DeepSeek-V3-bf16	deepseek-ai/DeepSeek-V3	unsloth	70.0	high
42	DeepSeek-V3-GGUF	deepseek-ai/DeepSeek-V3	unsloth	70.0	high
43	Olmo-3-32B-Think	allenai/Olmo-3-32B-Think-DPO	allenai	69.1	medium	AlpacaEval 2 LC
44	Olmo-3.1-32B-Think	allenai/Olmo-3-32B-Think-DPO	allenai	69.1	medium	AlpacaEval 2 LC
45	Olmo-3-32B-Think-SFT	allenai/Olmo-3-1125-32B	allenai	69.1	medium	AlpacaEval 2 LC
46	Olmo-3.1-32B-Think-GGUF	allenai/Olmo-3.1-32B-Think	unsloth	69.1	medium	AlpacaEval 2 LC
47	Olmo-3-32B-Think-GGUF	allenai/Olmo-3-32B-Think	unsloth	69.1	medium	AlpacaEval 2 LC
48	Olmo-3-32B-Think-DPO	allenai/Olmo-3-32B-Think-SFT	allenai	69.1	medium	AlpacaEval 2 LC
49	Olmo-3-32B-Think-unsloth-bnb-4bit	allenai/Olmo-3-32B-Think	unsloth	69.1	medium	AlpacaEval 2 LC
50	Falcon-H1-34B-Instruct	tiiuae/Falcon-H1-34B-Base	tiiuae	48.32	medium	Alpaca-Eval
51	Falcon-H1-34B-Instruct-GGUF	tiiuae/Falcon-H1-34B-Instruct	tiiuae	48.32	medium	Alpaca-Eval
52	Falcon-H1-34B-Instruct-GGUF	tiiuae/Falcon-H1-34B-Instruct	unsloth	48.32	medium	Alpaca-Eval
53	Falcon-H1-34B-Instruct-GPTQ-Int4	tiiuae/Falcon-H1-34B-Instruct	tiiuae	48.32	medium	Alpaca-Eval
54	OLMo-7B-Instruct-hf	allenai/OLMo-7B-Instruct-hf	allenai	46.8	low
55	OLMo-7B-Instruct	allenai/OLMo-7B-Instruct	allenai	46.8	low
56	OLMo-7B-SFT-hf	allenai/OLMo-7B-SFT-hf	allenai	46.8	low
57	OLMo-7B-SFT	allenai/OLMo-7B-SFT	allenai	46.8	low
58	DeepSeek-V2.5	deepseek-ai/DeepSeek-V2.5	deepseek-ai	46.6	medium	AlpacaEval 2.0
59	rocket-3B-GGUF	pansophic/rocket-3B	TheBloke	45.71	low
60	OLMo-2-1124-7B-Instruct	allenai/OLMo-2-1124-7B-DPO	allenai	43.7	low
61	OLMo-2-1124-13B-Instruct	allenai/OLMo-2-1124-13B-Instruct-RLVR2	allenai	43.7	low
62	OLMo-2-1124-7B-SFT	allenai/OLMo2-7B-1124	allenai	43.7	low
63	OLMo-2-1124-7B-DPO	allenai/OLMo-2-1124-7B-SFT	allenai	43.7	low
64	OLMo-2-1124-13B-SFT	allenai/OLMo2-13B-1124	allenai	43.7	low
65	OLMo-2-1124-13B-DPO	allenai/OLMo-2-1124-13B-SFT	allenai	43.7	low
66	OLMo-2-1124-7B-Instruct-preview	allenai/OLMo-2-1124-7B-DPO	allenai	43.7	low
67	OLMo-2-1124-7B-RM	allenai/OLMo-2-1124-7B-SFT	allenai	43.7	low
68	OLMo-2-1124-7B-RM-Preview	allenai/OLMo-2-1124-7B-SFT	allenai	43.7	low
69	OLMo-2-1124-13B-RM	allenai/OLMo-2-1124-13B-SFT	allenai	43.7	low
70	OLMo-2-1124-13B-Instruct-preview	allenai/OLMo-2-1124-13B-DPO	allenai	43.7	low
71	OLMo-2-1124-7B-SFT-Preview	allenai/OLMo2-7B-1124	allenai	43.7	low
72	OLMo-2-1124-7B-DPO-Preview	allenai/OLMo-2-1124-7B-SFT	allenai	43.7	low
73	Olmo-3.1-32B-Instruct	allenai/Olmo-3.1-32B-Instruct-DPO	allenai	42.2	medium	AlpacaEval 2 LC
74	Olmo-3.1-32B-Instruct-SFT	allenai/Olmo-3-1125-32B	allenai	42.2	medium	AlpacaEval 2 LC
75	Olmo-3.1-32B-Instruct-DPO	allenai/Olmo-3.1-32B-Instruct-SFT	allenai	42.2	medium	AlpacaEval 2 LC
76	Olmo-3.1-32B-Instruct-GGUF	allenai/Olmo-3.1-32B-Instruct	unsloth	42.2	medium	AlpacaEval 2 LC
77	Olmo-3.1-32B-Instruct	allenai/Olmo-3.1-32B-Instruct	unsloth	42.2	medium	AlpacaEval 2 LC
78	Falcon-H1-7B-Instruct	tiiuae/Falcon-H1-7B-Base	tiiuae	40.23	medium	Alpaca-Eval
79	Falcon-H1-7B-Instruct-GPTQ-Int4	tiiuae/Falcon-H1-7B-Instruct	tiiuae	40.23	medium	Alpaca-Eval
80	Falcon-H1-7B-Instruct-GGUF	tiiuae/Falcon-H1-7B-Instruct	tiiuae	40.23	medium	Alpaca-Eval
81	Falcon-H1-7B-Instruct-GGUF	tiiuae/Falcon-H1-7B-Instruct	unsloth	40.23	medium	Alpaca-Eval
82	OLMo-2-0325-32B-Instruct	allenai/OLMo-2-0325-32B-DPO	allenai	38.7	low
83	OLMo-2-0325-32B-Instruct-GGUF	allenai/OLMo-2-0325-32B-Instruct	unsloth	38.7	low
84	OLMo-2-0325-32B-SFT	allenai/OLMo-2-0325-32B	allenai	38.7	low
85	OLMo-2-0325-32B-DPO	allenai/OLMo-2-0325-32B-SFT	allenai	38.7	low
86	OLMo-2-0325-32B-Instruct	allenai/OLMo-2-0325-32B-Instruct	unsloth	38.7	low
87	Falcon-H1-3B-Instruct	tiiuae/Falcon-H1-3B-Base	tiiuae	31.09	medium	Alpaca-Eval
88	Falcon-H1-3B-Instruct-GGUF	tiiuae/Falcon-H1-3B-Base	tiiuae	31.09	medium	Alpaca-Eval
89	Falcon-H1-3B-Instruct-GGUF	tiiuae/Falcon-H1-3B-Instruct	unsloth	31.09	medium	Alpaca-Eval
90	Falcon-H1-1.5B-Instruct	tiiuae/Falcon-H1-1.5B-Base	tiiuae	28.18	medium	Alpaca-Eval
91	Falcon-H1-1.5B-Instruct-GGUF	tiiuae/Falcon-H1-1.5B-Instruct	tiiuae	28.18	medium	Alpaca-Eval
92	Falcon-H1-1.5B-Instruct-GGUF	tiiuae/Falcon-H1-1.5B-Instruct	unsloth	28.18	medium	Alpaca-Eval
93	Falcon-H1-1.5B-Instruct-GPTQ-Int4	tiiuae/Falcon-H1-1.5B-Instruct	tiiuae	28.18	medium	Alpaca-Eval
94	Falcon-H1-1.5B-Instruct-GPTQ-Int8	tiiuae/Falcon-H1-1.5B-Instruct	tiiuae	28.18	medium	Alpaca-Eval
95	Falcon-H1-1.5B-Deep-Instruct	tiiuae/Falcon-H1-1.5B-Deep-Base	tiiuae	27.12	medium	Alpaca-Eval
96	Falcon-H1-1.5B-Deep-Instruct-GGUF	tiiuae/Falcon-H1-1.5B-Deep-Instruct	tiiuae	27.12	medium	Alpaca-Eval
97	Falcon-H1-1.5B-Deep-Instruct-GGUF	tiiuae/Falcon-H1-1.5B-Deep-Instruct	unsloth	27.12	medium	Alpaca-Eval
98	Falcon-H1-1.5B-Deep-Instruct	tiiuae/Falcon-H1-1.5B-Deep-Instruct	unsloth	27.12	medium	Alpaca-Eval
99	Falcon-H1-1.5B-Deep-Instruct-GPTQ-Int4	tiiuae/Falcon-H1-1.5B-Deep-Instruct	tiiuae	27.12	medium	Alpaca-Eval
100	OLMoE-1B-7B-0125-Instruct	allenai/OLMoE-1B-7B-0125-DPO	allenai	17.99	medium	AlpacaEval
101	OLMoE-1B-7B-0125-DPO	allenai/OLMoE-1B-7B-0125-SFT	allenai	17.99	medium	AlpacaEval
102	OLMoE-1B-7B-0125-SFT	allenai/OLMoE-1B-7B-0125	allenai	17.99	medium	AlpacaEval
103	Llama-3.1-Tulu-3-8B-SFT	meta-llama/Llama-3.1-8B	allenai	12.4	medium	AlpacaEval 2 (LC % win)
104	Llama-3.1-Tulu-3-8B	allenai/Llama-3.1-Tulu-3-8B-DPO	allenai	12.4	medium	AlpacaEval 2 (LC % win)
105	Llama-3.1-Tulu-3-8B-DPO	allenai/Llama-3.1-Tulu-3-8B-SFT	allenai	12.4	medium	AlpacaEval 2 (LC % win)
106	Llama-3.1-Tulu-3-8B-RM	allenai/Llama-3.1-Tulu-3-8B-SFT	allenai	12.4	medium	AlpacaEval 2 (LC % win)
107	Llama-3.1-Tulu-3.1-8B	allenai/Llama-3.1-Tulu-3-8B-DPO	allenai	12.4	medium	AlpacaEval 2 (LC % win)
108	Llama-3.1-Tulu-3-70B	allenai/Llama-3.1-Tulu-3-70B-DPO	allenai	12.4	medium	AlpacaEval 2 (LC % win)
109	Llama-3.1-Tulu-3-70B-SFT	meta-llama/Llama-3.1-70B	allenai	12.4	medium	AlpacaEval 2 (LC % win)
110	Llama-3.1-Tulu-3-405B	allenai/Llama-3.1-Tulu-3-405B-DPO	allenai	12.4	medium	AlpacaEval 2 (LC % win)
111	Llama-3.1-Tulu-3-70B-DPO	allenai/Llama-3.1-Tulu-3-70B-SFT	allenai	12.4	medium	AlpacaEval 2 (LC % win)
112	Llama-3.1-Tulu-3-8B-GGUF	allenai/Llama-3.1-Tulu-3-8B	unsloth	12.4	medium	AlpacaEval 2 (LC % win)
113	Llama-3.1-Tulu-3-405B-SFT	meta-llama/Llama-3.1-405B	allenai	12.4	medium	AlpacaEval 2 (LC % win)
114	Llama-3.1-Tulu-3-70B-GGUF	allenai/Llama-3.1-Tulu-3-70B	unsloth	12.4	medium	AlpacaEval 2 (LC % win)
115	Llama-3.1-Tulu-3-405B-DPO	allenai/Llama-3.1-Tulu-3-405B-SFT	allenai	12.4	medium	AlpacaEval 2 (LC % win)
116	Falcon-H1-0.5B-Instruct	tiiuae/Falcon-H1-0.5B-Base	tiiuae	10.79	medium	Alpaca-Eval
117	Falcon-H1-0.5B-Instruct-GGUF	tiiuae/Falcon-H1-0.5B-Base	tiiuae	10.79	medium	Alpaca-Eval
118	Falcon-H1-0.5B-Instruct-GGUF	tiiuae/Falcon-H1-0.5B-Instruct	unsloth	10.79	medium	Alpaca-Eval
119	Ming-Lite-Omni-1.5	inclusionAI/Ming-Lite-Omni	inclusionAI	4.65	low	Average(Open-ended QA)
120	LFM2.5-Audio-1.5B	LiquidAI/LFM2-1.2B	LiquidAI	3.76	high
121	LFM2.5-Audio-1.5B-GGUF	LiquidAI/LFM2-1.2B	Mungert	3.76	high
122	LFM2-Audio-1.5B	LiquidAI/LFM2-1.2B	LiquidAI	3.71	high
123	Ming-Lite-Omni	inclusionAI/Ling-lite	inclusionAI	3.69	low
124	OLMo-2-0425-1B-Instruct	allenai/OLMo-2-0425-1B-RLVR1	allenai	2.4	low
125	OLMo-2-0425-1B-SFT	allenai/OLMo-2-0425-1B	allenai	2.4	low
126	OLMo-2-0425-1B-DPO	allenai/OLMo-2-0425-1B-SFT	allenai	2.4	low
127	OLMo-2-0425-1B-Instruct-GGUF	allenai/OLMo-2-0425-1B-Instruct	unsloth	2.4	low
128	OLMo-2-0425-1B-Instruct	allenai/OLMo-2-0425-1B-Instruct	unsloth	2.4	low
129	OLMo-2-0425-1B-RLVR1	allenai/OLMo-2-0425-1B-DPO	allenai	2.4	low
130	internlm3-8b-instruct	internlm/internlm3-8b-instruct	internlm	2.0	medium
131	DeepSeek-V2-Chat	deepseek-ai/DeepSeek-V2-Chat	deepseek-ai	2.0	medium
132	DeepSeek-V2	deepseek-ai/DeepSeek-V2	deepseek-ai	2.0	medium
133	DeepSeek-V2.5	deepseek-ai/DeepSeek-V2.5	deepseek-ai	2.0	medium
134	Nemotron-4-340B-Instruct	nvidia/Nemotron-4-340B-Instruct	nvidia	2.0	medium
135	internlm3-8b-instruct-awq	internlm/internlm3-8b-instruct	internlm	2.0	medium
136	OLMoE-1B-7B-0924-Instruct	allenai/OLMoE-1B-7B-0924-SFT	allenai	1.0	medium