OpenBookQA

knowledge · openbookqa · 81 scores

https://huggingface.co/spaces/openbookqa

rank	variant	root	org	score	conf	context
1	GRIN-MoE	microsoft/GRIN-MoE	microsoft	89.8	medium	OpenBookQA
2	Phi-3-small-8k-instruct	microsoft/Phi-3-small-8k-instruct	microsoft	88.0	medium	OpenBookQA<br>10-shot
3	Phi-3-small-128k-instruct	microsoft/Phi-3-small-128k-instruct	microsoft	87.8	medium	OpenBookQA<br>10-shot
4	Phi-3-medium-4k-instruct	microsoft/Phi-3-medium-4k-instruct	microsoft	87.4	medium	OpenBookQA<br>10-shot
5	Phi-3-medium-128k-instruct	microsoft/Phi-3-medium-128k-instruct	microsoft	87.2	medium	OpenBookQA<br>10-shot
6	Phi-4-mini-instruct	microsoft/Phi-4-mini-instruct	microsoft	79.2	medium	OpenBookQA (10-shot)
7	Phi-4-mini-instruct-GGUF	microsoft/Phi-4-mini-instruct	unsloth	79.2	medium	OpenBookQA (10-shot)
8	Phi-4-mini-instruct-unsloth-bnb-4bit	microsoft/Phi-4-mini-instruct	unsloth	79.2	medium	OpenBookQA (10-shot)
9	Phi-4-mini-instruct-bnb-4bit	microsoft/Phi-4-mini-instruct	unsloth	79.2	medium	OpenBookQA (10-shot)
10	Phi-4-mini-instruct	microsoft/Phi-4-mini-instruct	unsloth	79.2	medium	OpenBookQA (10-shot)
11	Phi-4-mini-instruct-GGUF	microsoft/Phi-4-mini-instruct	Mungert	79.2	medium	OpenBookQA (10-shot)
12	Ming-Lite-Omni-1.5	inclusionAI/Ming-Lite-Omni	inclusionAI	65.93	low	Average(Open-ended QA)
13	Ming-Lite-Omni	inclusionAI/Ling-lite	inclusionAI	61.98	high
14	Mistral-Nemo-Instruct-2407	mistralai/Mistral-Nemo-Base-2407	mistralai	60.6	medium	OpenBookQA (0-shot)
15	Mistral-Nemo-Base-2407	mistralai/Mistral-Nemo-Base-2407	mistralai	60.6	medium	OpenBookQA (0-shot)
16	Mistral-Nemo-Instruct-FP8-2407	mistralai/Mistral-Nemo-Base-2407	mistralai	60.6	medium	OpenBookQA (0-shot)
17	OLMo-1B-0724-hf	allenai/OLMo-1B-0724-hf	allenai	51.2	medium
18	OLMo-7B-0424-hf	allenai/OLMo-7B-0424-hf	allenai	51.2	medium
19	OLMo-7B-0724-hf	allenai/OLMo-7B-0724-hf	allenai	51.2	medium
20	OLMo-7B-0424	allenai/OLMo-7B-0424	allenai	51.2	medium
21	NVIDIA-Nemotron-3-Super-120B-A12B-Base-BF16	nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-Base-BF16	nvidia	50.2	medium	OpenBookQA
22	OLMo-1B-hf	allenai/OLMo-1B-hf	allenai	49.8	medium
23	OLMo-7B	allenai/OLMo-7B	allenai	49.8	medium
24	OLMo-7B-hf	allenai/OLMo-7B-hf	allenai	49.8	medium
25	OLMo-1B	allenai/OLMo-1B	allenai	49.8	medium
26	OLMo-7B-Twin-2T-hf	allenai/OLMo-7B-Twin-2T-hf	allenai	49.8	medium
27	bagel-dpo-7B-v0.1-GGUF	jondurbin/bagel-dpo-7b-v0.1	TheBloke	49.8	low
28	OLMo-7B-Twin-2T	allenai/OLMo-7B-Twin-2T	allenai	49.8	medium
29	NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16	nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16	nvidia	48.6	medium	OpenBookQA
30	gemma-1.1-2b-it	google/gemma-1.1-2b-it	google	47.8	medium	[OpenBookQA](https://arxiv.org/abs/1809.02789)
31	gemma-2b	google/gemma-2b-it-pytorch	google	47.8	medium	[OpenBookQA](https://arxiv.org/abs/1809.02789)
32	gemma-2b-it	google/gemma-2b-it-pytorch	google	47.8	medium	[OpenBookQA](https://arxiv.org/abs/1809.02789)
33	gemma-7b	google/gemma-7b-it-quant-pytorch	google	47.8	medium	[OpenBookQA](https://arxiv.org/abs/1809.02789)
34	gemma-7b-it	google/gemma-7b	google	47.8	medium	[OpenBookQA](https://arxiv.org/abs/1809.02789)
35	gemma-1.1-7b-it	google/gemma-1.1-7b-it	google	47.8	medium	[OpenBookQA](https://arxiv.org/abs/1809.02789)
36	gemma-2b-AWQ	google/gemma-2b-it-pytorch	google	47.8	medium	[OpenBookQA](https://arxiv.org/abs/1809.02789)
37	gemma-7b	google/gemma-7b-it-quant-pytorch	alpindale	47.8	medium	[OpenBookQA](https://arxiv.org/abs/1809.02789)
38	gemma-2b	google/gemma-2b-it-pytorch	alpindale	47.8	medium	[OpenBookQA](https://arxiv.org/abs/1809.02789)
39	gemma-7b-AWQ	google/gemma-7b-it-quant-pytorch	google	47.8	medium	[OpenBookQA](https://arxiv.org/abs/1809.02789)
40	gemma-7b-it	google/gemma-7b-it-quant-pytorch	alpindale	47.8	medium	[OpenBookQA](https://arxiv.org/abs/1809.02789)
41	gemma-7b-GGUF	google/gemma-7b-it-quant-pytorch	google	47.8	medium	[OpenBookQA](https://arxiv.org/abs/1809.02789)
42	NVIDIA-Nemotron-Nano-9B-v2-Base	nvidia/NVIDIA-Nemotron-Nano-9B-v2-Base	nvidia	46.0	medium	OpenBookQA
43	NVIDIA-Nemotron-Nano-12B-v2-Base	nvidia/NVIDIA-Nemotron-Nano-12B-v2-Base	nvidia	46.0	medium	OpenBookQA
44	NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16	nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16	nvidia	44.8	medium	OpenBookQA (0-shot, acc_norm)
45	SmolLM2-1.7B-Instruct-GGUF	HuggingFaceTB/SmolLM2-1.7B	Mungert	42.2	medium	OpenBookQA
46	Nous-Hermes-Llama2-70B-GGUF	NousResearch/Nous-Hermes-Llama2-70b	TheBloke	38.8	medium
47	Beyonder-4x7B-v2-GGUF	mlabonne/Beyonder-4x7B-v2	TheBloke	37.8	medium
48	Beyonder-4x7B-v2	mlabonne/Marcoro14-7B-slerp	mlabonne	37.8	medium
49	SmolLM2-360M-Instruct-GGUF	HuggingFaceTB/SmolLM2-360M	Mungert	37.4	medium	OpenBookQA
50	Marcoro14-7B-slerp	AIDC-ai-business/Marcoroni-7B-v3	mlabonne	36.4	medium
51	Nous-Hermes-13B-GGUF	NousResearch/Nous-Hermes-13b	TheBloke	35.6	medium
52	Tulpar-7B-v0-GGUF	HyperbeeAI/Tulpar-7b-v0	TheBloke	35.6	medium
53	Redmond-Puffin-13B-GGUF	NousResearch/Redmond-Puffin-13B	TheBloke	35.6	medium
54	Nous-Hermes-13B-SuperHOT-8K-fp16	—	TheBloke	35.6	medium
55	Redmond-Puffin-13B-GPTQ	NousResearch/Redmond-Puffin-13B	TheBloke	35.6	medium
56	Nous-Hermes-13B-SuperHOT-8K-GPTQ	—	TheBloke	35.6	medium
57	Nous-Hermes-2-Yi-34B-GGUF	NousResearch/Nous-Hermes-2-Yi-34B	TheBloke	35.2	medium
58	Nous-Hermes-2-Yi-34B-AWQ	NousResearch/Nous-Hermes-2-Yi-34B	TheBloke	35.2	medium
59	laser-dolphin-mixtral-2x7b-dpo-GGUF	macadeliccc/laser-dolphin-mixtral-2x7b-dpo	TheBloke	35.0	medium
60	bitnet-b1.58-2B-4T-gguf	microsoft/bitnet-b1.58-2B-4T-bf16	microsoft	34.8	medium	OpenbookQA
61	bitnet-b1.58-2B-4T	microsoft/bitnet-b1.58-2B-4T	microsoft	34.8	medium	OpenbookQA
62	bitnet-b1.58-2B-4T-bf16	microsoft/bitnet-b1.58-2B-4T-bf16	microsoft	34.8	medium	OpenbookQA
63	OpenHermes-2-Mistral-7B-GGUF	teknium/OpenHermes-2-Mistral-7B	TheBloke	34.8	medium
64	dolly-v2-7b-olive-optimized	microsoft/dolly-v2-7b-olive-optimized	microsoft	34.8	low
65	OpenHermes-2-Mistral-7B-AWQ	teknium/OpenHermes-2-Mistral-7B	TheBloke	34.8	medium
66	OpenHermes-2.5-Mistral-7B-AWQ	teknium/OpenHermes-2.5-Mistral-7B	TheBloke	34.6	medium
67	OpenHermes-2.5-Mistral-7B-GGUF	teknium/OpenHermes-2.5-Mistral-7B	TheBloke	34.6	medium
68	OpenHermes-2.5-Mistral-7B-16k-GGUF	NurtureAI/OpenHermes-2.5-Mistral-7B-16k	TheBloke	34.6	medium
69	OpenHermes-2.5-Mistral-7B-GPTQ	teknium/OpenHermes-2.5-Mistral-7B	TheBloke	34.6	medium
70	SmolLM2-135M-Instruct-GGUF	HuggingFaceTB/SmolLM2-135M	Mungert	34.6	medium	OpenBookQA
71	Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF	NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO	TheBloke	34.4	medium
72	DPOpenHermes-7B-GGUF	openaccess-ai-collective/DPOpenHermes-7B	TheBloke	34.4	medium
73	NeuralHermes-2.5-Mistral-7B-laser	teknium/OpenHermes-2.5-Mistral-7B	mlabonne	34.4	medium
74	Nous-Hermes-2-Mixtral-8x7B-DPO-GPTQ	NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO	TheBloke	34.4	medium
75	Nous-Hermes-2-SOLAR-10.7B-GGUF	NousResearch/Nous-Hermes-2-SOLAR-10.7B	TheBloke	34.2	medium
76	minotaur-13B-fixed-GGUF	openaccess-ai-collective/minotaur-13b-fixed	TheBloke	34.2	medium
77	Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF	NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT	TheBloke	34.0	medium
78	CollectiveCognition-v1-Mistral-7B-GGUF	teknium/CollectiveCognition-v1-Mistral-7B	TheBloke	33.8	medium
79	Llama2-7b-WhoIsHarryPotter	microsoft/Llama2-7b-WhoIsHarryPotter	microsoft	33.8	low
80	CollectiveCognition-v1.1-Mistral-7B-GGUF	teknium/CollectiveCognition-v1.1-Mistral-7B	TheBloke	32.4	medium
81	Redmond-Hermes-Coder-GPTQ	—	TheBloke	19.6	medium