Our new X account is live! Follow @wizwand_team for updates

Question Answering on OpenBook-QA (Accuracy and Performance Gain)

91.6Accuracy

Mistral Small 24B Inst 2501

Updated 4d ago

Evaluation Results

Method	Links
Mistral Small 24B Inst 2501 2026.01		91.6	-0.2
Mistral Small 24B Inst 2501 2026.01		91.2	-0.6
Mistral Small 24B Base 2501 2026.01		85.6	0.4
Mistral Small 24B Base 2501 2026.01		85.6	0.4
Llama 3.1 8B Inst 2026.01		82.4	1.4
Llama 3.1 8B Inst 2026.01		81.8	0.8
Llama 3.1 8B 2026.01		76.6	1
Llama 3.1 8B 2026.01		76.6	1
Llama 3.2 3B Inst 2026.01		76.4	0.2
Llama 3.2 3B Inst 2026.01		76.2	0
Mistral 7B Inst v0.3 2026.01		74.8	1.2
Mistral 7B Inst v0.3 2026.01		74.2	0.6
Mistral Nemo Base 2407 2026.01		73.4	0.2
Mistral Nemo Base 2407 2026.01		73	-0.2
Mistral Nemo Inst 2407 2026.01		70	4.2
Mistral 7B v0.3 2026.01		68.8	0.6
Mistral 7B v0.3 2026.01		68.4	0.2
Mistral Nemo Inst 2407 2026.01		66.2	0.4
Llama 3.2 3B 2026.01		65.4	0.6
Llama 3.2 3B 2026.01		64.8	0
Llama 3.2 1B Inst 2026.01		59.8	0
Llama 3.2 1B Inst 2026.01		59.6	-0.2
Llama 3.2 1B 2026.01		47.4	3.8
Llama 3.2 1B 2026.01		44	0.4