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

Physical Reasoning on PIQA (Accuracy & Speedup)

91.3Accuracy

Mistral Small 24B Base 2501

Updated 4d ago

Evaluation Results

Method	Links
Mistral Small 24B Base 2501 2026.01		91.3	-	8.2
Mistral Small 24B Base 2501 2026.01		91.3	-	8.1
Llama 3.1 8B 2026.01		91	-	9.7
Llama 3.1 8B 2026.01		90.9	-	9.7
Mistral Nemo Base 2407 2026.01		89.5	-	7.3
Mistral Nemo Base 2407 2026.01		89.2	-	7
Mistral 7B v0.3 2026.01		88.8	-	7.6
Mistral Small 24B Inst 2501 2026.01		88.8	-	3.8
Mistral 7B v0.3 2026.01		88.6	-	7.4
Llama 3.2 1B 2026.01		88.4	-	11.7
Llama 3.2 1B 2026.01		88.4	-	11.7
Mistral Small 24B Inst 2501 2026.01		88.3	-	3.3
Llama 3.2 3B 2026.01		86.6	-	8.8
Llama 3.2 3B 2026.01		86.4	-	8.6
Mistral Nemo Inst 2407 2026.01		86	-	4.3
Mistral Nemo Inst 2407 2026.01		85.4	-	3.7
Mistral 7B Inst v0.3 2026.01		83.4	-	0.7
Llama 3.1 8B Inst 2026.01		82.2	-	2
Llama 3.2 1B Inst 2026.01		82	-	7.8
Mistral 7B Inst v0.3 2026.01		81.5	-	-1.1
Llama 3.2 1B Inst 2026.01		80.6	-	6.4
Llama 3.1 8B Inst 2026.01		80.1	-	-0.2
Llama 3.2 3B Inst 2026.01		79.3	-	2.5
Llama 3.2 3B Inst 2026.01		74	-	-2.8
Exp-k=2 (7.5, 2.5) 2025.12		73.25	1.11	-
Linear (7.5, 0) 2025.12		73.14	1.14	-
Exp-k=2 (7.5, 0) 2025.12		73.11	1.21	-
Linear (7.5, 2.5) 2025.12		73.09	1.1	-
Cosine (7.5, 2.5) 2025.12		73.08	1.11	-
Cosine (7.5, 0) 2025.12		73.06	1.14	-
Baseline 2025.12		73.02	1	-
Exp-k=16 (7.5, 2.5) 2025.12		72.78	1.55	-
Prophet 2025.12		72.33	1.01	-
Exp-k=16 (7.5, 0) 2025.12		58.81	2.5	-