Share your thoughts, 1 month free Claude Pro on usSee more

General Reasoning on Aggregated Evaluation Suite Coding, Math, Science

20.38Code Average

Granite-3.3

Updated 1mo ago

Evaluation Results

Method	Links
Granite-3.3 2026.03		20.38	52.04	41.76
Granite-3.3 2026.03		20	52.17	35.95
Granite-3.3 2026.03		19.78	53.19	36.16
Granite-3.3 2026.03		17.62	51.33	40.16
Mistral-7B 2026.03		16.71	48.6	31.48
Mistral-7B 2026.03		16.1	47.92	30.77
Mistral-7B 2026.03		15.96	48.28	35.05
Mistral-7B 2026.03		15.58	48.09	35.14
LLaMA-3.1 2026.03		13.2	39.84	29.69
LLaMA-3.1 2026.03		12.51	39.75	28.76
LLaMA-3.1 2026.03		12.32	42.06	26.38
LLaMA-3.1 2026.03		12.08	42.56	25.9
Granite-3.3 2026.03		10.71	44.99	24.91
Granite-3.3 2026.03		10.58	48.75	29.48
Mistral-7B 2026.03		10.19	29.28	18.49
Mistral-7B 2026.03		9.79	41.28	25.05
LLaMA-3.1 2026.03		6.48	37.98	21.33
LLaMA-3.1 2026.03		5.77	36.41	21.07
Granite-3.3 2026.03		2.07	8.95	11.19
Mistral-7B 2026.03		0.07	0.59	9.2
LLaMA-3.1 2026.03		0.04	2.24	7.49