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

Capability Self-Assessment on MMLU-Pro Science

69.1M-F1

OLMo2-7B

Updated 1d ago

Evaluation Results

Method	Links
OLMo2-7B 2026.05		69.1	10.95	106.5
Qwen3-1.7B 2026.05		67.4	10.12	102.2
OLMo2-7B 2026.05		66.3	7.83	88.3
OLMo2-13B 2026.05		65.7	8.4	99.5
OLMo2-7B 2026.05		65.4	7.08	76.9
Qwen3-4B 2026.05		64.4	8.07	101.8
Qwen3-4B 2026.05		63.6	7.38	87.6
OLMo2-13B 2026.05		63.6	6.99	61.1
Qwen3-8B 2026.05		62.4	6.72	101.5
Qwen3-8B 2026.05		62.3	6.34	94
Average 2026.05		62	7.07	99.8
Qwen3-1.7B 2026.05		61.1	6.39	89.6
Average 2026.05		61.1	5.61	80.8
Qwen3-14B 2026.05		61	5.57	92.5
Average 2026.05		60.8	5.65	83.8
OLMo2-13B 2026.05		60.6	5.7	76.2
Qwen3-14B 2026.05		60.4	5.12	95.2
Qwen3-4B 2026.05		59.8	5.92	86.8
Qwen3-0.6B 2026.05		58.6	3.97	61.8
Qwen3-8B 2026.05		58	4.19	91.5
Qwen3-0.6B 2026.05		57.4	3.63	69.4
Qwen3-14B 2026.05		56.6	5.25	100.4
OLMo2-7B 2026.05		55.1	3.44	100
Qwen3-1.7B 2026.05		54.7	2.75	81.2
OLMo2-13B 2026.05		54.4	6.13	100
Qwen3-8B 2026.05		50.2	10.73	49.1
Qwen3-1.7B 2026.05		49.2	5.3	37.3
Qwen3-0.6B 2026.05		48.7	0.03	86.8
Qwen3-1.7B 2026.05		46.4	3.02	100
Average 2026.05		45.4	3.06	100
Qwen3-8B 2026.05		45	-	100
Qwen3-14B 2026.05		45	-	100
Qwen3-0.6B 2026.05		44.9	0	2
OLMo2-7B 2026.05		44.4	0	0.7
Qwen3-4B 2026.05		42.2	-	100
OLMo2-13B 2026.05		42	0	5
Average 2026.05		40.4	3.25	17.4
Qwen3-4B 2026.05		31.5	4.47	20.8
Qwen3-0.6B 2026.05		29.5	0.33	100
Qwen3-14B 2026.05		20.5	2.25	6.7