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

Scheduling on FORGE-BENCH

99.3SR

DS-V3.1-Thinking

Updated 22d ago

Evaluation Results

Method	Links
DS-V3.1-Thinking 2026.05		99.3	98.5
DS-V3.1-Thinking 2026.05		99	91.4
gpt-o3 2026.05		99	94.5
Qwen3-235B-Thinking 2026.05		98	97.1
Qwen3-30B-A3B 2026.05		97	97.5
FORGE-7B-NP-MATH 2026.05		96.3	83.4
Qwen3-235B-Thinking 2026.05		95	93
Qwen3-32B 2026.05		94.1	91.4
Qwen3-32B 2026.05		94	93.9
FORGE-7B-NP 2026.05		93.7	79.1
gpt-o3 2026.05		87.4	87.3
Qwen3-235B-Instruct 2026.05		86	80
Qwen3-30B-A3B 2026.05		86	84
Qwen3-8B 2026.05		86	82.6
DS-R1-Qwen-32B 2026.05		85.7	79.7
FORGE-7B-NP 2026.05		85	43.5
gpt-4o-2024-08-06 2026.05		79	59.8
Qwen3-235B-Instruct 2026.05		78.7	74.4
Qwen3-8B 2026.05		78	75.3
FORGE-7B-NP-MATH 2026.05		72	57
QWEN2.5-7B-SFT 2026.05		68	62
DS-R1-Qwen-14B 2026.05		67.3	63.4
QWEN2.5-7B-SFT 2026.05		63	57.2
Qwen2.5-72B 2026.05		59	58.5
DS-R1-Qwen-14B 2026.05		52	51.7
DS-R1-Qwen-32B 2026.05		49	45.1
InternLM3-8b 2026.05		41.3	23.7
Qwen2.5-7B 2026.05		40	19.8
Qwen2.5-32B 2026.05		32	22.4
LLama3.1-8B 2026.05		28.7	11.4
Qwen2.5-72B 2026.05		27	17.4
Qwen2.5-7B 2026.05		26.7	15.2
Qwen2.5-14B 2026.05		23.3	12.7
Qwen2.5-3B 2026.05		23	10.7
Qwen2.5-14B 2026.05		21	15.8
InternLM3-8b 2026.05		20	9.5
Qwen2.5-3B 2026.05		17	5
Qwen2.5-32B 2026.05		15	12.8
gpt-4o-2024-08-06 2026.05		14.7	9.3
DS-R1-Qwen-7B 2026.05		13.7	8.9
LLama3.1-8B 2026.05		9	7.8
DS-R1-Qwen-7B 2026.05		1	0.9