RANKINGS

Open LLM Leaderboard — 4,637 models ranked

Showing 1–20 of 4,637

#	Model
1	kimi-k2.5/kimi-k2.5	77.3%	—	87.6%	—	—	—	—
2	kimi-k2-thinking-0905/kimi-k2-thinking-0905	73.4%	—	84.5%	—	—	—	—
3	qwen3.5-397b-a17b/qwen3.5-397b-a17b	70.2%	—	88.4%	—	—	—	—
4	glm-4.7/glm-4.7	70.0%	—	85.7%	—	—	—	—
5	longcat-flash-thinking-2601/longcat-flash-thinking-2601	66.4%	—	80.5%	—	—	—	—
6	mimo-v2-flash/mimo-v2-flash	66.3%	—	83.7%	—	—	—	—
7	deepseek-reasoner/deepseek-reasoner	65.0%	—	82.4%	—	—	—	—
8	minimax-m2.1/minimax-m2.1	62.6%	—	81.0%	—	—	—	—
9	glm-4.6/glm-4.6	61.0%	—	81.0%	—	—	—	—
10	deepseek-v3.2-exp/deepseek-v3.2-exp	59.4%	—	79.9%	—	—	—	—
11	glm-4.7-flash/glm-4.7-flash	56.6%	—	75.2%	—	—	—	—
12	minimax-m2/minimax-m2	56.4%	—	78.0%	—	—	—	—
13	MaziyarPanahi/calme-3.2-instruct-78bQwen2ForCausalLM · bfloat16	52.1%	62.6%	20.4%	80.6%	40.3%	70.0%	38.5%
14	MaziyarPanahi/calme-3.1-instruct-78bQwen2ForCausalLM · bfloat16	51.3%	62.4%	19.5%	81.4%	39.3%	68.7%	36.5%
15	dfurman/CalmeRys-78B-Orpo-v0.1Qwen2ForCausalLM · bfloat16	51.2%	61.9%	20.0%	81.6%	40.6%	66.8%	36.4%
16	MaziyarPanahi/calme-2.4-rys-78bQwen2ForCausalLM · bfloat16	50.8%	62.2%	20.4%	80.1%	40.7%	66.7%	34.6%
17	huihui-ai/Qwen2.5-72B-Instruct-abliteratedQwen2ForCausalLM · bfloat16	48.1%	60.5%	19.4%	85.9%	60.1%	50.4%	12.3%
18	Qwen/Qwen2.5-72B-InstructQwen2ForCausalLM · bfloat16	48.0%	61.9%	16.7%	86.4%	59.8%	51.4%	11.7%
19	MaziyarPanahi/calme-2.1-qwen2.5-72bQwen2ForCausalLM · bfloat16	47.9%	61.7%	15.1%	86.6%	59.1%	51.3%	13.3%
20	newsbang/Homer-v1.0-Qwen2.5-72BQwen2ForCausalLM · bfloat16	47.5%	62.3%	22.1%	76.3%	49.0%	57.2%	17.9%

…