Ran it, or it didn’t happen.

Benchmark open models on your own hardware. Runs count once their event log checks out.

Recent verified runsWhereSpeed

PassedFailedNot supported

Cloud leaderboard

Every model runs on the same pinned machine. 17 models, 70 runs.

#	Model	Pass rate				Speed	Runs
1	Qwen3.5-35B-A3BQ4_K_M	96%	9/9	8/9	9/9	201.4 tok/s	3
2	Qwen3.5-27BQ4_K_M	93%	8/9	9/9	8/9	35.5 tok/s	3
3	Qwen3-30B-A3B-Instruct-2507Q4_K_M	92%	11/12	10/12	12/12	187.6 tok/s	4
4	GLM-4.7-FlashQ4_K_M	89%	9/9	6/9	9/9	201.7 tok/s	3
5	Qwen3-Coder-30B-A3B-InstructQ4_K_M	89%	9/9	7/9	8/9	186.4 tok/s	3
6	Qwen3-8BQ4_K_M	89%	9/12	11/12	12/12	120.7 tok/s	4
7	Qwen3-14BQ4_K_M	87%	13/15	11/15	15/15	67.1 tok/s	5
8	gemma-3-27b-itQ4_K_M	86%	17/18	Not supported	14/18	36.2 tok/s	6
9	gpt-oss-20bMXFP4	85%	9/9	9/9	5/9	173.8 tok/s	3
10	gemma-3-4b-itQ4_K_M	83%	11/15	Not supported	14/15	232.7 tok/s	5
11	Qwen3.5-2BQ4_K_M	81%	9/12	9/12	11/12	298.1 tok/s	4
12	Qwen3-4BQ4_K_M	78%	6/9	6/9	9/9	247.9 tok/s	3
13	gemma-3-12b-itQ4_K_M	75%	8/12	Not supported	10/12	80.9 tok/s	4
14	Llama-3.1-8B-InstructQ4_K_M	71%	8/15	9/15	15/15	124.4 tok/s	5
15	Phi-3.5-mini-instructQ4_K_M	64%	9/18	Not supported	14/18	261.3 tok/s	6
16	MiniCPM5-2BQ4_K_M	52%	4/9	3/9	7/9	301.4 tok/s	3
17	Mistral-7B-Instruct-v0.2Q4_K_M	47%	6/18	Not supported	11/18	137.1 tok/s	6

Ranked by checks passed. A task a model can’t do is shown, not counted as a zero.

139 open-weight models in math ranked by LMArena score · updated Oct 28, 2026

#	Model	Score	Votes	Params	License	Downloads	Likes
139	gemma-2b-itgoogle	1009	597	2.5B	Gemma	13.8K	975
138	OLMo-7B-Instructallenai	1018	848	6.9B	Apache 2.0	845	54
137	Qwen1.5-4B-ChatQwen	1026	988	4.0B	Custom	15.9K	53
136	Llama-2-7b-chat-hfmeta-llama	1042	1.7K	6.7B	Llama 2	126.9K	4,949
135	gemma-1.1-2b-itgoogle	1047	1.4K	2.5B	Gemma	6.1K	175
134	SOLAR-10.7B-Instruct-v1.0upstage	1064	604	10.7B	CC BY-NC 4.0	48.9K	660
133	Llama-2-13b-chat-hfmeta-llama	1065	2.2K	13.0B	Llama 2	152.7K	1,138
132	gemma-7b-itgoogle	1066	1.1K	8.5B	Gemma	25.3K	1,263
131	Qwen-14B-ChatQwen	1068	534	14.2B	—	5.2K	381
130	Qwen1.5-7B-ChatQwen	1080	690	7.7B	Tongyi Qianwen	7.1K	192
129	Mistral-7B-Instruct-v0.2mistralai	1085	2.6K	7.2B	Apache 2.0	1.6M	3,279
128	Llama-3.2-1B-Instructmeta-llama	1086	1.2K	1.2B	Llama 3.2	1.5M	1,958
127	Phi-3-mini-128k-instructmicrosoft	1089	2.8K	3.8B	MIT	236.2K	1,713
126	Llama-2-70b-chat-hfmeta-llama	1091	4.7K	69.0B	Llama 2	4.6K	2,211
125	gemma-1.1-7b-itgoogle	1107	3K	8.5B	Gemma	4.3K	276
124	deepseek-llm-67b-chatdeepseek-ai	1108	576	—	Custom	2.7K	222
123	granite-3.0-2b-instructibm-granite	1117	908	2.6B	Apache 2.0	3.2K	48
122	Qwen1.5-14B-ChatQwen	1125	2.2K	14.2B	Tongyi Qianwen	12.1K	118
121	Llama-3.2-3B-Instructmeta-llama	1126	1.1K	3.2B	Llama 3.2	929.3K	2,952
120	gemma-2-2b-itgoogle	1135	6.6K	2.6B	Gemma	129.8K	1,605

Scores: LMArena, CC BY 4.0. Measured on served versions, not local builds. A model with several served variants shows its best.