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.

144 open-weight models in non-english ranked by LMArena score · updated Oct 28, 2026

#	Model	Score	Votes	Params	License	Downloads	Likes
144	gemma-2b-itgoogle	958	1.8K	2.5B	Gemma	13.8K	975
143	Llama-2-7b-chat-hfmeta-llama	973	3.9K	6.7B	Llama 2	126.9K	4,949
142	Llama-3.2-1B-Instructmeta-llama	973	3.7K	1.2B	Llama 3.2	1.5M	1,958
141	OLMo-7B-Instructallenai	977	2.3K	6.9B	Apache 2.0	845	54
140	Qwen1.5-4B-ChatQwen	979	2.8K	4.0B	Custom	15.9K	53
139	gemma-1.1-2b-itgoogle	988	4.9K	2.5B	Gemma	6.1K	175
138	gemma-7b-itgoogle	998	3.2K	8.5B	Gemma	25.3K	1,263
137	Phi-3-mini-128k-instructmicrosoft	1000	8.1K	3.8B	MIT	236.2K	1,713
136	Mistral-7B-Instruct-v0.2mistralai	1012	6.7K	7.2B	Apache 2.0	1.6M	3,279
135	SOLAR-10.7B-Instruct-v1.0upstage	1014	878	10.7B	CC BY-NC 4.0	48.9K	660
134	Llama-3.2-3B-Instructmeta-llama	1019	3.8K	3.2B	Llama 3.2	929.3K	2,952
133	Phi-3-mini-4k-instructmicrosoft	1021	9.8K	3.8B	MIT	324.8K	1,489
132	Llama-2-13b-chat-hfmeta-llama	1024	5.3K	13.0B	Llama 2	152.7K	1,138
131	granite-3.0-2b-instructibm-granite	1032	3.5K	2.6B	Apache 2.0	3.2K	48
130	granite-3.0-8b-instructibm-granite	1037	3.3K	8.2B	Apache 2.0	13.1K	209
129	Qwen-14B-ChatQwen	1041	1.1K	14.2B	—	5.2K	381
128	Llama-2-70b-chat-hfmeta-llama	1045	12.4K	69.0B	Llama 2	4.6K	2,211
127	gemma-1.1-7b-itgoogle	1051	11.2K	8.5B	Gemma	4.3K	276
126	Phi-3-small-8k-instructmicrosoft	1058	8.7K	7.4B	MIT	7.1K	182
125	Qwen1.5-7B-ChatQwen	1058	1.5K	7.7B	Tongyi Qianwen	7.1K	192

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