MB / MODELS

Model leaderboard

Ranked by daily token usage across 539 models

Data date 2026-09-11 Snapshot data Last synced 14:58 Back to home

Full leaderboard 539 models · page 3 of 12

#	Model	Context	Daily tokens	Daily requests	Daily change
100	google/gemma-3-27b-it	—	58B	25.4M	0.1%
101	z-ai/glm-5.1-20260406	—	57.9B	4M	6.3%
102	google/gemini-2.5-pro	—	56.3B	5.1M	4.4%
103	nvidia/nemotron-3-ultra-550b-a55b-20260604	—	50.3B	2.4M	43.6%
104	inclusionai/ling-3.0-flash-vl-20260910 free	—	50.2B	867.8K	—
105	nvidia/nemotron-3.5-lightning-20260807	—	48.9B	2.5M	5.9%
106	openai/gpt-5.2-20251211	—	46.9B	5.3M	66.5%
107	openai/gpt-4.1-2025-04-14	—	46.7B	8.6M	28.0%
108	z-ai/glm-4.7-20251222	—	46.6B	3.8M	0.9%
109	qwen/qwen3-30b-a3b-instruct-2507	—	43.6B	18.7M	4.2%
110	z-ai/glm-5-20260211	—	41B	2M	15.6%
111	deepseek/deepseek-chat-v3.1	—	39B	9.1M	8.5%
112	qwen/qwen3.5-397b-a17b-20260216	—	37.9B	2.4M	27.8%
113	nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428 free	—	36.8B	1.8M	1.9%
114	qwen/qwen3.5-9b-20260310	—	35.9B	8.6M	8.7%
115	meta-llama/llama-3.3-70b-instruct	—	33.5B	23.3M	9.9%
116	qwen/qwen3-vl-32b-instruct	—	32.5B	9.1M	83.3%
117	meta-llama/llama-4-scout-17b-16e-instruct	—	31.4B	7.2M	154.3%
118	google/gemini-embedding-2	—	31.1B	18.8M	4.1%
119	minimax/minimax-m2.5-20260211	—	30.9B	1.6M	28.2%
120	x-ai/grok-4.20-20260309	—	30.6B	4.1M	2.6%
121	openai/gpt-5.3-codex-20260224	—	29.1B	615.5K	8.0%
122	deepseek/deepseek-chat-v3-0324	—	27.6B	5.8M	8.7%
123	qwen/qwen3.8-2.4t-a95b-20260812	—	27.3B	786.6K	31.9%
124	qwen/qwen3-coder-next-2025-02-03	—	24.9B	1.1M	14.9%
125	meta/muse-spark-1.2-20260805	—	24.5B	1M	66.6%
126	baai/bge-m3-20251117	—	24.3B	20.3M	17.6%
127	inception/mercury-2.5-20260908	—	24B	2.9M	—
128	perplexity/pplx-embed-v1-0.6B	—	22.4B	9.1M	52.8%
129	thinkingmachines/inkling-20260715	—	22.2B	662.4K	54.2%
130	amazon/nova-micro-v1	—	22B	9.7M	9.9%
131	qwen/qwen3-vl-235b-a22b-instruct	—	21.9B	5.3M	14.5%
132	mistralai/mistral-small-2603	—	21.8B	6M	18.3%
133	qwen/qwen3-32b-04-28	—	21.8B	11.1M	39.4%
134	openai/gpt-5.1-20251113	—	21.4B	3.1M	1.3%
135	deepseek/deepseek-chat-v3	—	20.9B	8M	4.6%
136	mistralai/mistral-small-3.2-24b-instruct-2506	—	19B	7.4M	22.9%
137	qwen/qwen3.6-27b-20260422	—	18.9B	2.2M	47.0%
138	qwen/qwen3.7-max-20260520	—	18.5B	1M	3.5%
139	qwen/qwen3-coder-480b-a35b-07-25	—	18.3B	832.8K	19.9%
140	openai/gpt-5.6-terra-pro-20260709	—	17.8B	154.1K	14.0%
141	meta/muse-glimmer-30b-20260810	—	17.5B	3M	25.1%
142	deepseek/deepseek-v3.2-exp	—	17.1B	2.3M	9.4%
143	z-ai/glm-4.7-flash-20260119	—	16.9B	6.4M	10.8%
144	meta-llama/llama-4-maverick-17b-128e-instruct	—	16.6B	8M	16.5%
145	qwen/qwen3.6-plus-04-02	—	16.5B	3.3M	12.6%
146	anthropic/claude-4-sonnet-20250522	—	16.1B	2.1M	14.0%
147	qwen/qwen3.6-flash	—	14.1B	2.2M	27.2%

Daily usage = prompt + completion + reasoning tokens; change is versus the previous day. No public source link is exposed yet; treat the data as reference only.