Models

541 models with published results from our own benchmarks and licensed sources. Open a model to see every result, with its source and date.

Model	Provider	Sources	Results
amazon-nova-experimental-chat-12-10	Amazon	1	7
amazon-nova-experimental-chat-26-01-10	Amazon	1	7
amazon-nova-experimental-chat-26-02-10	Amazon	1	7
api-gpt-4o-search	OpenAI	1	1
apriel-nemotron-15b-thinker	Servicenow	1	3
arch-agent-1.5b	Katanemo	1	8
arch-agent-32b	Katanemo	1	8
arch-agent-3b	Katanemo	1	8
athene-70b-0725	Nexusflow	1	6
athene-v2-chat	Nexusflow	1	6
bielik-11b-v2.3-instruct	Speakleash And Ack Cyfronet Agh	1	8
bitagent-bounty-8b	Bittensor	1	8
chatglm-6b	Z.ai	1	5
chatglm2-6b	Z.ai	1	5
chatglm3-6b	Z.ai	1	5
claude-3-5-haiku-20241022	Anthropic	1	6
claude-3-5-sonnet-20240620	Anthropic	1	6
claude-3-5-sonnet-20241022	Anthropic	1	6
claude-3-sonnet-20240229	Anthropic	1	6
coalm-70b	Uiuc Oumi	1	8
coalm-8b	Uiuc Oumi	1	8
codellama-34b-instruct	Meta	1	5
codellama-70b-instruct	Meta	1	3
command-a-reasoning	Cohere	1	8
command-r	Cohere	1	6
command-r-plus	Cohere	1	6
dbrx-instruct-preview	Databricks	1	6
deepseek-coder-v2	DeepSeek	1	6
deepseek-llm-67b-chat	DeepSeek	1	5
deepseek-v2.5	DeepSeek	1	6
deepseek-v2.5-1210	DeepSeek	1	6
deepseek-v3.2-speciale	DeepSeek	1	3
deepseek-v4-flash-preview	DeepSeek	1	7
deepseek-v4-pro-preview	DeepSeek	1	7
devstral-small-2-24b-instruct-2512	Mistral	1	3
diffbot-small-xl	Diffbot	1	1
dola-seed-2.0-pro	Bytedance	1	7
dolly-v2-12b	Databricks	1	5
dolphin-2.2.1-mistral-7b	Cognitivecomputations	1	4
ernie-5.0-0110	Baidu	1	7
ernie-5.0-preview-1022	Baidu	1	7
ernie-5.0-preview-1203	Baidu	1	7
ernie-5.1	Baidu	1	8
exaone-4.0-32b	Lgai Exaone	1	3
falcon-180b-chat	TII	1	4
falcon-h1-0.5b-instruct	TII	1	3
falcon-h1-1.5b-deep-instruct	TII	1	3
falcon-h1-1.5b-instruct	TII	1	3
falcon-h1-3b-instruct	TII	1	3
falcon-h1-7b-instruct	TII	1	3

Want two models side by side? Compare models.