Developer

Ai2

27 indexed models; 8 currently meet the evidence threshold for the overall ranking. Together they have results from 14 evaluations.

Official Ai2 model information ↗

Models by Ai2

ModelEvalsComponentsRankRelease date
Llama 3.1 Tulu 3 8B35/7402024-11-20
Olmo 3 7B Instruct33/7972025-11-19
Olmo 3.1 32B Instruct32/71192025-12-10
Olmo 2 0325 32B Instruct86/72222025-03-13
Olmo 3.1 32B Think32/72492025-12-10
Olmo 2 1124 13B Instruct65/72702024-11-26
Olmo 2 1124 7B Instruct65/72952024-11-26
Olmoe 1B 7B 0125 Instruct53/73012025-01-27
Llama 3.1 Tulu 3 70B11/7
Llama 3.1 Tulu 3 70B Dpo12/72024-11-20
Llama 3.1 Tulu 3 70B Ppo Rlvf12/72024-11-20
Llama 3.1 Tulu 3 70B Sft12/72024-11-18
Llama 3.1 Tulu 3 8B Dpo25/72024-11-20
Llama 3.1 Tulu 3 8B Ppo Rlvf12/72024-11-20
Llama 3.1 Tulu 3 8B Sft25/72024-11-18
Molmo2 8B11/72025-12-14
Olmo 3 32B Think21/72025-11-19
Olmo 3 7B22/7
Olmo 3 7B Think11/72025-11-18
Olmo 7B 0724 Instruct25/72024-07-09
Olmo 7B Instruct Hf13/7
Olmoe 1B 7B 0924 Instruct13/7
Tulu 2 13B12/7
Tulu 2 7B12/7
Tulu 2 Dpo 13B14/72023-11-13
Tulu 2 Dpo 70B14/72023-11-12
Tulu 2 Dpo 7B14/72023-11-13
Evaluations covering Ai2 models (14)