MODEL DIRECTORY
Follow the model.
See the evidence.
Benchmark results, evaluation settings and disclosed training methods—collected in one place for each model.
3,335 reported models and checkpoint variants. Scores keep their original units and sources.
21 models · page 1 of 1
AI2
OLMo 2 Furious 13B
1 benchmarks · 1 observations
Explore results →AI2
Tulu 3 (Tülu 3) 70B
3 benchmarks · 3 observations
Explore results →AI2
Molmo-72B
3 benchmarks · 4 observations
Explore results →AI2
Molmo-7B-D
3 benchmarks · 4 observations
Explore results →AI2
Molmo-7B-O
2 benchmarks · 3 observations
Explore results →AI2
allenai/Llama-3.1-70B-Instruct-RM-RB2
1 benchmarks · 1 observations
Explore results →AI2
allenai/Llama-3.1-8B-Instruct-RM-RB2
1 benchmarks · 1 observations
Explore results →AI2
ollama/tulu3
1 benchmarks · 1 observations
Explore results →AI2
OLMo (7B)
1 benchmarks · 1 observations
Explore results →AI2
OLMo 1.7 (7B)
1 benchmarks · 1 observations
Explore results →AI2
OLMo-7B-0724-hf (Groeneveld et al., 2024)
1 benchmarks · 1 observations
Explore results →AI2
OLMo-7B-0724-Instruct-hf (Groeneveld et al., 2024)
1 benchmarks · 1 observations
Explore results →AI2
OLMo-7B-Instruct
1 benchmarks · 2 observations
Explore results →AI2
Tulu-2-13b
1 benchmarks · 12 observations
Explore results →AI2
Tulu-2-13b-dpo
1 benchmarks · 12 observations
Explore results →AI2
Tulu-2-70b
1 benchmarks · 12 observations
Explore results →AI2
Tulu-2-70b-dpo
1 benchmarks · 12 observations
Explore results →AI2
Tulu-2-7b
1 benchmarks · 12 observations
Explore results →AI2
Tulu-2-7b-dpo
1 benchmarks · 12 observations
Explore results →AI2
Tulu-2-dpo-70b
1 benchmarks · 1 observations
Explore results →AI2
tulu-v2.5-70b-preference-mix-rm
1 benchmarks · 1 observations
Explore results →