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.
636 models · page 14 of 14
OpenAI
text-babbage-001
1 benchmarks · 1 observations
Explore results →OpenAI
text-curie-001
1 benchmarks · 1 observations
Explore results →Microsoft
TinyLLaVA[53] (Phi2-2.7B[32])
1 benchmarks · 1 observations
Explore results →OpenAI
Transformers Agent (GPT-4)
1 benchmarks · 1 observations
Explore results →OpenAI
USTC-KCIL DBT Agent + GPT-5.4 USTC-KCIL
1 benchmarks · 1 observations
Explore results →OpenAI
Vanilla (GPT-4o)
1 benchmarks · 1 observations
Explore results →OpenAI
ViLT (GPT Eval)
1 benchmarks · 3 observations
Explore results →Microsoft
wizardlm-30b / v1.0
1 benchmarks · 1 observations
Explore results →OpenAI
Zero-Shot CoT GPT-3.5-turbo-16k
1 benchmarks · 1 observations
Explore results →OpenAI
Zero-Shot CoT GPT-4
1 benchmarks · 1 observations
Explore results →OpenAI
Zero-Shot GPT-3.5-turbo-16k
1 benchmarks · 1 observations
Explore results →OpenAI
Zero-Shot GPT-4
1 benchmarks · 1 observations
Explore results →