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.
600 models · page 6 of 13
OpenAI
GPT-2 (137M)
1 benchmarks · 12 observations
Explore results →OpenAI
GPT-2-XL-1.5B
1 benchmarks · 1 observations
Explore results →OpenAI
GPT-3.5 (175B)
1 benchmarks · 1 observations
Explore results →OpenAI
GPT-3.5 (gpt-3.5-turbo-instruct)
1 benchmarks · 2 observations
Explore results →OpenAI
GPT-3.5 (N/A)
1 benchmarks · 4 observations
Explore results →OpenAI
GPT-3.5 / Episodic + Reflexion
1 benchmarks · 1 observations
Explore results →OpenAI
GPT-3.5 / Episodic Retrieval
1 benchmarks · 1 observations
Explore results →OpenAI
GPT-3.5 / Reflexion
1 benchmarks · 1 observations
Explore results →OpenAI
GPT-3.5 / Semantic + Episodic
1 benchmarks · 1 observations
Explore results →OpenAI
GPT-3.5 / Semantic + Episodic + Reflexion
1 benchmarks · 1 observations
Explore results →OpenAI
GPT-3.5 / Semantic + Reflexion
1 benchmarks · 1 observations
Explore results →OpenAI
GPT-3.5 / Semantic Retrieval
1 benchmarks · 1 observations
Explore results →OpenAI
GPT-3.5 / Zero-shot
1 benchmarks · 1 observations
Explore results →OpenAI
GPT-3.5 + FreshPrompt
1 benchmarks · 4 observations
Explore results →OpenAI
GPT-3.5 + Self-Ask
1 benchmarks · 1 observations
Explore results →OpenAI
GPT-3.5 + Self-Ask (N/A)
1 benchmarks · 1 observations
Explore results →OpenAI
GPT-3.5 + Z-Code++ Microsoft Azure AI (He et al. 2022)
1 benchmarks · 2 observations
Explore results →OpenAI
GPT-3.5-1106
1 benchmarks · 8 observations
Explore results →OpenAI
GPT-3.5-turbo / unk
1 benchmarks · 1 observations
Explore results →OpenAI
GPT-3.5-turbo + CoT
1 benchmarks · 4 observations
Explore results →OpenAI
GPT-3.5-turbo + CoT + EthicsPrompt
1 benchmarks · 4 observations
Explore results →OpenAI
GPT-3.5-turbo + EthicsPrompt + NoGoals
1 benchmarks · 4 observations
Explore results →OpenAI
GPT-3.5-turbo-16K
1 benchmarks · 4 observations
Explore results →OpenAI
GPT-3.5-Turbo-20231106†
1 benchmarks · 1 observations
Explore results →OpenAI
GPT-4 (8-shot)
1 benchmarks · 1 observations
Explore results →OpenAI
GPT-4 (gpt-4-0613)
1 benchmarks · 2 observations
Explore results →OpenAI
GPT-4 (Medprompt) Microsoft (Nori et al. 2023)
1 benchmarks · 1 observations
Explore results →OpenAI
GPT-4 (N/A)
1 benchmarks · 4 observations
Explore results →OpenAI
GPT-4 (NA)
1 benchmarks · 1 observations
Explore results →OpenAI
GPT-4 (vision preview)
1 benchmarks · 1 observations
Explore results →OpenAI
GPT-4 / Base
1 benchmarks · 3 observations
Explore results →OpenAI
GPT-4 / Episodic + Reflexion
1 benchmarks · 1 observations
Explore results →OpenAI
GPT-4 / Episodic Retrieval
1 benchmarks · 1 observations
Explore results →OpenAI
GPT-4 / Reflexion
1 benchmarks · 1 observations
Explore results →OpenAI
GPT-4 / Semantic + Episodic
1 benchmarks · 1 observations
Explore results →OpenAI
GPT-4 / Semantic + Episodic + Reflexion
1 benchmarks · 1 observations
Explore results →OpenAI
GPT-4 / Semantic + Reflexion
1 benchmarks · 1 observations
Explore results →OpenAI
GPT-4 / Semantic Retrieval
1 benchmarks · 1 observations
Explore results →OpenAI
GPT-4 / Zero-shot
1 benchmarks · 1 observations
Explore results →OpenAI
GPT-4 + CoT
1 benchmarks · 4 observations
Explore results →OpenAI
GPT-4 + CoT+ EthicsPrompt
1 benchmarks · 4 observations
Explore results →OpenAI
GPT-4 + EthicsPrompt + NoGoals
1 benchmarks · 4 observations
Explore results →OpenAI
GPT-4 + FreshPrompt
1 benchmarks · 4 observations
Explore results →OpenAI
GPT-4 + plugins*
1 benchmarks · 3 observations
Explore results →OpenAI
GPT-4 + Self-Ask
1 benchmarks · 1 observations
Explore results →OpenAI
GPT-4 + Self-Ask (N/A)
1 benchmarks · 1 observations
Explore results →OpenAI
GPT-4 Baseline
1 benchmarks · 1 observations
Explore results →OpenAI
GPT-4 Microsoft & OpenAI (Nori et al. 2023)
1 benchmarks · 1 observations
Explore results →