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.
275 models · page 3 of 6
Meta
Llama 1 / 7B
2 benchmarks · 2 observations
Explore results →Meta
Llama 3-70B-Inst
2 benchmarks · 19 observations
Explore results →Meta
Llama 3-8B-Inst
2 benchmarks · 10 observations
Explore results →Meta
Llama 3-OffsetBias-RM-8B
2 benchmarks · 2 observations
Explore results →Meta
Llama 3.2 90B Vision Instruct
2 benchmarks · 2 observations
Explore results →Meta
Llama 3.2 Vision (11B)
2 benchmarks · 2 observations
Explore results →Meta
Llama 3.2 Vision (90B)
2 benchmarks · 2 observations
Explore results →Meta
Llama 3.2-1B-Inst
2 benchmarks · 4 observations
Explore results →Meta
Llama 3.2-1B-Instruct
2 benchmarks · 7 observations
Explore results →Meta
Llama 3.2-3B-Inst
2 benchmarks · 4 observations
Explore results →Meta
Llama 3.2-3B-Instruct
2 benchmarks · 7 observations
Explore results →Meta
Llama 4-Scout-17B-16E-Instruct
2 benchmarks · 2 observations
Explore results →Meta
LLaMA-Adapter-V2
2 benchmarks · 3 observations
Explore results →Microsoft
Phi-3-medium-128k-instruct
2 benchmarks · 55 observations
Explore results →Microsoft
Phi-3-mini-128k-instruct
2 benchmarks · 55 observations
Explore results →Microsoft
Phi3.5-Vision-4B
2 benchmarks · 3 observations
Explore results →Meta
Phind-CodeLlama-34B-v2
2 benchmarks · 2 observations
Explore results →Microsoft
wizardlm-13b / v1.2
2 benchmarks · 3 observations
Explore results →Meta
Chinese-LLaMA-13B
1 benchmarks · 2 observations
Explore results →Meta
CodeLlama-13b-Instruct-hf
1 benchmarks · 1 observations
Explore results →Meta
CodeLlama-34b-Instruct-hf
1 benchmarks · 1 observations
Explore results →Meta
CodeLlama-7b-Instruct-hf
1 benchmarks · 1 observations
Explore results →Meta
Emu [41] / LLaMA-13B
1 benchmarks · 1 observations
Explore results →Meta
EvalPlanner-Llama-8B
1 benchmarks · 1 observations
Explore results →Meta
Few-Shot CoT Llama-2-70B-chat
1 benchmarks · 1 observations
Explore results →Meta
Few-Shot Llama-2-70B-chat
1 benchmarks · 1 observations
Explore results →Meta
Galactica Meta AI (Taylor et al. 2022)
1 benchmarks · 1 observations
Explore results →Meta
HarmB-Llama
1 benchmarks · 2 observations
Explore results →Meta
IDEFICS-9B-Instruct [21] / LLaMA-7B
1 benchmarks · 1 observations
Explore results →Meta
J1-Llama-70B
1 benchmarks · 1 observations
Explore results →Meta
LLaMA
1 benchmarks · 4 observations
Explore results →Meta
Llama 1 / 30B
1 benchmarks · 1 observations
Explore results →Meta
Llama 1 / 70B
1 benchmarks · 1 observations
Explore results →Meta
Llama 1 33B
1 benchmarks · 1 observations
Explore results →Meta
Llama 1 65B
1 benchmarks · 1 observations
Explore results →Meta
Llama 13b + EthicsPrompt + NoGoals
1 benchmarks · 4 observations
Explore results →Meta
Llama 2 7B / NQ / Adapt-LLM (ours)
1 benchmarks · 1 observations
Explore results →Meta
Llama 2 7B / NQ / Always Retrieve
1 benchmarks · 1 observations
Explore results →Meta
Llama 2 7B / NQ / Never Retrieve
1 benchmarks · 1 observations
Explore results →Meta
Llama 2 7B / SQuAD / Adapt-LLM (ours)
1 benchmarks · 1 observations
Explore results →Meta
Llama 2 7B / SQuAD / Always Retrieve
1 benchmarks · 1 observations
Explore results →Meta
Llama 2 7B / SQuAD / Never Retrieve
1 benchmarks · 1 observations
Explore results →Meta
Llama 2 base / 70B
1 benchmarks · 1 observations
Explore results →Meta
Llama 2-70b-chat-hf†
1 benchmarks · 1 observations
Explore results →Meta
Llama 2-7B-32K
1 benchmarks · 42 observations
Explore results →Meta
Llama 2-7B-32K-Instruct
1 benchmarks · 42 observations
Explore results →Meta
Llama 2-CHAT 13B (8-shot)
1 benchmarks · 1 observations
Explore results →Meta
Llama 2-CHAT 70B (8-shot)
1 benchmarks · 1 observations
Explore results →