Llama-2-7B

Reported on 5 benchmarks across 2 tasks · 2 papers

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing5 results

Sentence OrderingonEconLogicQA
Accuracy· 2024-05-13
0.0077
best: 0.5692 (GPT-4-Turbo)
EconLogicQA: A Question-Answering Benchmark for Evaluating Large Language Models in Economic Sequential Reasoning arXiv:2405.07938
Conversational Web NavigationonWebLINX
Element (IoU)· 2024-02-08
22.26
best: 22.82 (Llama-2-13B)
WebLINX: Real-World Website Navigation with Multi-Turn Dialogue arXiv:2402.05930
Conversational Web NavigationonWebLINX
Intent Match· 2024-02-08
82.64
best: 84 (S-LLaMA-2.7B)
WebLINX: Real-World Website Navigation with Multi-Turn Dialogue arXiv:2402.05930
Conversational Web NavigationonWebLINX
Overall score· 2024-02-08
24.57
best: 25.21 (Llama-2-13B)
WebLINX: Real-World Website Navigation with Multi-Turn Dialogue arXiv:2402.05930
Conversational Web NavigationonWebLINX
Text (F1)· 2024-02-08
26.5
best: 27.17 (S-LLaMA-2.7B)
WebLINX: Real-World Website Navigation with Multi-Turn Dialogue arXiv:2402.05930