Compare Models
Llama 3.1 Instruct Turbo (70B)

Release Date: Jul 23, 2024

Developer Meta 🇺🇸
Context Window 131k
Max Output Tokens 4k
Token Costs (in/out) $0.88/0.88
Weights Open
Input Modalities

Accuracy

56.17 %

Avg. Cost (In/Out)

$ 0.88 / $ 0.88

Latency

4.33 s

Vals Index
BenchmarksAccuracyRankings
TaxEval v2

0.0%

±0.97
134/141
Proprietary BenchmarksAcademic BenchmarksIndustry Partners
Vals
Default Provider : Meta
Temperature: Default
Top P: Default
Top K: Default
Max Output Tokens: 4,096