TAU2
Measured May 14, 2026Source
Score
0.15
Models15 1 
Meta
Llama 3.1 Instruct 70B
MetaMetaUnited States
Llama 3.1 Instruct 70B is a 70-billion parameter, instruction-tuned large language model from Meta. It features a 128K token context window and is optimized for high-performance, open-source deployment across a wide range of tasks.
ReasoningLong contextCheapCoding
Input / 1M tokens
$0.56Output / 1M tokens
$0.56Output tokens/s
31.52First-token seconds
0.59sSupported plans
2Benchmark history
Evaluations
Terminalbench Hard
Measured May 14, 2026Source
Score
0.03
Lcr
Measured May 14, 2026Source
Score
0.06
Ifbench
Measured May 14, 2026Source
Score
0.34
Aime 25
Measured May 14, 2026Source
Score
0.04
Aime
Measured May 14, 2026Source
Score
0.17
Math 500
Measured May 14, 2026Source
Score
0.65
Scicode
Measured May 14, 2026Source
Score
0.27
Livecodebench
Measured May 14, 2026Source
Score
0.23
Hle
Measured May 14, 2026Source
Score
0.05
Gpqa
Measured May 14, 2026Source
Score
0.41
Mmlu Pro
Measured May 14, 2026Source
Score
0.68
Artificial Analysis Math Index
Measured May 14, 2026Source
Score
4
Artificial Analysis Coding Index
Measured May 14, 2026Source
Score
10.9
Artificial Analysis Intelligence Index
Measured May 14, 2026Source
Score
12.5
Plan availability
Products and plans that support this model
Synthetic
Synthetic
Synthetic is a platform that runs open-source AI models in private, secure datacenters. It offers subscription and usage-based pricing for accessing models like DeepSeek, Llama, MiniMax, Kimi, and others, with OpenAI-compatible API access for use in coding agents and tools.
Discussion
Thinking... Make sure you are connected to GitHub server