TAU2
Measured Jul 10, 2026Source
Score
0
Models12 0 
Llama 3 Instruct 70B
MetaMetaUnited States
Meta's latest open-source instruction-tuned model with 70 billion parameters. It supports a 128K context window and demonstrates strong performance in reasoning and coding tasks.
ReasoningLong contextCoding
Input / 1M tokens
$0.65Output / 1M tokens
$2.75Output tokens/s
46.37First-token seconds
0.67sSupported plans
0Benchmark history
Evaluations
Terminalbench Hard
Measured Jul 10, 2026Source
Score
0.01
Lcr
Measured Jul 10, 2026Source
Score
0
Ifbench
Measured Jul 10, 2026Source
Score
0.37
Aime
Measured Jul 10, 2026Source
Score
0
Math 500
Measured Jul 10, 2026Source
Score
0.48
Scicode
Measured Jul 10, 2026Source
Score
0.19
Livecodebench
Measured Jul 10, 2026Source
Score
0.2
Hle
Measured Jul 10, 2026Source
Score
0.04
Gpqa
Measured Jul 10, 2026Source
Score
0.38
Mmlu Pro
Measured Jul 10, 2026Source
Score
0.57
Artificial Analysis Intelligence Index
Measured Jul 10, 2026Source
Score
3.5
Plan availability
Products and plans that support this model
No products or plans have been linked to this model yet.
User ratings
Loading ratings...
Discussion
Thinking... Make sure you are connected to GitHub server