TAU2
Measured May 14, 2026Source
Score
0.72
Models13 0 
Nova 2.0 Pro Preview (Non-reasoning)
AmazonAmazonUnited States
This is a preview version of Amazon's Nova 2.0 Pro model, positioned as a non-reasoning variant. It is designed to offer strong performance in general tasks, coding, and multimodal understanding without a dedicated chain-of-thought reasoning mode.
CodingFastCheapLong contextMultimodal
Input / 1M tokens
$1.25Output / 1M tokens
$10.00Output tokens/s
144.86First-token seconds
0.74sSupported plans
0Benchmark history
Evaluations
Terminalbench Hard
Measured May 14, 2026Source
Score
0.17
Lcr
Measured May 14, 2026Source
Score
0.28
Ifbench
Measured May 14, 2026Source
Score
0.52
Aime 25
Measured May 14, 2026Source
Score
0.31
Scicode
Measured May 14, 2026Source
Score
0.28
Livecodebench
Measured May 14, 2026Source
Score
0.47
Hle
Measured May 14, 2026Source
Score
0.04
Gpqa
Measured May 14, 2026Source
Score
0.64
Mmlu Pro
Measured May 14, 2026Source
Score
0.77
Artificial Analysis Math Index
Measured May 14, 2026Source
Score
30.7
Artificial Analysis Coding Index
Measured May 14, 2026Source
Score
20.5
Artificial Analysis Intelligence Index
Measured May 14, 2026Source
Score
23.1
Plan availability
Products and plans that support this model
No products or plans have been linked to this model yet.
Discussion
Thinking... Make sure you are connected to GitHub server