TAU2
Measured May 14, 2026Source
Score
0.17
Models13 0 
Granite 4.0 H Small
IBMIBMUnited States
Granite 4.0 H Small is a compact, efficient model from IBM's Granite family, designed for enterprise applications. It offers a balance of strong reasoning capabilities and fast response times, making it suitable for tasks requiring quick and reliable inference.
ReasoningFastCheap
Input / 1M tokens
$0.06Output / 1M tokens
$0.25Output tokens/s
265.36First-token seconds
8.77sSupported plans
0Benchmark history
Evaluations
Terminalbench Hard
Measured May 14, 2026Source
Score
0.02
Lcr
Measured May 14, 2026Source
Score
0.09
Ifbench
Measured May 14, 2026Source
Score
0.32
Aime 25
Measured May 14, 2026Source
Score
0.14
Scicode
Measured May 14, 2026Source
Score
0.21
Livecodebench
Measured May 14, 2026Source
Score
0.25
Hle
Measured May 14, 2026Source
Score
0.04
Gpqa
Measured May 14, 2026Source
Score
0.42
Mmlu Pro
Measured May 14, 2026Source
Score
0.62
Artificial Analysis Math Index
Measured May 14, 2026Source
Score
13.7
Artificial Analysis Coding Index
Measured May 14, 2026Source
Score
8.5
Artificial Analysis Intelligence Index
Measured May 14, 2026Source
Score
10.8
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