Terminalbench Hard
Measured May 29, 2026Source
Score
0.17
Models11 0 
Cogito v2.1 (Reasoning)
Deep CogitoDeep CogitoUnited States
Deep Cogito develops advanced AI models, notably the Cogito family, including Cogito v2.1, a 671B parameter Mixture of Experts model with superior reasoning efficiency and performance rivaling top commercial models.
Input / 1M tokens
$1.25Output / 1M tokens
$1.25Output tokens/s
66.84First-token seconds
0.52sSupported plans
0Benchmark history
Evaluations
Lcr
Measured May 29, 2026Source
Score
0.22
Ifbench
Measured May 29, 2026Source
Score
0.46
Aime 25
Measured May 29, 2026Source
Score
0.73
Scicode
Measured May 29, 2026Source
Score
0.41
Livecodebench
Measured May 29, 2026Source
Score
0.69
Hle
Measured May 29, 2026Source
Score
0.11
Gpqa
Measured May 29, 2026Source
Score
0.77
Mmlu Pro
Measured May 29, 2026Source
Score
0.85
Artificial Analysis Math Index
Measured May 29, 2026Source
Score
72.7
Artificial Analysis Coding Index
Measured May 29, 2026Source
Score
24.8
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