32-B parameter reasoning model from DeepCogito (Qwen backbone) – strong general reasoning & coding at low price.
Added May 10, 2025
Context Window
128.0K
Max Output
32.8K
Input Price (Auto)
$1.80/1M
Output Price (Auto)
$1.80/1M
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
17.2
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
GPQA Diamond
Graduate-level scientific reasoning
61.5%
Better than 50% of models compared
HLE
Humanity's Last Exam
5.5%
Better than 50% of models compared
IFBench
Instruction-following benchmark
22.9%
Better than 7% of models compared
AA-LCR
Long context reasoning evaluation
9.7%
Better than 24% of models compared
SciCode
Python programming for scientific computing
37.6%
Better than 75% of models compared
LiveCodeBench
Contamination-free coding benchmark
27.0%
Better than 29% of models compared
AIME 2025
American Invitational Mathematics Examination 2025
63.0%
Better than 59% of models compared
AIME
American Invitational Mathematics Examination
68.7%
Better than 78% of models compared
MMLU-Pro
Professional and academic subject knowledge
73.9%
Better than 44% of models compared
Last updated May 15, 2026
Artificial AnalysisMath-500
Diverse mathematical problem solving benchmark
94.1%
Better than 75% of models compared
