Private AI
The reasoning version of Thinking Machines' 276B-parameter open-weights multimodal Mixture-of-Experts model with 12B active parameters. It reasons over text and images, and is designed for agentic coding, tool use, instruction following, and long workflows with controllable thinking effort.
Added Jul 31, 2026
Model weightsContext Window
524.3K
Max Output
32.8K
Input Price (Auto)
$0.50/1M
Output Price (Auto)
$1.20/1M
Cache Read (Auto)
$0.10/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
41.2
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Coding Index
52.9
Agentic Index
31.9
GPQA Diamond
Graduate-level scientific reasoning
89.5%
Better than 91% of models compared
HLE
Humanity's Last Exam
33.3%
Better than 89% of models compared
AA-LCR
Long context reasoning evaluation
69.3%
Better than 79% of models compared
GDPval-AA
Economically valuable tasks
38.5%
CritPt
Research-level physics reasoning
8.3%
SciCode
Python programming for scientific computing
48.7%
Better than 89% of models compared
AA-Omniscience Accuracy
Proportion of correctly answered questions
33.2%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
63.0%
Last updated Aug 8, 2026
Artificial Analysis