Private AI
StepFun's most capable open-source reasoning model with visible reasoning traces. Built on a sparse Mixture-of-Experts architecture with 196B total parameters and only 11B active per token, it achieves frontier-level performance in math, logic, and agentic coding while reaching up to 350 tokens/sec. Supports 256K context. NOTE: This model runs via StepFun, which may log and train on your prompts.
Added Feb 2, 2026
Model weightsContext Window
256.0K
Max Output
256.0K
Avg output tokens (7d)
2.2K tokens
Input Price (Auto)
$0.10/1M
Output Price (Auto)
$0.30/1M
Cache Read (Auto)
$0.050/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
26.0
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
GPQA Diamond
Graduate-level scientific reasoning
83.1%
Better than 78% of models compared
HLE
Humanity's Last Exam
19.1%
Better than 78% of models compared
IFBench
Instruction-following benchmark
64.6%
Better than 76% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
94.4%
Better than 92% of models compared
AA-LCR
Long context reasoning evaluation
43.0%
Better than 51% of models compared
CritPt
Research-level physics reasoning
2.5%
SciCode
Python programming for scientific computing
40.4%
Better than 74% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
27.3%
AA-Omniscience Accuracy
Proportion of correctly answered questions
23.9%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
85.2%
Last updated Jun 19, 2026, 12:00 PM
Artificial AnalysisBetter than 70% of models compared
