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
Context Window
256.0K
Max Output
256.0K
Input Price (Auto)
$0.10/1M
Output Price (Auto)
$0.30/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
38.5
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Coding Index
34.6
GPQA Diamond
Graduate-level scientific reasoning
82.6%
Better than 86% of models compared
HLE
Humanity's Last Exam
22.6%
Better than 91% of models compared
IFBench
Instruction-following benchmark
66.5%
Better than 84% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
87.4%
Better than 85% of models compared
AA-LCR
Long context reasoning evaluation
54.3%
Better than 72% of models compared
SciCode
Python programming for scientific computing
38.5%
Better than 78% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
32.6%
Better than 83% of models compared
Last updated May 15, 2026
Artificial Analysis
