Open source Arcee reasoning model with a 262K context window, 80K max output, and native reasoning and tool support for agentic workloads.
Added Apr 1, 2026
Context Window
262.1K
Max Output
80.0K
Input Price (Auto)
$0.25/1M
Output Price (Auto)
$0.90/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
31.9
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Coding Index
27.2
Agentic Index
42.6
GPQA Diamond
Graduate-level scientific reasoning
75.2%
Better than 72% of models compared
HLE
Humanity's Last Exam
14.7%
Better than 83% of models compared
IFBench
Instruction-following benchmark
56.3%
Better than 74% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
90.1%
Better than 87% of models compared
AA-LCR
Long context reasoning evaluation
33.0%
Better than 52% of models compared
GDPval-AA
Economically valuable tasks
18.3%
Better than 78% of models compared
CritPt
Research-level physics reasoning
0.9%
Better than 83% of models compared
SciCode
Python programming for scientific computing
36.1%
Better than 69% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
22.7%
Better than 70% of models compared
AA-Omniscience Accuracy
Proportion of correctly answered questions
22.8%
Better than 77% of models compared
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
86.6%
Better than 33% of models compared
Last updated May 15, 2026
Artificial Analysis
