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
Model weightsContext Window
262.1K
Max Output
80.0K
Input Price (Auto)
$0.25/1M
Output Price (Auto)
$0.90/1M
Cache Read (Auto)
$0.13/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
18.7
Coding Index
25.8
Agentic Index
3.7
Reasoning
GPQA Diamond
Graduate-level scientific reasoning
75.2%
Better than 60% of models compared
HLE
Humanity's Last Exam
15.8%
Better than 70% of models compared
IFBench
Instruction-following benchmark
56.3%
Better than 67% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
90.1%
Better than 84% of models compared
AA-LCR
Long context reasoning evaluation
38.3%
Better than 44% of models compared
GDPval-AA
Economically valuable tasks
3.1%
CritPt
Research-level physics reasoning
0.9%
Coding
SciCode
Python programming for scientific computing
36.1%
Better than 56% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
22.7%
Better than 62% of models compared
Knowledge
AA-Omniscience Accuracy
Proportion of correctly answered questions
22.5%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
85.9%
Last updated Aug 16, 2026
Artificial AnalysisProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Related text models
Compare Trinity Large Thinking with similar models from the same provider or model family.
Mistral Large 3 675B
mistralai/mistral-large-3-675b-instruct-2512Mistral Large 3 675B is Mistral AI's flagship language model featuring advanced rope scaling and Eagle speculative decoding. Delivers exceptional performance across reasoning, coding, and multilingual tasks.
Hermes 4 Large
nousresearch/hermes-4-405bAdvanced reasoning model built on Llama-3.1-405B with hybrid thinking modes. Features internal deliberation capabilities, excels at math, code, STEM, and logical reasoning while supporting structured outputs with improved steerability and neutral alignment.
Jamba Large
jamba-largeJamba 1.7 with improved grounding and instruction following for more accurate and reliable responses. Ideal for complex reasoning and document analysis tasks with 256k context window.
Jamba Large 1.7
jamba-large-1.7Latest Jamba model with improved grounding and instruction following for more accurate and reliable responses. Superior speed while processing large volumes of unstructured data.
Jamba Large 1.6
jamba-large-1.6Its ability to process large volumes of unstructured data (256k tokens) with high accuracy makes it ideal for summarization and document analysis.
Llama 3.3 70B Wayfarer
LatitudeGames/Wayfarer-Large-70B-Llama-3.3Llama 3.3 70B Wayfarer is a fine-tuned version of Llama 3.3 70B, trained on a diverse set of creative writing and RP datasets with a focus on variety and deduplication. This model is designed to be highly creative and non-repetitive by making sure no two entries in the dataset have repeated characters or situations, which makes sure the model does not latch on to a certain personality and be capable of understanding and acting appropriately to any characters or situations.