An open-weight, 117B-parameter Mixture-of-Experts (MoE) language model designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.
Added Feb 3, 2026
Model weightsContext Window
128.0K
Max Output
16.4K
Avg output tokens (7d)
774 tokens
Input Price (Auto)
$0.030/1M
Output Price (Auto)
$0.17/1M
Cache Read (Auto)
$0.030/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
12.3
Coding Index
30.4
Agentic Index
6.2
Agentic work
AutomationBench-AA
Workflow automation with guardrail penalties
0.2%
Better than 4% of models compared
AutomationBench-AA Tasks Completed
Fully completed workflows without guardrail violations
0.0%
Better than 0% of models compared
AA-Briefcase
Agentic knowledge work (Elo)
0 Elo
Better than 2% of models compared
GDPval-AA v2
Economically valuable tasks (Elo)
745 Elo
Better than 35% of models compared
Document reasoning
GDP.pdf
Professional PDF reasoning: all-pass rate
4.0%
Better than 28% of models compared
AA-LCR v1.1
Long context reasoning with updated grading
52.0%
Better than 48% of models compared
Reasoning
HLE
Humanity's Last Exam
19.6%
Better than 71% of models compared
IFBench
Instruction-following benchmark
69.0%
Better than 83% of models compared
CritPt
Research-level physics reasoning
1.1%
Coding
Terminal-Bench v4.0
Practical coding and terminal tasks
0.0%
Better than 17% of models compared
SciCode
Python programming for scientific computing
34.0%
Better than 14% of models compared
LiveCodeBench
Contamination-free coding benchmark
87.8%
Better than 98% of models compared
Math
AIME 2025
American Invitational Mathematics Examination 2025
93.4%
Better than 94% of models compared
Knowledge
MMLU-Pro
Professional and academic subject knowledge
80.8%
Better than 71% of models compared
AA-Omniscience Accuracy
Proportion of correctly answered questions
21.8%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
90.8%
Legacy benchmarks
GPQA Diamond (legacy)
Graduate-level scientific reasoning
78.2%
Better than 63% of models compared
Terminal-Bench Hard (legacy)
Agentic coding and terminal use
23.5%
Better than 63% of models compared
T²-Bench Telecom (legacy)
Conversational AI agents in dual-control scenarios
65.8%
Better than 60% of models compared
AA-LCR (unversioned / legacy)
Long context reasoning evaluation
52.0%
Better than 48% of models compared
GDPval-AA (unversioned / legacy)
Economically valuable tasks
12.2%
Last updated Sep 13, 2026
Artificial AnalysisProviders
Choose explicit providers for this model. Auto routing remains available as the default option.
Loading provider options…
Related text models
Compare GPT OSS 120B with similar models from the same provider or model family.
GPT OSS Safeguard 20B
openai/gpt-oss-safeguard-20bgpt-oss-safeguard is a first open weight reasoning model specifically trained for safety classification tasks to help classify text content based on customizable policies. As a fine-tuned version of gpt-oss, gpt-oss-safeguard is designed to follow explicit written policies that you provide. This enables bring-your-own-policy Trust & Safety AI, where your own taxonomy, definitions, and thresholds guide classification decisions. Well crafted policies unlock gpt-oss-safeguard's reasoning capabilities, enabling it to handle nuanced content, explain borderline decisions, and adapt to contextual factors.
GPT OSS 20B
openai/gpt-oss-20bAn open-weight 21B parameter model released under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI's Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.
GPT Astra Latest
openai/gpt-astra-latestCompatibility alias that routes to GPT 6 Astra, the latest supported GPT Astra model.
GPT Luna Latest
openai/gpt-luna-latestCompatibility alias that routes to GPT 5.6 Luna, the latest supported GPT Luna model.
GPT Sol Latest
openai/gpt-sol-latestCompatibility alias that routes to GPT 5.6 Sol, the latest supported GPT Sol model.
GPT Terra Latest
openai/gpt-terra-latestCompatibility alias that routes to GPT 5.6 Terra, the latest supported GPT Terra model.