GPT 6 Sol
GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, reasoning, coding, and agentic workflows.
- Reasoning
- Vision
- Native PDF input
- Tool Calling
- Structured Output
Added Sep 22, 2026
Pricing
Auto routing · per 1M tokens- Input
- $2.00
- Output
- $10.00
- Cache read
- $0.20
Specifications
- Context window
- 1.1M
- Max output
- 128K
- Avg output (7d)
- 245 tokens
- Longer than 27% of models
Benchmarks
Benchmarks
Sourced from Artificial Analysis.
Agentic work
AutomationBench-AA
Workflow automation with guardrail penalties
58.0%
Better than 79% of models compared
AutomationBench-AA Tasks Completed
Fully completed workflows without guardrail violations
28.2%
Better than 80% of models compared
Harvey LAB-AA v1.1
Legal tasks fully passed without material hallucinations
3.6%
Better than 61% of models compared
AA-Briefcase v1.1
Agentic knowledge work (Elo)
1148 Elo
Better than 56% of models compared
GDPval-AA v2.1
Economically valuable tasks (Elo)
1352 Elo
Better than 68% of models compared
Document reasoning
GDP.pdf
Professional PDF reasoning: all-pass rate
23.8%
Better than 80% of models compared
AA-LCR v1.1
Long context reasoning with updated grading
82.3%
Better than 92% of models compared
MLCR-AA
Medical long-context reasoning
28.9%
Better than 88% of models compared
Reasoning
HLE
Humanity's Last Exam
41.0%
Better than 87% of models compared
Coding
Terminal-Bench v4.0
Practical coding and terminal tasks
18.7%
Better than 68% of models compared
SciCode
Python programming for scientific computing
53.8%
Better than 69% of models compared
Legacy benchmarks
AA-LCR (unversioned / legacy)
Long context reasoning evaluation
82.3%
Better than 92% of models compared
Last updated Nov 2, 2026
Artificial AnalysisProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…