GPT-5.6 Sol
A high-intelligence model that leads the cited Coding Agent Index snapshot in OpenAI’s Codex harness.
INTELLIGENCE59index
CODING80%
AGENTIC—NOT MEASURED
SPEED60tok/s
FIT / INTERPRETATION
Where the evidence points.
- Coding agents
- Deep reasoning
- Large-context analysis
TECHNICAL CONTEXT
Score needs conditions.
- Context
- 1M
- Input / 1M
- $5
- Output / 1M
- $30
- Access
- Proprietary