SWE-1.7: Frontier Intelligence at a Fraction of the Cost
- It reaches frontier-level intelligence at a much lower cost, advancing the cost-performance Pareto curve.
- SWE-1.7 is the result of broad improvements across our RL pipeline: better infrastructure, more stable training, higher-quality data, and new techniques for long-horizon tasks.
Unverified
- It reaches frontier-level intelligence at a much lower cost, advancing the cost-performance Pareto curve.
- SWE-1.7 is the result of broad improvements across our RL pipeline: better infrastructure, more stable training, higher-quality data, and new techniques for long-horizon tasks.
Sources: Cognition