Agents
The bigger change is at the low end. At low effort, GPT-6.1 Sol scores 58.1% for $0.21 per task, up from 50.5% for GPT-6 Sol at the same set…
The bigger change is at the low end. At low effort, GPT-6.1 Sol scores 58.1% for 0.21 per task, up from 50.5% for GPT-6 Sol at the same setting. That's the highest score of any model under 0.30 per ta
The bigger change is at the low end. At low effort, GPT-6.1 Sol scores 58.1% for 0.21 per task, up from 50.5% for GPT-6 Sol at the same setting. That's the highest score of any model under 0.30 per task on the leaderboard. https://devin.ai/blog/gpt-6-1-sol
Related
- FrontierCode has three task sets: Extended (150 tasks), Main (100 tasks) and Diamond (50 tasks). SOTA LLMs have significant room for improve…
- Introducing SWE-1.7, the most capable model we’ve trained yet. It scores within a few points of the strongest frontier models at a fraction …
- With SWE-1.6 we've made significant progress on 'intelligence per token'. We post-trained the model from scratch (same pre-trained model) wi…
Source: Cognition AI (X) | 2026-09-29