Albert Örwall

@aorwall

Building Moatless Tools (github.com/aorwall/moatle…) and eval.moatless.ai

Stockholm, Sweden

Joined May 2007

458 Following

211 Followers

Replies Reposts Media

Albert Örwall
@aorwall
Jul 29, 2025
I did wonder how long this could continue... But I never ran 24/7. Just a few days with good flow and agents running in parallell using the Claude Code SDK x.com/AnthropicAI/st…
Anthropic
@AnthropicAI
Jul 28, 2025
Replying to @AnthropicAI
Some of the biggest Claude Code fans are running it continuously in the background, 24/7. These uses are remarkable and we want to enable them. But a few outlying cases are very costly to support. For example, one user consumed tens of thousands in model usage on a $200 plan.
2
Albert Örwall
@aorwall
Jun 24, 2025
Nice to see Moatless Tools at the top again. The challenge continues to solve as many issues as possible with as few tokens as possible
Ofir Press
@OfirPress
Jun 23, 2025
We're going to update the SWE-bench leaderboards soon- lots of new submissions, including 3 systems for SWE-bench Multimodal :) We will also release SWE-agent Multimodal. w/ @jyangballin @_carlosejimenez @KLieret
1
Albert Örwall
@aorwall
Jan 20, 2025
Deepseek-R1 gets 50% on SWE-Bench Verified Mini with Moatless Tools, surpassing Claude 3.5 Sonnet. experiments.moatless.ai/evaluations/20…
DeepSeek
@deepseek_ai
Jan 20, 2025
🚀 DeepSeek-R1 is here! ⚡ Performance on par with OpenAI-o1 📖 Fully open-source model & technical report 🏆 MIT licensed: Distill & commercialize freely! 🌐 Website & API are live now! Try DeepThink at chat.deepseek.com today! 🐋 1/n
4
Albert Örwall
@aorwall
Jan 19, 2025
I just benchmarked Moatless Tools with multiple AI models on the SWE-Bench Verified Mini dataset created by @MariusHobbhahn. Check out the results here experiments.moatless.ai
1
Albert Örwall
@aorwall
Jan 17, 2025
Finally, a leaderboard that Moatless Tools can top. It’s too easy to just throw money at the agent to get a high score on SWE-Bench.
Sayash Kapoor
@sayashk
Jan 16, 2025
How expensive are the best SWE-Bench agents? Do reasoning models outperform language models? Can we trust agent evaluations? 📢 Announcing HAL, a Holistic Agent Leaderboard for evaluating AI agents, with 11 benchmarks, 90+ agents, and many more to come.
1