Kilian Lieret

Congrats to the Kimi team on the super strong SWE-bench Verified and SWE-bench Multilingual numbers!!

Do language models have algorithmic creativity? To find out, we built AlgoTune, a benchmark challenging agents to optimize 100+ algorithms like gzip compression, AES encryption and PCA. Frontier models struggle, finding only surface-level wins. Lots of headroom here!🧵⬇️

We just updated the SWE-bench Multimodal leaderboard with new systems from @refact_ai, @allhands_ai and @TU_Muenchen. Congrats to all teams on pushing the state-of-the-art performance! SWE-bench Multimodal challenges AI systems to fix issues that are described using screenshots.

Can GPT, Claude, and Gemini play video games like Zelda, Civ, and Doom II? 𝗩𝗶𝗱𝗲𝗼𝗚𝗮𝗺𝗲𝗕𝗲𝗻𝗰𝗵 evaluates VLMs on Game Boy & MS-DOS games given only raw screen input, just like how a human would play. The best model (Gemini) completes just 0.48% of the benchmark! 🧵👇

40% with just 1 try per task: SWE-agent-LM-32B is the new #1 open source model on SWE-bench Verified. We built it by synthesizing a ton of agentic training data from 100+ Python repos. Today we’re open-sourcing the toolkit that made it happen: SWE-smith.

Introducing SWE-bench Multilingual: a new eval in the SWE-bench family to test LLM coding abilities in *9* programming languages, fully integrated with SB so it can plug into existing workflows. Claude 3.7 gets 43% on SB Multilingual vs 63% on SB Verified, a 20 pt drop!🧵

Had a great time talking about building agents, SWE-agent, SWE-bench, and more