Thanks! Looking forward to seeing your results.
🔄 In a Training Loop
Wanghan Xu
black-yt
AI & ML interests
LLMs, Agents, AI Scientists, Generative AI
Recent Activity
authored a paper 6 days ago
CoworkOS:Scaling Agent Coworkers for Real-world Automation upvoted a paper 6 days ago
CoworkOS:Scaling Agent Coworkers for Real-world Automation upvoted an article 17 days ago
Introducing A5: Proactive Personal Agent in Your Life-Long ContextOrganizations
replied to their post 5 months ago
reacted to their post with 🔥 5 months ago
Post
4,908
Hey all — our ResearchClawBench leaderboard just updated 🔥
We let AI do real science: 40 tasks across 10 disciplines, compared to human papers. Hard example? 🏔️ Glacier mass change — AI must integrate 233 datasets from 35 teams, 4 methods, reproduce 6542±387 Gt ice loss vs IPCC. No toy problems.
Latest leaderboard (2026-06-09) 📊:
Agents: 🥇 Claude Code 21.5 (50 = match human), $5.3; 🥈 EvoScientist 18.8, $4.1; 🥉 Codex CLI 18.4, just $2.0
LLMs+Harness: 🥇 Claude-Opus-4.8 21.1, $4.0; 🥈 Claude-Opus-4.7 20.7; 🥉 MiniMax-M3 19.8, only $0.45; Qwen3.7-Max 18.7, $0.42, 11min 💥
Claude still king, but MiniMax/Qwen/DeepSeek are crazy cheap and competitive. Expensive isn't always better.
📎 Code & star: https://github.com/InternScience/ResearchClawBench
🏠 Website: https://internscience.github.io/ResearchClawBench-Home/
🤗 Upvote paper: ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research (2606.07591)
We let AI do real science: 40 tasks across 10 disciplines, compared to human papers. Hard example? 🏔️ Glacier mass change — AI must integrate 233 datasets from 35 teams, 4 methods, reproduce 6542±387 Gt ice loss vs IPCC. No toy problems.
Latest leaderboard (2026-06-09) 📊:
Agents: 🥇 Claude Code 21.5 (50 = match human), $5.3; 🥈 EvoScientist 18.8, $4.1; 🥉 Codex CLI 18.4, just $2.0
LLMs+Harness: 🥇 Claude-Opus-4.8 21.1, $4.0; 🥈 Claude-Opus-4.7 20.7; 🥉 MiniMax-M3 19.8, only $0.45; Qwen3.7-Max 18.7, $0.42, 11min 💥
Claude still king, but MiniMax/Qwen/DeepSeek are crazy cheap and competitive. Expensive isn't always better.
📎 Code & star: https://github.com/InternScience/ResearchClawBench
🏠 Website: https://internscience.github.io/ResearchClawBench-Home/
🤗 Upvote paper: ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research (2606.07591)
- 2 replies
posted an update 5 months ago
Post
4,908
Hey all — our ResearchClawBench leaderboard just updated 🔥
We let AI do real science: 40 tasks across 10 disciplines, compared to human papers. Hard example? 🏔️ Glacier mass change — AI must integrate 233 datasets from 35 teams, 4 methods, reproduce 6542±387 Gt ice loss vs IPCC. No toy problems.
Latest leaderboard (2026-06-09) 📊:
Agents: 🥇 Claude Code 21.5 (50 = match human), $5.3; 🥈 EvoScientist 18.8, $4.1; 🥉 Codex CLI 18.4, just $2.0
LLMs+Harness: 🥇 Claude-Opus-4.8 21.1, $4.0; 🥈 Claude-Opus-4.7 20.7; 🥉 MiniMax-M3 19.8, only $0.45; Qwen3.7-Max 18.7, $0.42, 11min 💥
Claude still king, but MiniMax/Qwen/DeepSeek are crazy cheap and competitive. Expensive isn't always better.
📎 Code & star: https://github.com/InternScience/ResearchClawBench
🏠 Website: https://internscience.github.io/ResearchClawBench-Home/
🤗 Upvote paper: ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research (2606.07591)
We let AI do real science: 40 tasks across 10 disciplines, compared to human papers. Hard example? 🏔️ Glacier mass change — AI must integrate 233 datasets from 35 teams, 4 methods, reproduce 6542±387 Gt ice loss vs IPCC. No toy problems.
Latest leaderboard (2026-06-09) 📊:
Agents: 🥇 Claude Code 21.5 (50 = match human), $5.3; 🥈 EvoScientist 18.8, $4.1; 🥉 Codex CLI 18.4, just $2.0
LLMs+Harness: 🥇 Claude-Opus-4.8 21.1, $4.0; 🥈 Claude-Opus-4.7 20.7; 🥉 MiniMax-M3 19.8, only $0.45; Qwen3.7-Max 18.7, $0.42, 11min 💥
Claude still king, but MiniMax/Qwen/DeepSeek are crazy cheap and competitive. Expensive isn't always better.
📎 Code & star: https://github.com/InternScience/ResearchClawBench
🏠 Website: https://internscience.github.io/ResearchClawBench-Home/
🤗 Upvote paper: ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research (2606.07591)
- 2 replies