Primary sourceavailable
Claude Opus 5.5 System Card ↗
2026-09-22 (day) · retrieved 2026-09-26
original_bytes: 7311c9c6bbb16d012f1c12c7418b05949fcf7ae3e30d2c40f22050074b2a7378Provenance
Sources
The public documents behind every record.
20 source records·8 publishers·Primary sources are preferred.
Anthropic
Primary sourceavailable
Measurements for understanding the pace of AI development inside frontier labs ↗
2026-09-17 (day) · retrieved 2026-09-26
OpenAI
Primary sourceavailable
GPT-6 Astra System Card ↗
2026-09-03 (day) · retrieved 2026-09-26
original_bytes: bb824295442992a152dd4596b5f615697b194e79c794a9a4c1dd6170279ee20fPrimary sourceavailable
PaperBench: Evaluating AI’s Ability to Replicate AI Research (v1) ↗
2025-04-02 (day) · retrieved 2026-09-26
original_bytes: 1704aec76a9740f8f4af9e47a9008d79aaddc17a0e16f72d3eccc39db568d27dPrimary sourceavailable
MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering (v1) ↗
2024-10-09 (day) · retrieved 2026-09-26
original_bytes: ecfe27c79181a88c1358822316198b4e085441c2e26379b3c6ef49312918bf7dGoogle DeepMind
Primary sourceavailable
Gemini 3.7 Flash Frontier Safety Framework Report ↗
2026-08 (month) · retrieved 2026-09-26
original_bytes: f0eec853b7371aac56d3ef3e21f2e0f52e3ca7eb60db5119ee5b4234f66d522cPrimary sourceavailable
Gemini 3 Pro Frontier Safety Framework Report, v2 ↗
2025-11 (month) · retrieved 2026-09-26
Primary sourceavailable
AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms ↗
2025-05-14 (day) · retrieved 2026-09-26
Primary sourceavailable
Gemini 3.1 Pro Model Card ↗
2026-02-19 (day) · retrieved 2026-09-27
original_bytes: 70bcda79a248255d2c858600cb1fecae9ea30278c942684754df0bca71ca8315AI4AI-Bench authors
Primary sourceavailable
AI4AI-Bench: Benchmarking LLM Agents in Algorithmic Design for Recursive Self-Improvement ↗
2026-08-20 (day) · retrieved 2026-09-26
original_bytes: 60938176890f24ede8eb7040c02b4e8f8b3666c38977af3d5c863123f5a2024cMETR
Primary sourceavailable
Time Horizon 1.1 ↗
2026-01-29 (day) · retrieved 2026-09-26
original_bytes: 4c76602bcdc168fa395218ec0bd0e893796852092e47e84503107e0df86d3b9dPrimary sourceavailable
Evaluating frontier AI R&D capabilities of language model agents against human experts ↗
2024-11-22 (day) · retrieved 2026-09-26
Primary sourceavailable
Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity ↗
2025-07-10 (day) · retrieved 2026-09-26
Primary sourceavailable
We are Changing our Developer Productivity Experiment Design ↗
2026-02-24 (day) · retrieved 2026-09-26
Primary sourceavailable
Recent Frontier Models Are Reward Hacking ↗
2025-06-05 (day) · retrieved 2026-09-26
Primary sourceavailable
Summary of METR's predeployment evaluation of GPT-5.6 Sol ↗
2026-06-26 (day) · retrieved 2026-09-27
original_bytes: 232140ff97a4f324e2b1bdd918d243be6f0a16ddc999ca0e3d90d7b6ece002bfDarwin Gödel Machine authors
Primary sourceavailable
Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents (v1) ↗
2025-05-29 (day) · retrieved 2026-09-26
original_bytes: effea2116602683c69b5807823778af3814987cb187ae93bc6ea31f2ccc7d07bDuan et al.
Primary sourceavailable
The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement, supplied v1 ↗
2026-09-10 (day) · retrieved 2026-09-26
original_bytes: 9fde92cba4d50a38a42570c25b89fe116312f746659e560290d344ead91f7a9bWeco AI
Primary sourceavailable
Recursive self-improvement of AI research agents, AIDE² v1 ↗
2026-09-22 (day) · retrieved 2026-09-26
original_bytes: 823660bd50c747408b7c3249497efee2f5faccc558d16b31ee2c61baf5b5e400Primary sourceavailable
Weco: 4 Levels of Recursive Self-Improvement (alternative taxonomy) ↗
2026-07-10 (day) · retrieved 2026-09-26