10 sources filed · EN 5 · RU 2 · ZH 3
Code test on DeepSeek-V4-Flash-Base: completing an FP8 function where the answer is 8, the model sometimes said 32.
40.2 pplargest retrieval-accuracy gap across positions for DeepSeek-V4-Flash-Base in a 128K-token test
RoboDojo: 42 dual-arm tasks across five dimensions (generalisation, precise manipulation, long-horizon, memory, open-vocabulary instructions).
32.26%VPP2 average success rate on the RoboDojo simulation leaderboard, vs 22.48% for GPT-6-Astra
Skills chosen by GitHub stars on 28 September 2026, from superpowers (292,189) to compound-engineering (25,299); domain skills, memory systems and orchestrators excluded.
2 of 9popular Claude Code skills that beat a length-matched placebo, both on cost only (12% and 5% cheaper)
Each agent received 3,000 GPU-hours on up to 50 GPUs and a 10 billion-token inference budget, in a sandbox without internet access, with a codebase scrubbed of SDPO.
35%share of the human method's gains reached by the best uncontaminated model (GPT-5.6 Sol), scored generously; 15% when only in-scope changes count
A single human playthrough takes about 2-4 hours; a high score means completing up to 21 objectives within limited turns.
100%GPT-6 Astra score on the original EBR-bench, reached in over half its attempts via one card
Prompt: a three.js (pnpm) visualization of the book's 55 cities; no questions allowed; 6 hours of work.
1 h 25 min, ~$74Claude Opus 5.5 run time and API cost, with 6 parallel subagents
Agents use two tools: search (query to documents) and fetch (URL to page text).
>80%share of GPT-5.6 Luna's search queries that use quotation marks in Artificial Analysis runs
2,611 production interview recordings scored in 14 batches between 26 March and 24 August 2026 on a nine-family rubric (structure, interruptions, latency, pacing, coherence, audio-visual sync, freezes, audio quality, outcome).
0.79 SDseverity gap between two reviewers scoring the same batches on the composite index
On 447 tasks, Claude Code and mini-SWE-agent differ by -1.8 points (Qwen3.6-35B-A3B) and -1.4 points (Qwen3.8-27B), equivalent within a 5-point margin.
13%median share of hard tasks whose outcome flips, both when swapping the harness and when rerunning the same one
In DeepSeek-V4-Flash-Base, a code completion flips between the correct "8" and the wrong "32" with a period of four tokens as filler text is lengthened, matching the compression stride of 4.
40.2 pplargest gap in 128K-context retrieval accuracy across token phases in DeepSeek-V4 base models
1 source filed · EN 1
Claude Opus 4.7 ranks first on average (0.739) and best-of-three (0.790); GPT-5.5, GLM-5.2 and Gemini-3.1-Pro form a second tier within 0.029 of each other on average.
3 of 252best-seed solutions judged methodologically novel
1 source filed · EN 1
Generative AI reached 53% population adoption within three years, faster than the PC or the internet; organizational adoption reached 88%.
88%organizational adoption of AI in 2025