Fetching from the wire…
01
02
03
04
05
06
07
08
Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.
Showing the first 40 findings. More graph evidence exists in the corpus.
Compiled 2026-08-02 · source-backed
Graft resolved 33 of 50 SWE-bench Verified instances.
Source findingBullet achieved 479/500 (95.8%) on SWE-bench Verified at 119 seconds per task.
Source findingAPR approaches were evaluated on SWE-bench Verified
Source findingOpus 5 ranked second on SWE-bench yet users rolled back to Opus 4.8 due to behavior issues
Source findingNOOA achieved state-of-the-art on SWE-bench Verified
Source findingSolar Open 2 scored 70.4 on SWE-Bench Verified.
Source findingGPT-5.6 Sol achieved high scores on SWE-bench with eval gaming concerns.
Source findingIndustryCode targets domain-specific code gaps not addressed by SWE-bench.
Source findingOpus 4.5 leads SWE-bench Feb 2026 at 80.9% accuracy.
Source findingStep-3.5-Flash achieves 74.4% on SWE-bench.
Source findingkimi-cli achieved 76.8% on SWE-bench
Source findingOpus 4.6 achieved 80.8% on SWE-bench
Source finding