512QA campaign — results

Self-contained static site generated by gen-site.sh from telemetry-512qa-multi/runs/*/summary.json. Wall times marked (derived) are reconstructed, not measured. Click a config for its per-domain breakdown — or skip the spreadsheet and read the highlights (pass 1) or independent top 10 (pass 2).

configlanemodelokfailexpectedcompletionwall_smutations ok/totalflags
sol-fast-titaniumsekhmetgpt-5.6-sol5440512106.3%3009s32/32
grok-4.6-lowgrokgrok-4.653616512104.7%~493s (derived)24/40
grok-4.6-highgrokgrok-4.651513512100.6%~848s (derived)6/16
luna-fast-titaniumsekhmetgpt-5.6-luna51232512100%2296s0/32
glm-5.3opencodeopencode-go/glm-5.3507651299%3538s1/1
ox-alpha-freeopencodeopencode-go/ox-alpha-free267727397.8%2367s1/1
ds-pro-0813tpalibaba-token-plan/deepseek-v4-pro-08133978344589.2%3295s0/35
ds-flash-0731tpalibaba-token-plan/deepseek-v4-flash-073144510751286.9%1478s0/40
qwen3.8-max-lowqwen38qwen3.8-max4161551281.3%~908s (derived)0/0 incomplete
grok-4.6-defaultgrokgrok-4.6399151277.9%~735s (derived)0/0 incomplete
hy3-freeopencodeopencode/hy3-free35015850868.9%~241s (derived)0/0
mimo-v2.5-freeopencodeopencode/mimo-v2.5-free29115644765.1%~331s (derived)0/0
x-preview-f-freeopencodeopencode/x-preview-f-free31225612.1%~2035s (derived)1/1 incomplete
muse-spark-1.2-contributor-freeopencodeopencode/muse-spark-1.2-contributor-free3505126.8%~270s (derived)1/1 incomplete
nemotron-3.5-lightning-freeopencodeopencode/nemotron-3.5-lightning-free2734346.2%~776s (derived)1/1 incomplete
nemotron-3-ultra-freeopencodeopencode/nemotron-3-ultra-free3125096.1%~499s (derived)1/1 incomplete
codex-spark-goldensekhmetgpt-5.3-codex-spark05445120%13s0/32quota-stub quota-stub os-error-122