A childhood game idea prototyped "with Opus 5.5 and Grok 4.7" in three.js
x.com · link re-checked 2026-10-16
By SpaceXAI. 6 results on 6 boards, copied as published. Different boards, different metrics: don't add them up.
Grok 4.5 · % resolved · board #13
Mini-SWE-agent · as of 2026-09-01 Stale ↗
Grok 4.5 [high] · Resolved rate % · board #2
SWE-rebench harness (agent rows are full products) · as of 2026-07-01 Stale ↗
Grok 4.5 · Accuracy % · board #15
Vals AI implementation (no agent) · as of 2026-09-01 Stale ↗
Grok 4.5 (high) · Resolution rate
Grok Build · as of 2026-07-16 Stale ↗
No result on the boards we captured
No result on the boards we captured
No mature public leaderboard
No sourced use case names this exact model version.
x.com · link re-checked 2026-10-16
x.com · link re-checked 2026-10-16
x.com · link re-checked 2026-10-16
x.com · link re-checked 2026-10-16
x.com · link re-checked 2026-10-16
x.com · link re-checked 2026-10-16
lmarena.ai/leaderboard/webdev vals.ai/benchmarks/swebench swe-rebench.com tbench.ai/leaderboard vals.ai/benchmarks/vibe-code vals.ai/benchmarks/lcb
What changed in AI coding plans: prices, limits, resets. Email signups open soon. Until then, updates go out on X.