llama3.1:8b vs GPT-5.5 (Codex)

Both models answered the same one-shot tasks under identical rules — no retries, answers published unedited. Two separate axes, never blended: does the code actually run, and how do blind-scored text answers hold up against a written gold answer. Frontier references sit outside the blind field and are deliberately unscored on text.

Model	Runnable sims	Blind text avg	Failure modes
llama3.1:8b	13% (12/95)	6.66 (38 scored)	ERR 47 · STAT 19 · BLANK 9 · HANG 3 · DNF 5
GPT-5.5 (Codex) frontier reference	96% (91/95)	unscored by design	ERR 2 · STAT 1 · BLANK 1

Biggest contrasts

Rounds where the two models diverged most — open them and read both answers side by side.

Round	llama3.1:8b	GPT-5.5 (Codex)
R174 · Recursive fractal tree growing branch by branch	STAT	OK
R173 · Metaball lava lamp with heating and cooling blobs	ERR	OK
R172 · Raindrops sliding down a window pane	STAT	OK
R171 · Fireworks bursting into fading sparks	ERR	OK
R165 · Recursive backtracker carving a maze, then solving it	ERR	OK

→ Interactive round-by-round comparison · → Full leaderboard

Generated 2026-08-04 from the published rounds. Harness failures are excluded from every base — a broken cluster node is our fault, not the model's.