llama3.1:8b vs mistral-small:24b

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.

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
mistral-small:24b	32% (30/95)	8.26 (38 scored)	ERR 29 · STAT 12 · BLANK 9 · HANG 7 · DNF 8

Biggest contrasts

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

Round	llama3.1:8b	mistral-small:24b
R175 · Noise flowfield painting additive particle trails	OK	STAT
R172 · Raindrops sliding down a window pane	STAT	OK
R164 · Boids flocking with separation, alignment, cohesion and a predator	ERR	OK
R155 · Linked list with animated pointer relinking	ERR	OK
R154 · Ring buffer with producer and consumer at different rates	STAT	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.