qwen3.5:9b vs Claude Sonnet 5

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
qwen3.5:9b	37% (35/95)	9.06 (48 scored)	ERR 30 · STAT 12 · BLANK 17 · HANG 1
Claude Sonnet 5 frontier reference	100% (95/95)	unscored by design	—

Biggest contrasts

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

Round	qwen3.5:9b	Claude Sonnet 5
R175 · Noise flowfield painting additive particle trails	ERR	OK
R173 · Metaball lava lamp with heating and cooling blobs	BLANK	OK
R172 · Raindrops sliding down a window pane	ERR	OK
R171 · Fireworks bursting into fading sparks	ERR	OK
R165 · Recursive backtracker carving a maze, then solving it	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.