Overview › Compare › qwen3:14b vs GPT-5.5 (Codex)
Head-to-head

qwen3:14b 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.

ModelRunnable simsBlind text avgFailure modes
qwen3:14b 31% (29/95)8.73 (48 scored)ERR 42 · STAT 10 · BLANK 13 · HANG 1
GPT-5.5 (Codex) frontier reference 96% (91/95)unscored by designERR 2 · STAT 1 · BLANK 1

Biggest contrasts

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

Roundqwen3:14bGPT-5.5 (Codex)
R173 · Metaball lava lamp with heating and cooling blobsBLANKOK
R171 · Fireworks bursting into fading sparksERROK
R165 · Recursive backtracker carving a maze, then solving itERROK
R162 · Breadth-first search flooding a random grid mazeERROK
R161 · Selection sort vs shell sort racing side by sideHANGOK

→ 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.