Overview › Compare › deepseek-r1:14b vs GPT-5.5 (Codex)
Head-to-head

deepseek-r1:14b 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
deepseek-r1:14b 14% (13/95)7.55 (42 scored)ERR 61 · STAT 5 · BLANK 12 · HANG 1 · DNF 3
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.

Rounddeepseek-r1:14bGPT-5.5 (Codex)
R175 · Noise flowfield painting additive particle trailsERROK
R174 · Recursive fractal tree growing branch by branchERROK
R173 · Metaball lava lamp with heating and cooling blobsBLANKOK
R172 · Raindrops sliding down a window paneERROK
R165 · Recursive backtracker carving a maze, then solving itBLANKOK

→ 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.