OverviewCompare › deepseek-r1:32b vs GPT-5.5 (Codex)
Head-to-head

deepseek-r1:32b 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-r1:32b 27% (23/85)8.90 (20 scored)ERR 34 · STAT 7 · BLANK 19 · HANG 1 · DNF 1
GPT-5.5 (Codex) frontier reference 95% (81/85)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-r1:32bGPT-5.5 (Codex)
R152 · Hash table with visible collision chainsBLANKOK
R151 · Binary search tree growing node by nodeERROK
R137 · Cloth mesh hanging and rippling in the windBLANKOK
R130 · Radix sort ordering by one digit at a timeERROK
R129 · Heap sort sifting the maximum to the backSTATOK

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

Generated 2026-07-31 from the published rounds. Harness failures are excluded from every base — a broken cluster node is our fault, not the model's.