OverviewCompare › command-r:35b vs GPT-5.5 (Codex)
Head-to-head

command-r:35b 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
command-r:35b 26% (22/85)7.25 (20 scored)ERR 29 · STAT 10 · BLANK 8 · HANG 3 · DNF 13
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.

Roundcommand-r:35bGPT-5.5 (Codex)
R155 · Linked list with animated pointer relinkingDNFOK
R154 · Ring buffer with producer and consumer at different ratesDNFOK
R151 · Binary search tree growing node by nodeDNFOK
R140 · Water sloshing in a tilting containerDNFOK
R138 · Two-source wave interference patternDNFOK

→ 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.