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.
| Model | Runnable sims | Blind text avg | Failure modes |
|---|---|---|---|
| deepseek-r1:14b | 14% (12/85) | 8.09 (32 scored) | ERR 55 · STAT 4 · BLANK 10 · HANG 1 · DNF 3 |
| GPT-5.5 (Codex) frontier reference | 95% (81/85) | unscored by design | ERR 2 · STAT 1 · BLANK 1 |
Biggest contrasts
Rounds where the two models diverged most — open them and read both answers side by side.
| Round | deepseek-r1:14b | GPT-5.5 (Codex) |
|---|---|---|
| R155 · Linked list with animated pointer relinking | BLANK | OK |
| R151 · Binary search tree growing node by node | ERR | OK |
| R140 · Water sloshing in a tilting container | ERR | OK |
| R137 · Cloth mesh hanging and rippling in the wind | ERR | OK |
| R136 · Double pendulum tracing a chaotic path | ERR | OK |
→ 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.