Overview › Compare › qwq:32b vs deepseek-r1:32b
Head-to-head

qwq:32b vs deepseek-r1:32b

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.

ModelRunnable simsBlind text avgFailure modes
qwq:32b 8% (8/95)8.70 (30 scored)ERR 4 · STAT 43 · BLANK 23 · DNF 17
deepseek-r1:32b 25% (24/95)8.77 (30 scored)ERR 42 · STAT 7 · BLANK 19 · HANG 2 · DNF 1

Biggest contrasts

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

Roundqwq:32bdeepseek-r1:32b
R171 · Fireworks bursting into fading sparksOKERR
R161 · Selection sort vs shell sort racing side by sideBLANKOK
R155 · Linked list with animated pointer relinkingDNFOK
R154 · Ring buffer with producer and consumer at different ratesSTATOK
R140 · Water sloshing in a tilting containerDNFOK

→ 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.