released 2025-03-051 source
QwQ-32B benchmark scores: 6 benchmarks tracked. 0% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 6 benchmarks·best result 83.3 on Fiction.LiveBench (unverified)·0 of 6 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| Fiction.LiveBench | 83.3accuracy (%) | unverifiedT1 | 2025-03-05Fiction.live leaderboard |
| Lech Mazur Writing | 80.2accuracy (%) | unverifiedT1 | 2025-03-05lechmazur/writing Github repository |
| OTIS Mock AIME 2024-2025 | 59.13accuracy (%) | unverifiedT2 | 2025-03-05 |
| GPQA diamond | 53.79accuracy (%) | unverifiedT2 | 2025-03-05 |
| Aider polyglot | 20.9accuracy (%) | unverifiedT1 | 2025-03-05https://aider.chat/docs/leaderboards/ |
| Chess Puzzles | 0.04accuracy (%) | unverifiedT2 | 2025-03-05 |
Claims drawn from cited facts, not live model generation.
This model dates from 2025, placing its vintage squarely in the current release cycle rather than an earlier generation. Because no parameter count is offered for this model, its scale cannot be quantified here, so any claim about efficiency, cost, or headroom would be unsupported.
1 cited fact
This model is scored on 6 tracked benchmarks, but it holds no current top score. Its record is unverified — no outside evaluation has either confirmed or disputed the reported numbers, so they should be read with that uncertainty in mind.
3 cited facts
Its mean gap to the best recorded score across its tracked benchmarks is 40.28 points.
1 cited fact
1 facts cross-checked across data sources: 1 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: epoch_benchmarks
QwQ-32B is an AI model released 2025-03-05. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
QwQ-32B has recorded scores on 6 benchmarks, each shown with its evidence status.
QwQ-32B has recorded scores on 6 benchmarks — Lech Mazur Writing, GPQA diamond, OTIS Mock AIME 2024-2025, Chess Puzzles, Aider polyglot, Fiction.LiveBench. The full table above shows each score with its evidence status.
0 of 6 recorded scores (0%) are independently reproduced rather than self-reported by the lab.
QwQ-32B has 6 tracked claims: 6 unverified.