xAI·released 2025-09-191 source
Grok 4 Fast 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 94.4 on Fiction.LiveBench (unverified)·0 of 6 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| Fiction.LiveBench | 94.4accuracy (%) | unverifiedT1 | 2025-09-19Fiction.live leaderboard |
| DTBench | 71.12accuracy (%) | unverifiedT1 | 2025-09-19https://conceptualreasoning.ai/dtbench |
| ARC-AGI | 48.5accuracy (%) | unverified· optimizedT2 | 2025-09-19 |
| WeirdML | 42.86accuracy (%) | unverifiedT1 | 2025-09-19https://htihle.github.io/weirdml.html |
| Cybench | 30accuracy (%) | self-reported· optimizedT1 | 2025-09-19Grok 4 Fast Model Card |
| ARC-AGI-2 | 5.28accuracy (%) | unverifiedT2 | 2025-09-19 |
Claims drawn from cited facts, not live model generation.
This model was developed by xAI and released in 2025. That makes it a current-generation release whose identity rests on its origin and vintage, since no parameter count is disclosed to put a scale on it.
4 cited facts
This model is scored on 6 tracked benchmarks, and it holds no current top score on any of them. Its record is self-reported: the numbers are vendor claims that have not yet been independently confirmed, so they should be read as claims rather than verified results.
3 cited facts
With an average SOTA gap of 46.96 points, this model sits well behind the leaders — a wide gap that reads as clearly not at the frontier. It holds the top score on 0 benchmarks, meaning it has no category leadership yet.
2 cited facts
1 facts cross-checked across data sources: 1 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: epoch_benchmarks
Grok 4 Fast is an AI model developed by xAI, released 2025-09-19. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Grok 4 Fast has recorded scores on 6 benchmarks, each shown with its evidence status.
Grok 4 Fast has recorded scores on 6 benchmarks — DTBench, WeirdML, Cybench, ARC-AGI, Fiction.LiveBench, ARC-AGI-2. 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.
Grok 4 Fast has 6 tracked claims: 1 self-reported, 5 unverified.