Grok 4.1 Fast (Non-reasoning): benchmark results
Grok 4.1 Fast evaluated with reasoning disabled. Provider: xAI. Released 2025-11-19. Access: API.
Aggregate Rating 1533 ± 10, rank #945 of 2168 rated models, from 193 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SourceBench - Argumentative | 90.35 | Weighted source-quality score on a 20 to 100 scale: every we | 100 |
| SpeechMap Compliance | 97.9 | % Requests Completed | 98.5 |
| Horangi 4 - Korean Hate Speech | 70 | Accuracy (%) | 94.7 |
| SourceBench | 83.38 | Weighted source-quality score on a 20 to 100 scale: every we | 85.7 |
| SourceBench - Shopping | 84.49 | Weighted source-quality score on a 20 to 100 scale: every we | 85.7 |
| UGI Leaderboard | 47.46 | UGI Score | 83.9 |
| ShatterMed-QA (Chinese, Hard) | 96.33 | Accuracy (%) on the 327 Chinese Hard multiple-choice clinica | 82.5 |
| ShatterMed-QA (English, Hard) | 96.1 | Accuracy (%) on the 1,692 English Hard multiple-choice clini | 80 |
| UGI - Writing | 41.88 | Writing Score | 77.5 |
| UGI - Natural Intelligence | 31.39 | NatInt Score | 75.5 |
| ShatterMed-QA (Chinese, Easy) | 97.63 | Accuracy (%) on the 2,616 Chinese Easy multiple-choice clini | 75 |
| AA Omniscience - Software Engineering (SWE) - R | 16 | Accuracy (%) | 72.5 |
Interactive version: theaggregate.ai/model?slug=grok-4-1-fast-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-10-20.