grok-4.1-thinking
1,434±3
1,431CI1,437
aiqbench · LLM benchmarks
1,434±3
1,431CI1,437
1,431±3
1,428CI1,434
1,413±3
1,410CI1,416
One grid, every column. Pick axes in the Axes panel — one axis ranks like a single board, several blend into a weighted composite, all of them read as the index. Rank is assigned before any filter and never renumbers.
| Model | Org | ± CI | Swing | Add to compare | |||||
|---|---|---|---|---|---|---|---|---|---|
| 96 | grok-4.1-thinking | xai | Oct 2026 | — | 1,434 | 1,431–1,437 | #71–482 | ||
| 104 | grok-4.1 | xai | Oct 2026 | — | 1,431 | 1,428–1,434 | #83–511 | ||
| 133 | grok-4-1-fast-reasoning | xai | Oct 2026 | — | 1,413 | 1,410–1,416 | #139–464 |
Showing Factuality Arena exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.