← Benchmark report cards
Ability
Hard prompts
Published by arena.ai (LMArena). Source page ↗ · Data we read ↗
Bradley–Terry ratings from anonymous pairwise votes; style control on.
Facts
| Fact | Value | Where it comes from |
|---|---|---|
| Who runs the evaluation | public votes | curated by aiqbench, reviewed 2026-10-09 |
| Test set exposure | live / refreshed | curated by aiqbench, reviewed 2026-10-09 |
| Data licence | CC-BY-4.0 | the board's attribution record |
| Newest published result | 4 days ago | the ingested rows |
| Last pulled by aiqbench | 11 minutes ago · every 12 h | the sync log |
| Models on this axis | 416 | the ingested rows |
| Rows with a published interval | every row | the ingested rows |
| Headroom at the top | Best 1,549; top 10 within 31. | computed from the ingested rows |
| Axes it tracks closely |
| Spearman ρ over shared models (see Clusters) |
Where it appears
Weighted in the built-in templates: Reasoning ×1.
View this axis alone in the console →Attribution
Source: LMArena / arena.ai Leaderboard Dataset (lmarena-ai/leaderboard-dataset) on Hugging Face — https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset. Licensed under CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Modified by aiqbench: normalised into aiqbench's common board format; we ingest the latest snapshot of the 'text_style_control' config.