LLM Stats leaderboard
1 observations · 1 standings · first ingest Oct 2, 2026
Source record llm-stats-bixbench · higher is better · declared max 1
Current standings — best observation per subject × instrument
| Subject | Value | Instrument | Protocol | Measured by | Reported | Document |
|---|---|---|---|---|---|---|
| GPT-5.5 | 0.81 | – | – | OpenAI | Apr 23, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/bixbench?top_n=500 |
Full observation history (1 rows, newest first)
| Subject | Value | Reported | Kind | Ingested |
|---|