LLM Stats (Terminal-Bench-Science 0.1): leaderboard
Metric: Score (%). Source: llm-stats.com. Saturation forecast: Around January 2028. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-6 | 64.6 |
| 2 | Claude Sonnet 5.5 | 59.9 |
| 3 | Claude Opus 5.5 | 58.7 |
| 4 | Claude Fable 5.1 | 52.6 |
Interactive version: theaggregate.ai/benchmark?slug=llm-stats-terminal-bench-science-0-1 · How It Works · Data refreshed daily, snapshot 2026-09-30.