LiveAgentBench (No Tools): leaderboard
Metric: Share of the 374 LiveAgentBench tasks solved (%), pass@1, string-matched against closed answers, by LLMs prompted zero-shot with no tools; tasks whose attachments or media a model cannot take in count as failed; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 16.85 | #145 |
| 2 | DeepSeek R1 | 9.89 | #245 |
| 3 | GPT-4o | 9.09 | #333 |
| 4 | Claude 3.5 Sonnet | 8.28 | #337 |
| 5 | Qwen 3 235B A22B | 7.75 | #304 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=liveagentbench-no-tools · How It Works · Data refreshed daily, snapshot 2026-10-11.