ToolSandbox leaderboard
As of November 5, 2026, among the results listed here, LiquidAI LFM2.5-24B-A2B has the highest reported ToolSandbox score, 80.7, published by Liquid, ahead of LiquidAI LFM2.5-2.6B at 77.8. 2 models have a ToolSandbox result in our records.
Scores as the model makers published them, not re-run by us; each row links to its announcement.
2 models ranked · 1 maker
| Rank | Model | Score | Setting | Reported by | Date |
|---|---|---|---|---|---|
| 1 | LFM2.5-24B-A2B | 80.7 | Not published | Liquid | October 13, 2026 (model release) |
| 2 | LFM2.5-2.6B | 77.8 | 2.6B | Liquid | August 11, 2026 (model release) |
How much to trust these numbers
- Source
- Reported by the model makers themselves. Not re-run by LLMBenchmark or anyone independent.
- Settings
- Settings differ between makers. Check the Setting column before comparing two scores.
- Spread
- 80.7 to 77.8 across 2 models.
- Freshness
- Newest result published October 13, 2026; oldest August 11, 2026.
What ToolSandbox measures
ToolSandbox tests models’ tool use in conversations where actions depend on changing state, with scores indicating tool-use capability. Source: ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities