PluginEval - Over-Recall: leaderboard
Over-recall on the 500 adversarial negative queries of PluginEval (2026), a Chinese function-calling benchmark: the share of queries that need no tool on which the model still calls one. Percent; lower is better.
Metric: Over-recall rate (%; share of the 500 adversarial negative queries on which the model wrongly calls a tool; lower is better; 3,000 human-verified Chinese function-calling queries over 54 plugins and 63 tools with real API execution (2,500 positive queries requiring grounded calls, 500 adversarial negatives requiring abstention; easy/medium/hard 0.4/0.4/0.2); GPT-5.2 judge anchored to gold annotations). Source: arxiv.org. Saturation forecast: Around February 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 18.55 | #94 |
| 2 | Qwen 3 235B A22B | 24.22 | #623 |
| 3 | DeepSeek V4 Pro | 28.91 | #188 |
| 4 | Claude Opus 4.6 | 29.1 | #102 |
| 5 | GPT-5.4 | 33.2 | #123 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=plugineval-over-recall · How It Works · Data refreshed daily, snapshot 2026-11-13.