SynthAPI Paper - AppWorld Test-N: leaderboard
SynthAPI tests whether models can use unfamiliar APIs and complete tasks with tools, including AppWorld, ASTRA and function calling. Task Goal Completion (%).
Metric: Task Goal Completion (%). Source: arxiv.org. Saturation forecast: Around January 2027. 20 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.5 27B | 81.8 | #186 |
| 2 | Qwen 3.5 4B | 47.5 | #496 |
| 3 | Qwen 3.5 9B | 45.4 | #387 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=synthapi-paper-appworld-test-n · How It Works · Data refreshed daily, snapshot 2026-10-29.