WildAgtEval: leaderboard
Agent API-use benchmark measuring robustness to real-world API complexity across multi-turn conversations, API functions, and injected complexity scenarios.
Metric: Complexity-Injected API Call Accuracy (imported). Source: github.com. Source: benchmarklist.com. Saturation forecast: Around December 2026. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4 (Thinking) | 67.5 | #199 (Claude Sonnet 4) |
| 2 | Claude Sonnet 4 | 63.6 | #199 |
| 3 | Qwen 3 235B A22B (Thinking) | 62.6 | #313 (Qwen 3 235B A22B) |
| 4 | GPT-OSS-120B | 62.5 | #341 |
| 5 | Claude 3.7 Sonnet | 61.6 | #249 |
| 6 | Claude 3.5 Sonnet | 55.8 | #350 |
| 7 | Qwen 3 32B | 49.9 | #443 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=wildagteval · How It Works · Data refreshed daily, snapshot 2026-10-20.