ComplexFuncBench: leaderboard
1,000 multi-step function-calling tasks over 43 live travel APIs (hotels, flights, attractions, car rental, taxi) with 128k contexts, from Zhipu AI and Tsinghua (2025); success rate, GPT-4o 60.5%.
Metric: Score (self-reported). Source: benchmarklist.com. Status: saturated. 20 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o (2024-11-20) | 66.5 |
| 2 | GPT-4.1 | 65.5 |
| 3 | GPT-4.5 | 63 |
| 4 | Claude 3.5 Sonnet | 61 |
| 5 | GPT-4o (2024-08-06) | 60.5 |
| 6 | GPT-4 Turbo | 49.5 |
| 7 | GPT-4.1 Mini | 49.3 |
| 8 | O1 (High) | 47.6 |
| 9 | Claude 3.5 Haiku | 45.8 |
| 10 | Qwen 2.5 72B | 40.1 |
| 11 | GPT-4o Mini | 38.6 |
| 12 | Mistral Large 2 (Jul) | 20.1 |
| 13 | O3 Mini (High) | 17.6 |
| 14 | Llama 3.1 8B | 10 |
| 15 | glm-4-9B | 9.4 |
Interactive version: theaggregate.ai/benchmark?slug=complexfuncbench · How It Works · Data refreshed daily, snapshot 2026-09-05.