ComplexFuncBench — leaderboard
ComplexFuncBench evaluates model capability on tool use tasks from the linked upstream source with Score as the primary reported metric.
Metric: Score (self-reported). Source: benchmarklist.com. Status: saturation imminent. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 3.5 Sonnet | 61 |
| 2 | GPT-4o (2024-08-06) | 60.5 |
| 3 | GPT-4 Turbo | 49.5 |
| 4 | Claude 3.5 Haiku | 45.8 |
| 5 | Qwen 2.5 72B Instruct | 40.1 |
| 6 | Mistral Large 2 (Nov) Instruct (2411) | 20.1 |
| 7 | glm-4-9B | 9.4 |
| 8 | Qwen 2.5 7B | 5 |
| 9 | Llama 3.1 405B Instruct | 4 |
| 10 | Llama 3.1 70B | 2.7 |
| 11 | Llama 3.1 8B | 0.1 |
Interactive version: theaggregate.ai/benchmark?slug=complexfuncbench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.