OrchestrationBench — leaderboard
Multi-step workflow orchestration benchmark testing planning, function calling accuracy, and call rejection ability in Korean and English.
Metric: Average Score. Source: github.com. Status: saturation imminent. 17 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 85.07 |
| 2 | Gemini 3 Pro (Preview) | 84.12 |
| 3 | Gemini 3 Flash (Preview) | 83.54 |
| 4 | GLM-4.7 | 83.17 |
| 5 | Gemini 3.1 Pro (Preview) | 82.8 |
| 6 | GPT-5.4 (2026-03-05) | 78.15 |
| 7 | GPT-5.2 | 76.05 |
| 8 | Qwen 3 235B A22B 2507 Instruct | 70.65 |
| 9 | Qwen 3 30B A3B 2507 Instruct | 66.08 |
| 10 | Qwen 2.5 32B Instruct | 66.03 |
Interactive version: theaggregate.ai/benchmark?slug=orchestrationbench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.