Drift-Bench (Service-Oriented, No Clarification) - Premise: leaderboard
Metric: Success rate (%; 150 StableToolBench G1 API tasks with a premise fault (a false assumption), no clarification tools, mean of 3 trials). Source: arxiv.org. Saturation forecast: Around 2030. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GLM-4.7 | 56.65 |
| 2 | Llama 4 Maverick | 54.44 |
| 3 | DeepSeek V3.2 | 47.11 |
| 4 | Qwen 3 235B A22B 2507 Instruct | 46.33 |
| 5 | Gemini 2.5 Flash | 40.44 |
| 6 | GPT-5.2 | 36.78 |
| 7 | GPT-OSS-120B | 34.44 |
Interactive version: theaggregate.ai/benchmark?slug=drift-bench-service-oriented-no-clarification-premise · How It Works · Data refreshed daily, snapshot 2026-09-25.