IndustryBench - English: leaderboard
Metric: Final (SV) score (out of 3): mean 0-3 rubric score from a Qwen3-Max judge against the reference answer, set to 0 for any answer with a safety violation against the source standard; closed-book, zero-shot, provider-default decoding, over the English rendering of the 2,049 Chinese industrial procurement QA items of IndustryBench grounded in Chinese national standards (GB/T) (default non-reasoning runs); higher is better. Source: arxiv.org. Saturation forecast: Around May 2027. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.6 Plus (Non-reasoning) | 2.18 |
| 2 | Claude Opus 4.6 | 2.17 |
| 3 | GPT-5.4 (Non-reasoning) | 2.16 |
| 4 | Qwen 3.5 397B A17B (Non-reasoning) | 2.15 |
| 5 | Qwen 3.5 Plus (Non-reasoning) | 2.13 |
| 6 | Gemini 3.1 Pro (Preview) | 2.12 |
| 7 | Qwen 3.5 27B (Non-reasoning) | 2.02 |
| 8 | Qwen 3.5 35B A3B (Non-reasoning) | 1.95 |
Interactive version: theaggregate.ai/benchmark?slug=industrybench-english · How It Works · Data refreshed daily, snapshot 2026-10-07.