IndustryBench - Vietnamese: leaderboard
IndustryBench (2026) on its Vietnamese rendering of the 2,049 Chinese industrial procurement questions grounded in national standards, answered closed-book in default non-reasoning mode and scored 0 to 3 by a Qwen3-Max judge, with answers that violate a safety clause set to 0. Mean score out of 3; higher is better.
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 Vietnamese 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 February 2027. 8 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Qwen 3.6 Plus | Non-reasoning | 2.16 | #238 |
| 2 | Gemini 3.1 Pro (Preview) | 2.13 | #99 | |
| 3 | GPT-5.4 | Non-reasoning | 2.1 | #135 |
| 4 | Qwen 3.5 397B A17B | Non-reasoning | 2.1 | #264 |
| 5 | Qwen 3.5 Plus | Non-reasoning | 2.09 | #242 |
| 6 | Claude Opus 4.6 | 2.08 | #113 | |
| 7 | Qwen 3.5 27B | Non-reasoning | 1.93 | #375 |
| 8 | Qwen 3.5 35B A3B | Non-reasoning | 1.92 | #492 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=industrybench-vietnamese · How It Works · Data refreshed daily, snapshot 2026-11-21.