IndustryBench - Quality and Metrology: leaderboard

IndustryBench (2026) restricted to its 93 Quality and Metrology questions (testing methods, quality metrics and measurement standards), Chinese industrial procurement QA 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 93 items of the 2,049 Chinese industrial procurement QA items of IndustryBench grounded in Chinese national standards (GB/T) in the Quality and Metrology capability dimension (testing methods, quality metrics and measurement standards; default non-reasoning runs); higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 17 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1Gemini 3.1 Pro (Preview)2.26#102
2Kimi K2.5Non-reasoning2.22#272
3GPT-5.4Non-reasoning2.16#138
4Qwen 3.6 PlusNon-reasoning2.16#245
5Qwen 3.5 397B A17BNon-reasoning2.15#270
6Qwen 3.5 122B A10BNon-reasoning2.15#350
7Qwen 3 MaxNon-reasoning2.15#420
8Qwen 3.5 27BNon-reasoning2.13#380
9Claude Opus 4.62.1#114
10GPT-5.2Non-reasoning2.08#190
11Qwen 3.5 PlusNon-reasoning2.07#250
12Qwen 3.5 35B A3BNon-reasoning2.05#494
13GLM-5Non-reasoning2.04#276
14Claude Sonnet 4.62.04#179
15MiniMax-M2.51.87#600

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=industrybench-quality-and-metrology · How It Works · Data refreshed daily, snapshot 2026-11-22.