IndustryBench: leaderboard
In industrial procurement, an LLM answer is useful only if it survives a standards check: recommended material must match operating condition, every parameter must respect a regulated threshold, and no procedure may contradict a safety clause. Partial correctness can mask safety-critical contradictions that aggregate LLM benchmarks rarely capture. We introduce IndustryBench, a 2,049-item benchmark
Metric: Final (SV) (self-reported). Source: benchmarklist.com. Saturation forecast: Around July 2027. 17 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 2.08 | #58 |
| 2 | GPT-5.4 | 2.07 | #79 |
| 3 | Qwen 3.6 Plus | 2.07 | #120 |
| 4 | Claude Opus 4.6 | 2.01 | #63 |
| 5 | Qwen 3.5 Plus | 2 | #125 |
| 6 | Qwen 3.5 397B A17B | 1.99 | #146 |
| 7 | GPT-5.2 | 1.98 | #110 |
| 8 | Qwen 3 Max | 1.97 | #208 |
| 9 | Qwen 3.5 122B A10B | 1.96 | #173 |
| 10 | Kimi K2.5 | 1.93 | #144 |
| 11 | Qwen 3.5 27B | 1.87 | #187 |
| 12 | Claude Sonnet 4.6 | 1.81 | #90 |
| 13 | Qwen 3.5 35B A3B | 1.75 | #256 |
| 14 | Qwen 3 235B A22B | 1.5 | #313 |
| 15 | Qwen 3 32B | 1.39 | #443 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=industrybench · How It Works · Data refreshed daily, snapshot 2026-10-20.