FirmCORe - Opportunity Detection: leaderboard
Detect whether two Chinese firms have a collaboration opportunity from their profiles, over 3,230 firms in 1,114 industries. Macro-F1, higher is better. Source: arxiv.org/abs/2609.17128.
Metric: Macro-F1 (%). Source: arxiv.org. Saturation forecast: Around February 2027. 17 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.6 27B | 74.51 | #182 |
| 2 | Qwen 3.6 Max | 70.23 | #97 |
| 3 | Qwen 3.7 Plus | 69.64 | #98 |
| 4 | Qwen3 Coder | 56.48 | #304 |
| 5 | Qwen 3.6 35B A3B | 56.04 | #238 |
| 6 | GLM-5.2 | 53.78 | #80 |
| 7 | Qwen 3 8B | 51.42 | #678 |
| 8 | Gemma 4 26B | 50.82 | #322 |
| 9 | GLM-5.1 | 43.22 | #109 |
| 10 | Llama 3.1 8B | 36.5 | #1130 |
| 11 | Qwen 3 4B | 34.48 | #834 |
| 12 | Gemma 3 12B | 32.22 | #674 |
| 13 | Llama 3.2 3B | 25.77 | #1376 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=firmcore-opportunity-detection · How It Works · Data refreshed daily, snapshot 2026-11-05.