AI BENCHY Category
Data parsing and extraction Ranking
See which AI models perform best on Data parsing and extraction, which ones stay reliable, and where the biggest gaps appear. Sort by: Response Time (avg) ↓.
| Rank | Model | Company | Data parsing and extraction Score | Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #161 | Qwen3.5-9B medium | Qwen | 3.6 | 4.2 | 0/2 | 87.3s |
| #150 | Qwen3 Coder Next medium | Qwen | 6.5 | 4.6 | 1/2 | 81.8s |
| #66 | Qwen3.5-35B-A3B medium | Qwen | 7.3 | 7.1 | 1/2 | 59.3s |
| #49 | Qwen3.5-Flash medium | Qwen | 7.3 | 7.4 | 1/2 | 57.0s |
| #76 | Kimi K2.5 medium | Moonshot AI | 10.0 | 6.8 | 2/2 | 49.8s |
| #25 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 10.0 | 7.9 | 2/2 | 46.9s |
| #96 | Ring-2.6-1T none | Inclusionai | 3.0 | 6.2 | 0/2 | 45.9s |
| #135 | Kimi K2.5 none | Moonshot AI | 7.3 | 5.2 | 1/2 | 42.1s |
| #14 | Qwen3.6 Max Preview medium | Qwen | 10.0 | 8.5 | 2/2 | 41.2s |
| #36 | Qwen3.5 Plus 2026-04-20 medium | Qwen | 10.0 | 7.6 | 2/2 | 38.3s |
| #75 | Ring-2.6-1T medium | Inclusionai | 6.5 | 6.9 | 1/2 | 37.4s |
| #78 | Qwen3.6 27B medium | Qwen | 3.5 | 6.8 | 0/2 | 37.3s |
| #72 | DeepSeek V3.2 medium | DeepSeek | 10.0 | 7.0 | 2/2 | 36.1s |
| #113 | DeepSeek V4 Pro none | DeepSeek | 6.9 | 5.7 | 1/2 | 30.5s |
| #30 | Qwen3.5-27B medium | Qwen | 10.0 | 7.8 | 2/2 | 30.3s |