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) |
|---|---|---|---|---|---|---|
| #97 | Qwen3.5-9B medium | Qwen | 3.6 | 4.4 | 0/2 | 87.3s |
| #92 | Qwen3 Coder Next medium | Qwen | 6.5 | 4.7 | 1/2 | 81.8s |
| #43 | Qwen3.5-35B-A3B medium | Qwen | 7.3 | 7.4 | 1/2 | 59.3s |
| #32 | Qwen3.5-Flash medium | Qwen | 7.3 | 7.8 | 1/2 | 57.0s |
| #46 | Kimi K2.5 medium | Moonshot AI | 10.0 | 7.0 | 2/2 | 49.8s |
| #8 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 10.0 | 8.5 | 2/2 | 46.9s |
| #76 | Kimi K2.5 none | Moonshot AI | 7.3 | 5.5 | 1/2 | 42.1s |
| #27 | DeepSeek V3.2 medium | DeepSeek | 10.0 | 8.0 | 2/2 | 36.1s |
| #10 | Qwen3.5-27B medium | Qwen | 10.0 | 8.4 | 2/2 | 30.3s |
| #39 | Seed-2.0-Mini medium | Bytedance Seed | 10.0 | 7.5 | 2/2 | 24.3s |
| #19 | Qwen3.5-122B-A10B medium | Qwen | 10.0 | 8.1 | 2/2 | 23.4s |
| #50 | Hunter Alpha medium | OpenRouter | 10.0 | 6.7 | 2/2 | 23.2s |
| #80 | MiniMax M2.7 medium | Minimax | 6.3 | 5.3 | 1/2 | 21.9s |
| #57 | GPT-5 Nano medium | OpenAI | 3.7 | 6.3 | 0/2 | 21.4s |
| #14 | Gemma 4 31B medium | 10.0 | 8.3 | 2/2 | 21.1s |