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: Metric ↑.
| Rank | Model | Company | Data parsing and extraction Score | Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #94 | MiMo-V2-Flash none | Xiaomi | 2.9 | 4.5 | 0/2 | 19.7s |
| #98 | LFM2-24B-A2B none | Liquid | 3.0 | 4.1 | 0/2 | 714ms |
| #97 | Qwen3.5-9B medium | Qwen | 3.6 | 4.4 | 0/2 | 87.3s |
| #57 | GPT-5 Nano medium | OpenAI | 3.7 | 6.3 | 0/2 | 21.4s |
| #71 | MiniMax M2.5 medium | Minimax | 4.6 | 5.7 | 0/2 | 7.48s |
| #93 | GLM 4.7 Flash medium | Z.ai | 6.3 | 4.6 | 1/2 | 1.51s |
| #64 | DeepSeek V3.2 none | DeepSeek | 6.3 | 6.1 | 1/2 | 9.42s |
| #80 | MiniMax M2.7 medium | Minimax | 6.3 | 5.3 | 1/2 | 21.9s |
| #68 | gpt-oss-120b medium | OpenAI | 6.4 | 5.8 | 1/2 | 1.98s |
| #81 | Elephant medium | Openrouter | 6.5 | 5.2 | 1/2 | 979ms |
| #85 | Elephant none | Openrouter | 6.5 | 5.2 | 1/2 | 1.04s |
| #87 | Qwen3 Coder Next none | Qwen | 6.5 | 5.1 | 1/2 | 1.32s |
| #92 | Qwen3 Coder Next medium | Qwen | 6.5 | 4.7 | 1/2 | 81.8s |
| #96 | GPT-5.4 Nano none | OpenAI | 6.5 | 4.5 | 1/2 | 1.11s |
| #41 | MiMo-V2-Flash medium | Xiaomi | 6.5 | 7.5 | 1/2 | 0ms |