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: Tests Correct ↑.
359/359
Filter models
No models match the current search and filters.
| Rank | Model | Company | Data parsing and extraction Score | Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #231 | Trinity Large Thinking low | Arcee AI | 7.3 | 6.0 | $0.625 | 1/2 | 14.3s |
| #242 | Hy3 preview high | Tencent | 6.5 | 5.9 | $0.135 | 1/2 | 12.1s |
| #243 | GLM 5.3 Flash low | Z.ai | 6.5 | 5.9 | $0.030 | 1/2 | 2.39s |
| #245 | Seed 2.1 Turbo none | Bytedance Seed | 7.1 | 5.9 | $0.092 | 1/2 | 2.63s |
| #257 | KAT-Coder-Air V2.5 high | Kwaipilot | 6.5 | 5.6 | $0.077 | 1/2 | 3.59s |
| #260 | GPT-6 Luna none | OpenAI | 7.3 | 5.6 | $0.012 | 1/2 | 9.34s |
| #264 | KAT-Coder-Air V2.5 medium | Kwaipilot | 6.5 | 5.6 | $0.048 | 1/2 | 3.65s |
| #265 | Nemotron 3.5 Lightning high | NVIDIA | 7.3 | 5.6 | $0.133 | 1/2 | 14.0s |
| #266 | Hy4 preview low | Tencent | 8.7 | 5.6 | $1.745 | 1/2 | 88.5s |
| #267 | Qwen3.6 27B none | Qwen | 7.3 | 5.5 | $0.075 | 1/2 | 2.06s |
| #268 | Hy3 preview low | Tencent | 6.5 | 5.5 | $0.042 | 1/2 | 5.85s |
| #269 | Qwen3.8 27B none | Qwen | 6.5 | 5.5 | ~$0.006 | 1/2 | 1.14s |
| #273 | DeepSeek V4.1 Flash none | DeepSeek | 6.5 | 5.4 | $0.151 | 1/2 | 3.09s |
| #275 | KAT-Coder-Air V2.5 low | Kwaipilot | 6.5 | 5.4 | $0.046 | 1/2 | 2.82s |
| #278 | Kimi K2.5 none | Moonshot AI | 7.3 | 5.4 | $0.101 | 1/2 | 42.1s |