searchit Entity Extraction
53 models with a score. Leader: GPT-6 astra with 77.1 %.
| Benchmark profile | |
|---|---|
| Task | Extract details such as names, companies and amounts from German-language texts (measured by searchit). |
| Metric | Share of correctly extracted details in % |
| Direction | ↑ higher is better |
| As of | 24 Sept 2026 |
| Source | How the data is made |
| Licence | measured by searchit |
Ranking (53)
No entry matches the filter.
| Model | Rank | Score | Developer | EU processing: InputEU in | EU processing: OutputEU out | all providers: Inputall in | all providers: Outputall out | Open weights | GPU memory (4-bit, derived)GPU memory |
|---|---|---|---|---|---|---|---|---|---|
| GPT-6 astra | 1 | 77.1 % | OpenAI | €9.68 | €48.40 | €4.48 | €22.39 | – no | – |
| Gemini 2.5 Flash | 2 | 75.2 % | €0.27 | €2.24 | €0.13 | €1.12 | – no | – | |
| Mistral Large 4 | 3 | 70.7 % | Mistral AI | €0.50 | €1.75 | €0.50 | €1.75 | ✓ yes | from 582 GB |
| DeepSeek V4.1 Flash | 4 | 67.8 % | DeepSeek | €0.18 | €0.54 | €0.13 | €0.54 | – no | – |
| Claude Opus 5.5 | 5 | 64.2 % | Anthropic | €3.92 | €19.58 | €1.79 | €8.96 | – no | – |
| DeepSeek V4 Pro | 6 | 63.8 % | DeepSeek | €0.90 | €1.79 | €0.90 | €1.79 | ✓ yes | from 884 GB |
| Kimi K3 | 7 | 62.9 % | Moonshot AI | €2.55 | €12.76 | €1.66 | €8.51 | ✓ yes | from 1,533 GB |
| Kimi K2.5 (Retiring) | 8 | 61.6 % | Moonshot AI | €0.58 | €3.22 | €0.27 | €1.34 | ✓ yes | from 554 GB |
| Mistral Medium 3.5 | 9 | 61.3 % | Mistral AI | €1.50 | €6.00 | €1.50 | €6.00 | ✓ yes | from 75 GB |
| Kimi K2.6 | 10 | 59.9 % | Moonshot AI | €0.43 | €2.67 | €0.35 | €1.61 | ✓ yes | from 569 GB |
| MiMo v2.5 | 11 | 59.3 % | Xiaomi | – | – | €0.13 | €0.25 | ✓ yes | from 175 GB |
| GPT-5.6 luna | 12 | 58.7 % | OpenAI | €0.20 | €1.18 | €0.09 | €0.54 | – no | – |
| Seed 2.1 Turbo | 13 | 57.8 % | ByteDance | – | – | €0.56 | €2.80 | – | – |
| Qwen3.5-27B | 14 | 55.1 % | Alibaba Cloud | – | – | €0.23 | €2.33 | ✓ yes | from 20 GB |
| Claude Haiku 4.5 | 15 | 54.5 % | Anthropic | €0.89 | €4.47 | €0.45 | €2.24 | – no | – |
| GLM 5.1 | 16 | 51.5 % | Z.ai | €1.24 | €3.90 | €0.81 | €2.60 | ✓ yes | from 419 GB |
| Qwen3 235B A22B Instruct 2507 | 17 | 51.1 % | qwen-alibaba | €0.08 | €0.53 | €0.099 | €0.39 | ✓ yes | from 134 GB |
| Haiku 5.5 | 18 | 51 % | Anthropic | €0.10 | €0.51 | €0.045 | €0.22 | – no | – |
| GLM-5 | 19 | 48.7 % | Z.ai | €1.15 | €3.68 | €0.45 | €1.43 | – | – |
| Qwen3-Max | 20 | 48 % | Alibaba Cloud | – | – | – | – | – no | – |
| DeepSeek V4 Flash | 21 | 47.5 % | DeepSeek | €0.22 | €0.27 | €0.081 | €0.16 | ✓ yes | from 165 GB |
| Mistral Large 2.1 | 22 | 45.8 % | Mistral AI | – | – | – | – | ✓ yes | from 72 GB |
| GPT-6 luna | 23 | 45.4 % | OpenAI | €0.11 | €0.54 | €0.045 | €0.22 | – no | – |
| Qwen 3 Next 80b | 24 | 45.2 % | Alibaba Cloud | – | – | €0.063 | €0.54 | ✓ yes | from 49 GB |
| Qwen3.5-397B-A17B | 24 | 45.2 % | Alibaba Cloud | €0.60 | €3.58 | €0.40 | €2.69 | ✓ yes | from 226 GB |
| Gemma 4 31B | 26 | 42.6 % | €0.09 | €0.27 | €0.09 | €0.27 | ✓ yes | from 22 GB | |
| Qwen3.8-27B | 27 | 42.1 % | Alibaba Cloud | €0.09 | €0.27 | €0.09 | €0.27 | ✓ yes | from 20 GB |
| Qwen3.5-35B-A3B | 28 | 41 % | Alibaba Cloud | – | – | €0.13 | €0.90 | ✓ yes | from 24 GB |
| Qwen3.6-27B | 29 | 40.3 % | Alibaba Cloud | €0.40 | €2.70 | €0.22 | €1.79 | ✓ yes | from 20 GB |
| GPT-5.4 mini | 30 | 38.9 % | OpenAI | €0.74 | €4.43 | €0.34 | €2.02 | – no | – |
| Ministral 3 8B | 31 | 36 % | Mistral AI | €0.16 | €0.16 | €0.063 | €0.063 | ✓ yes | from 9 GB |
| GPT-4.1 | 32 | 35.5 % | OpenAI | €1.97 | €7.87 | €0.90 | €3.58 | – no | – |
| Mistral Small 3.2 24B | 33 | 34.9 % | Mistral AI | €0.061 | €0.16 | €0.061 | €0.16 | ✓ yes | from 18 GB |
| Mistral Small 4 119B | 34 | 33.6 % | Mistral AI | €0.14 | €0.56 | €0.14 | €0.56 | – | – |
| Qwen3.7-Plus | 35 | 32.9 % | Alibaba Cloud | – | – | €0.29 | €1.15 | – no | – |
| Qwen3.8-Flash | 36 | 32.8 % | Alibaba Cloud | €0.20 | €0.50 | €0.13 | €0.44 | ✓ yes | from 103 GB |
| Qwen3.6-35B-A3B | 37 | 32.7 % | Alibaba Cloud | €0.13 | €0.45 | €0.13 | €0.45 | ✓ yes | from 24 GB |
| NVIDIA Nemotron 3 Super 120B A12B | 38 | 30.5 % | NVIDIA | – | – | €0.067 | €0.29 | ✓ yes | from 70 GB |
| Qwen3.5-9B | 39 | 29.3 % | Alibaba Cloud | €0.09 | €0.13 | €0.09 | €0.13 | ✓ yes | from 10 GB |
| Qwen3.5-Flash | 40 | 28.8 % | Alibaba Cloud | – | – | – | – | – no | – |
| Seed 2.0 Lite | 41 | 28.4 % | ByteDance | – | – | – | – | – | – |
| GPT-5.4 nano | 42 | 26.9 % | OpenAI | – | – | €0.09 | €0.56 | – no | – |
| Gemma 3 27B | 43 | 25.2 % | €0.089 | €0.27 | €0.072 | €0.14 | ✓ yes | from 20 GB | |
| Gemma 4 26B A4B | 43 | 25.2 % | €0.11 | €0.27 | €0.063 | €0.30 | – | – | |
| GPT-4o | 45 | 24.8 % | OpenAI | €2.39 | €9.55 | €1.12 | €4.48 | – no | – |
| gpt-4.1-mini | 46 | 24.7 % | OpenAI | €0.39 | €1.53 | €0.18 | €0.72 | – no | – |
| Seed 2.0 Mini | 47 | 19.4 % | ByteDance | – | – | – | – | – | – |
| Gemini 3.1 Flash-Lite | 48 | 19.1 % | €0.24 | €1.46 | €0.11 | €0.67 | – no | – | |
| Nova Lite | 49 | 17.9 % | Amazon | €0.062 | €0.25 | €0.054 | €0.21 | – no | – |
| Nova Pro | 50 | 16.4 % | Amazon | €0.82 | €3.29 | €0.36 | €1.43 | – no | – |
| Gemma 3 12B | 51 | 14.2 % | – | – | €0.045 | €0.13 | ✓ yes | from 11 GB | |
| Llama 3.3 70B | 52 | 12.6 % | Meta | €0.45 | €0.65 | €0.09 | €0.29 | ✓ yes | from 43 GB |
| GPT-4o mini | 53 | 0 % | OpenAI | €0.14 | €0.57 | €0.067 | €0.27 | – no | – |
Equal scores share a rank. When filtering, the rank stays the position in the whole list. GPU memory “from …” is a lower bound (parameters × 0.55 GB + 4 GB). Prices: € per 1M tokens. Source: providers' pricing pages, read and checked by searchit. As of 7 Nov 2026.
Price and performance
Scores: searchit, measured by searchit. Taken unchanged from the source.