<!-- https://models.searchit-agent.ai/en/leaderboards/searchit-entity-extraction/ | searchit Models -->

# 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](https://models.searchit-agent.ai/en/knowledge/how-the-data-is-made/) |
| Licence | measured by searchit |

## Ranking (53)

| Model | Rank | Score | Developer | EU processing: Input | EU processing: Output | all providers: Input | all providers: Output | Open weights | GPU memory (4-bit, derived) |
|---|---:|---:|---|---:|---:|---:|---:|---|---:|
| [GPT-6 astra](https://models.searchit-agent.ai/en/models/gpt-6-astra/) | 1 | **77.1 %** | OpenAI | €9.68 | €48.40 | €4.48 | €22.39 | – no | – |
| [Gemini 2.5 Flash](https://models.searchit-agent.ai/en/models/gemini-2-5-flash/) | 2 | **75.2 %** | Google | €0.27 | €2.24 | €0.13 | €1.12 | – no | – |
| [Mistral Large 4](https://models.searchit-agent.ai/en/models/mistral-large-4/) | 3 | **70.7 %** | Mistral AI | €0.50 | €1.75 | €0.50 | €1.75 | ✓ yes | [from 582 GB](https://models.searchit-agent.ai/en/self-hosting/#tier-8x) |
| [DeepSeek V4.1 Flash](https://models.searchit-agent.ai/en/models/deepseek-flash/) | 4 | **67.8 %** | DeepSeek | €0.18 | €0.54 | €0.13 | €0.54 | – no | – |
| [Claude Opus 5.5](https://models.searchit-agent.ai/en/models/claude-opus-5-5/) | 5 | **64.2 %** | Anthropic | €3.92 | €19.58 | €1.79 | €8.96 | – no | – |
| [DeepSeek V4 Pro](https://models.searchit-agent.ai/en/models/deepseek-v4-pro/) | 6 | **63.8 %** | DeepSeek | €0.90 | €1.79 | €0.90 | €1.79 | ✓ yes | [from 884 GB](https://models.searchit-agent.ai/en/self-hosting/#tier-rechenzentrum) |
| [Kimi K3](https://models.searchit-agent.ai/en/models/kimi-k3/) | 7 | **62.9 %** | Moonshot AI | €2.55 | €12.76 | €1.66 | €8.51 | ✓ yes | [from 1,533 GB](https://models.searchit-agent.ai/en/self-hosting/#tier-rechenzentrum) |
| [Kimi K2.5 (Retiring)](https://models.searchit-agent.ai/en/models/kimi-k2-5/) | 8 | **61.6 %** | Moonshot AI | €0.58 | €3.22 | €0.27 | €1.34 | ✓ yes | [from 554 GB](https://models.searchit-agent.ai/en/self-hosting/#tier-8x) |
| [Mistral Medium 3.5](https://models.searchit-agent.ai/en/models/mistral-medium-3-5/) | 9 | **61.3 %** | Mistral AI | €1.50 | €6.00 | €1.50 | €6.00 | ✓ yes | [from 75 GB](https://models.searchit-agent.ai/en/self-hosting/#tier-96-gb) |
| [Kimi K2.6](https://models.searchit-agent.ai/en/models/kimi-k2-6/) | 10 | **59.9 %** | Moonshot AI | €0.43 | €2.67 | €0.35 | €1.61 | ✓ yes | [from 569 GB](https://models.searchit-agent.ai/en/self-hosting/#tier-8x) |
| [MiMo v2.5](https://models.searchit-agent.ai/en/models/mimo-v2-5/) | 11 | **59.3 %** | Xiaomi | – | – | €0.13 | €0.25 | ✓ yes | [from 175 GB](https://models.searchit-agent.ai/en/self-hosting/#tier-2x) |
| [GPT-5.6 luna](https://models.searchit-agent.ai/en/models/gpt-5-6-luna/) | 12 | **58.7 %** | OpenAI | €0.20 | €1.18 | €0.09 | €0.54 | – no | – |
| [Seed 2.1 Turbo](https://models.searchit-agent.ai/en/models/seed-2-1-turbo/) | 13 | **57.8 %** | ByteDance | – | – | €0.56 | €2.80 | – | – |
| [Qwen3.5-27B](https://models.searchit-agent.ai/en/models/qwen3-5-27b/) | 14 | **55.1 %** | Alibaba Cloud | – | – | €0.23 | €2.33 | ✓ yes | [from 20 GB](https://models.searchit-agent.ai/en/self-hosting/#tier-24-gb) |
| [Claude Haiku 4.5](https://models.searchit-agent.ai/en/models/claude-haiku-4-5/) | 15 | **54.5 %** | Anthropic | €0.89 | €4.47 | €0.45 | €2.24 | – no | – |
| [GLM 5.1](https://models.searchit-agent.ai/en/models/glm-5-1/) | 16 | **51.5 %** | Z.ai | €1.24 | €3.90 | €0.81 | €2.60 | ✓ yes | [from 419 GB](https://models.searchit-agent.ai/en/self-hosting/#tier-8x) |
| [Qwen3 235B A22B Instruct 2507](https://models.searchit-agent.ai/en/models/qwen3-235b-a22b-instruct-2507/) | 17 | **51.1 %** | qwen-alibaba | €0.08 | €0.53 | €0.099 | €0.39 | ✓ yes | [from 134 GB](https://models.searchit-agent.ai/en/self-hosting/#tier-2x) |
| [Haiku 5.5](https://models.searchit-agent.ai/en/models/claude-haiku-5-5/) | 18 | **51 %** | Anthropic | €0.10 | €0.51 | €0.045 | €0.22 | – no | – |
| [GLM-5](https://models.searchit-agent.ai/en/models/glm-5/) | 19 | **48.7 %** | Z.ai | €1.15 | €3.68 | €0.45 | €1.43 | – | – |
| [Qwen3-Max](https://models.searchit-agent.ai/en/models/qwen3-max/) | 20 | **48 %** | Alibaba Cloud | – | – | – | – | – no | – |
| [DeepSeek V4 Flash](https://models.searchit-agent.ai/en/models/deepseek-v4-flash/) | 21 | **47.5 %** | DeepSeek | €0.22 | €0.27 | €0.081 | €0.16 | ✓ yes | [from 165 GB](https://models.searchit-agent.ai/en/self-hosting/#tier-2x) |
| [Mistral Large 2.1](https://models.searchit-agent.ai/en/models/mistral-large-2-1/) | 22 | **45.8 %** | Mistral AI | – | – | – | – | ✓ yes | [from 72 GB](https://models.searchit-agent.ai/en/self-hosting/#tier-96-gb) |
| [GPT-6 luna](https://models.searchit-agent.ai/en/models/gpt-6-luna/) | 23 | **45.4 %** | OpenAI | €0.11 | €0.54 | €0.045 | €0.22 | – no | – |
| [Qwen 3 Next 80b](https://models.searchit-agent.ai/en/models/qwen3-next-80b-a3b-instruct/) | 24 | **45.2 %** | Alibaba Cloud | – | – | €0.063 | €0.54 | ✓ yes | [from 49 GB](https://models.searchit-agent.ai/en/self-hosting/#tier-96-gb) |
| [Qwen3.5-397B-A17B](https://models.searchit-agent.ai/en/models/qwen3-5-397b-a17b/) | 24 | **45.2 %** | Alibaba Cloud | €0.60 | €3.58 | €0.40 | €2.69 | ✓ yes | [from 226 GB](https://models.searchit-agent.ai/en/self-hosting/#tier-4x) |
| [Gemma 4 31B](https://models.searchit-agent.ai/en/models/gemma-4-31b/) | 26 | **42.6 %** | Google | €0.09 | €0.27 | €0.09 | €0.27 | ✓ yes | [from 22 GB](https://models.searchit-agent.ai/en/self-hosting/#tier-24-gb) |
| [Qwen3.8-27B](https://models.searchit-agent.ai/en/models/qwen3-8-27b/) | 27 | **42.1 %** | Alibaba Cloud | €0.09 | €0.27 | €0.09 | €0.27 | ✓ yes | [from 20 GB](https://models.searchit-agent.ai/en/self-hosting/#tier-24-gb) |
| [Qwen3.5-35B-A3B](https://models.searchit-agent.ai/en/models/qwen3-5-35b-a3b/) | 28 | **41 %** | Alibaba Cloud | – | – | €0.13 | €0.90 | ✓ yes | [from 24 GB](https://models.searchit-agent.ai/en/self-hosting/#tier-24-gb) |
| [Qwen3.6-27B](https://models.searchit-agent.ai/en/models/qwen3-6-27b/) | 29 | **40.3 %** | Alibaba Cloud | €0.40 | €2.70 | €0.22 | €1.79 | ✓ yes | [from 20 GB](https://models.searchit-agent.ai/en/self-hosting/#tier-24-gb) |
| [GPT-5.4 mini](https://models.searchit-agent.ai/en/models/gpt-5-4-mini/) | 30 | **38.9 %** | OpenAI | €0.74 | €4.43 | €0.34 | €2.02 | – no | – |
| [Ministral 3 8B](https://models.searchit-agent.ai/en/models/ministral-3-8b/) | 31 | **36 %** | Mistral AI | €0.16 | €0.16 | €0.063 | €0.063 | ✓ yes | [from 9 GB](https://models.searchit-agent.ai/en/self-hosting/#tier-24-gb) |
| [GPT-4.1](https://models.searchit-agent.ai/en/models/gpt-4-1/) | 32 | **35.5 %** | OpenAI | €1.97 | €7.87 | €0.90 | €3.58 | – no | – |
| [Mistral Small 3.2 24B](https://models.searchit-agent.ai/en/models/mistral-small-3-2-24b/) | 33 | **34.9 %** | Mistral AI | €0.061 | €0.16 | €0.061 | €0.16 | ✓ yes | [from 18 GB](https://models.searchit-agent.ai/en/self-hosting/#tier-24-gb) |
| [Mistral Small 4 119B](https://models.searchit-agent.ai/en/models/mistral-small-4/) | 34 | **33.6 %** | Mistral AI | €0.14 | €0.56 | €0.14 | €0.56 | – | – |
| [Qwen3.7-Plus](https://models.searchit-agent.ai/en/models/qwen3-7-plus/) | 35 | **32.9 %** | Alibaba Cloud | – | – | €0.29 | €1.15 | – no | – |
| [Qwen3.8-Flash](https://models.searchit-agent.ai/en/models/qwen3-8-flash/) | 36 | **32.8 %** | Alibaba Cloud | €0.20 | €0.50 | €0.13 | €0.44 | ✓ yes | [from 103 GB](https://models.searchit-agent.ai/en/self-hosting/#tier-2x) |
| [Qwen3.6-35B-A3B](https://models.searchit-agent.ai/en/models/qwen3-6-35b-a3b/) | 37 | **32.7 %** | Alibaba Cloud | €0.13 | €0.45 | €0.13 | €0.45 | ✓ yes | [from 24 GB](https://models.searchit-agent.ai/en/self-hosting/#tier-24-gb) |
| [NVIDIA Nemotron 3 Super 120B A12B](https://models.searchit-agent.ai/en/models/nvidia-nemotron-3-super-120b-a12b/) | 38 | **30.5 %** | NVIDIA | – | – | €0.067 | €0.29 | ✓ yes | [from 70 GB](https://models.searchit-agent.ai/en/self-hosting/#tier-96-gb) |
| [Qwen3.5-9B](https://models.searchit-agent.ai/en/models/qwen3-5-9b/) | 39 | **29.3 %** | Alibaba Cloud | €0.09 | €0.13 | €0.09 | €0.13 | ✓ yes | [from 10 GB](https://models.searchit-agent.ai/en/self-hosting/#tier-24-gb) |
| [Qwen3.5-Flash](https://models.searchit-agent.ai/en/models/qwen3-5-flash/) | 40 | **28.8 %** | Alibaba Cloud | – | – | – | – | – no | – |
| [Seed 2.0 Lite](https://models.searchit-agent.ai/en/models/seed-2-0-lite/) | 41 | **28.4 %** | ByteDance | – | – | – | – | – | – |
| [GPT-5.4 nano](https://models.searchit-agent.ai/en/models/gpt-5-4-nano/) | 42 | **26.9 %** | OpenAI | – | – | €0.09 | €0.56 | – no | – |
| [Gemma 3 27B](https://models.searchit-agent.ai/en/models/gemma-3-27b/) | 43 | **25.2 %** | Google | €0.089 | €0.27 | €0.072 | €0.14 | ✓ yes | [from 20 GB](https://models.searchit-agent.ai/en/self-hosting/#tier-24-gb) |
| [Gemma 4 26B A4B](https://models.searchit-agent.ai/en/models/gemma-4-26b-a4b/) | 43 | **25.2 %** | Google | €0.11 | €0.27 | €0.063 | €0.30 | – | – |
| [GPT-4o](https://models.searchit-agent.ai/en/models/gpt-4o/) | 45 | **24.8 %** | OpenAI | €2.39 | €9.55 | €1.12 | €4.48 | – no | – |
| [gpt-4.1-mini](https://models.searchit-agent.ai/en/models/gpt-4-1-mini/) | 46 | **24.7 %** | OpenAI | €0.39 | €1.53 | €0.18 | €0.72 | – no | – |
| [Seed 2.0 Mini](https://models.searchit-agent.ai/en/models/seed-2-0-mini/) | 47 | **19.4 %** | ByteDance | – | – | – | – | – | – |
| [Gemini 3.1 Flash-Lite](https://models.searchit-agent.ai/en/models/gemini-3-1-flash-lite/) | 48 | **19.1 %** | Google | €0.24 | €1.46 | €0.11 | €0.67 | – no | – |
| [Nova Lite](https://models.searchit-agent.ai/en/models/nova-lite/) | 49 | **17.9 %** | Amazon | €0.062 | €0.25 | €0.054 | €0.21 | – no | – |
| [Nova Pro](https://models.searchit-agent.ai/en/models/nova-pro/) | 50 | **16.4 %** | Amazon | €0.82 | €3.29 | €0.36 | €1.43 | – no | – |
| [Gemma 3 12B](https://models.searchit-agent.ai/en/models/gemma-3-12b/) | 51 | **14.2 %** | Google | – | – | €0.045 | €0.13 | ✓ yes | [from 11 GB](https://models.searchit-agent.ai/en/self-hosting/#tier-24-gb) |
| [Llama 3.3 70B](https://models.searchit-agent.ai/en/models/llama-3-3-70b/) | 52 | **12.6 %** | Meta | €0.45 | €0.65 | €0.09 | €0.29 | ✓ yes | [from 43 GB](https://models.searchit-agent.ai/en/self-hosting/#tier-48-gb) |
| [GPT-4o mini](https://models.searchit-agent.ai/en/models/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

48 models with a price: vertical the score (top = better), horizontal the blended price of the cheapest offer. Filled dots are also available with processing in the EU.

_Scores: searchit, measured by searchit. Taken unchanged from the source._

---

Prices as of 7 Nov 2026. Providers' list prices, without guarantee.