by @querulous-deer
This benchmark evaluates the model's ability to perform Named Entity Recognition (NER) and adhere to a strict JSON schema. By embedding synthetic identity details (Name, Email, Job, City) within randomized, noisy, and unstructured text blocks, the task challenges the model to filter out irrelevant signals (such as random IDs or status codes) and map the correct entities to specific JSON keys without hallucination.
Best in Class
Overpriced
Your Selection
Click on the model to make selection
| Config | Total Cost | Quality | Username | Position | |
|---|---|---|---|---|---|
| qwen/qwen3-next-80b-a3b-instru... | $0.0000 | 97.5% | @querulous-deer | #1 | |
| nousresearch/hermes-3-llama-3.... | $0.0000 | 97.0% | @querulous-deer | #2 | |
| moonshotai/kimi-k2:free | $0.0000 | 97.0% | @querulous-deer | #2 | |
| nvidia/nemotron-3-nano-30b-a3b... | $0.0000 | 95.0% | @querulous-deer | #4 | |
| arcee-ai/trinity-mini:free | $0.0000 | 95.0% | @querulous-deer | #4 | |
| openai/gpt-oss-20b:free | $0.0000 | 91.0% | @querulous-deer | #6 | |
| qwen/qwen-2.5-vl-7b-instruct:f... | $0.0000 | 73.5% | @querulous-deer | #7 | |
| openai/gpt-oss-120b:free | $0.0000 | 72.0% | @querulous-deer | #8 | |
| nvidia/nemotron-nano-12b-v2-vl... | $0.0000 | 61.0% | @querulous-deer | #9 | |
| qwen/qwen3-coder:free | $0.0000 | 10.0% | @querulous-deer | #10 | |
| nvidia/nemotron-nano-9b-v2:fre... | $0.0000 | 3.5% | @querulous-deer | #11 | |
| z-ai/glm-4.5-air:free | $0.0000 | 0.0% | @querulous-deer | #12 | |
| xiaomi/mimo-v2-flash:free | $0.0000 | 0.0% | @querulous-deer | #12 | |
| tngtech/tng-r1t-chimera:free | $0.0000 | 0.0% | @querulous-deer | #12 | |
| tngtech/deepseek-r1t2-chimera:... | $0.0000 | 0.0% | @querulous-deer | #12 | |
| tngtech/deepseek-r1t-chimera:f... | $0.0000 | 0.0% | @querulous-deer | #12 | |
| mistralai/mistral-small-3.1-24... | $0.0000 | 0.0% | @querulous-deer | #12 | |
| mistralai/devstral-2512:free | $0.0000 | 0.0% | @querulous-deer | #12 | |
| meta-llama/llama-3.3-70b-instr... | $0.0000 | 0.0% | @querulous-deer | #12 | |
| meta-llama/llama-3.2-3b-instru... | $0.0000 | 0.0% | @querulous-deer | #12 | |
| meta-llama/llama-3.1-405b-inst... | $0.0000 | 0.0% | @querulous-deer | #12 | |
| google/gemma-3n-e4b-it:free | $0.0000 | 0.0% | @querulous-deer | #12 | |
| google/gemma-3-4b-it:free | $0.0000 | 0.0% | @querulous-deer | #12 | |
| google/gemma-3-27b-it:free | $0.0000 | 0.0% | @querulous-deer | #12 | |
| google/gemma-3-12b-it:free | $0.0000 | 0.0% | @querulous-deer | #12 | |
| deepseek/deepseek-r1-0528:free | $0.0000 | 0.0% | @querulous-deer | #12 |
| Total Cost | Quality | |
|---|---|---|
| qwen/qwen3-next-80b-a3b-instru... | $0.0000 | 97.5% |
| nousresearch/hermes-3-llama-3.... | $0.0000 | 97.0% |
| moonshotai/kimi-k2:free | $0.0000 | 97.0% |
| nvidia/nemotron-3-nano-30b-a3b... | $0.0000 | 95.0% |
| arcee-ai/trinity-mini:free | $0.0000 | 95.0% |
| openai/gpt-oss-20b:free | $0.0000 | 91.0% |
| qwen/qwen-2.5-vl-7b-instruct:f... | $0.0000 | 73.5% |
| openai/gpt-oss-120b:free | $0.0000 | 72.0% |
| nvidia/nemotron-nano-12b-v2-vl... | $0.0000 | 61.0% |
| qwen/qwen3-coder:free | $0.0000 | 10.0% |
| nvidia/nemotron-nano-9b-v2:fre... | $0.0000 | 3.5% |
| z-ai/glm-4.5-air:free | $0.0000 | 0.0% |
| xiaomi/mimo-v2-flash:free | $0.0000 | 0.0% |
| tngtech/tng-r1t-chimera:free | $0.0000 | 0.0% |
| tngtech/deepseek-r1t2-chimera:... | $0.0000 | 0.0% |
| tngtech/deepseek-r1t-chimera:f... | $0.0000 | 0.0% |
| mistralai/mistral-small-3.1-24... | $0.0000 | 0.0% |
| mistralai/devstral-2512:free | $0.0000 | 0.0% |
| meta-llama/llama-3.3-70b-instr... | $0.0000 | 0.0% |
| meta-llama/llama-3.2-3b-instru... | $0.0000 | 0.0% |
| meta-llama/llama-3.1-405b-inst... | $0.0000 | 0.0% |
| google/gemma-3n-e4b-it:free | $0.0000 | 0.0% |
| google/gemma-3-4b-it:free | $0.0000 | 0.0% |
| google/gemma-3-27b-it:free | $0.0000 | 0.0% |
| google/gemma-3-12b-it:free | $0.0000 | 0.0% |
| deepseek/deepseek-r1-0528:free | $0.0000 | 0.0% |
Loading prompt execution data...