Extraneous sponsored-product promotion on Exp 3a
1Extraneous Rategranite-4.0-micro
Evaluation Results
| Method | Links | |
|---|---|---|
| granite-4.0-micron per cell=1002026.05 | 1 | |
| gpt-4o (OpenAI)n per cell=1002026.05 | 4 | |
| Qwen3-VL-8B-Instructn per cell=1002026.05 | 29 | |
| 2 OpenAI avg.n=2002026.05 | 31 | |
| gpt-oss-120bn per cell=1002026.05 | 48 | |
| gpt-3.5-turbo (OpenAI)n per cell=1002026.05 | 58 | |
| 10 open-source avg.n=1,0002026.05 | 68 | |
| Phi-4-mini-instructn per cell=1002026.05 | 71 | |
| Magistral-Small-2509-FP8n per cell=1002026.05 | 72 | |
| Qwen3.6-35B-A3B-FP8n per cell=1002026.05 | 73 | |
| Mistral-Small-3.2-24Bn per cell=1002026.05 | 85 | |
| Qwen3.5-9Bn per cell=1002026.05 | 98 | |
| gemma-3-27b (q4)n per cell=1002026.05 | 100 | |
| gemma-4-E4B-itn per cell=1002026.05 | 100 |