Workflow Execution on T3 Payment
100TSR8 models (Gemma4:e4b/26b/31b, GPT-OSS:20b/120b, MSmall3.2:24b, GPT-5.2)
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| 8 models (Gemma4:e4b/26b/31b, GPT-OSS:20b/120b, MSmall3.2:24b, GPT-5.2)2026.05 | 100 | 100 | 100 | |
| Qwen2.5:32b2026.05 | 100 | 100 | 99.99 | |
| GPT-4.12026.05 | 100 | 100 | 99.96 | |
| Qwen3:32b2026.05 | 100 | 100 | 99.97 | |
| Qwen3:8b2026.05 | 100 | 100 | 99.97 | |
| Qwen2.5:14b2026.05 | 99.76 | 99.8 | 99.56 | |
| Qwen3:14b2026.05 | 99.68 | 99.84 | 99.64 | |
| Llama3.1:70b2026.05 | 98.88 | 98.78 | 98.81 | |
| Magistral:24b2026.05 | 94.72 | 97.05 | 93.88 | |
| Llama3.1:8b2026.05 | 93.44 | 96.05 | 93.31 | |
| Qwen2.5:7b2026.05 | 53.28 | 64.16 | 47.83 |