Tier Classification on Management Benchmark post-June-30-2025 publications
60.8AccuracyGPT-4.1-nano (SFT) + Qwen3-30B-A3B (SFT)
Evaluation results
| Method | Links | |
|---|---|---|
| GPT-4.1-nano (SFT) + Qwen3-30B-A3B (SFT)Model 1=GPT-4.1-nano (SFT), Model 2=Qwen3-30B-A3B (SFT)2026.03 | 60.8 | |
| GPT-4.1 (SFT) + Qwen3-30B-A3B (SFT)Model 1=GPT-4.1 (SFT), Model 2=Qwen3-30B-A3B (SFT)2026.03 | 60 | |
| GPT-4.1 (SFT) + Qwen3-4B (SFT)Model 1=GPT-4.1 (SFT), Model 2=Qwen3-4B (SFT)2026.03 | 60 | |
| GPT-4.1-nano (SFT) + Qwen3-4B (SFT)Model 1=GPT-4.1-nano (SFT), Model 2=Qwen3-4B (SFT)2026.03 | 60 | |
| GPT-4.1-nano (SFT) + GPT-4.1 (SFT)Model 1=GPT-4.1-nano (SFT), Model 2=GPT-4.1 (SFT)2026.03 | 59.2 | |
| Qwen3-30B-A3B (SFT) + Qwen3-4B (SFT)Model 1=Qwen3-30B-A3B (SFT), Model 2=Qwen3-4B (SFT)2026.03 | 59.2 |