Response Classification on 38 topics Indirect
60.5Pos ScoreKimi K2
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Kimi K2Model Scale=Large-scale2026.04 | 60.5 | 23.7 | 10.5 | 5.3 | 0 | |
| Haiku 4.5Model Scale=Smaller2026.04 | 60.5 | 7.9 | 10.5 | 21.1 | 0 | |
| Opus 4.6Model Scale=Large-scale2026.04 | 55.3 | 36.8 | 2.6 | 5.3 | 0 | |
| GPT-5.4-miniModel Scale=Smaller2026.04 | 28.9 | 65.8 | 5.3 | 0 | 0 | |
| Grok 4.2Model Scale=Large-scale2026.04 | 26.3 | 63.2 | 10.5 | 0 | 0 | |
| GPT-5.4Model Scale=Large-scale2026.04 | 21.1 | 76.3 | 2.6 | 0 | 0 | |
| Sabiazinho-4Model Scale=Smaller2026.04 | 18.4 | 78.9 | 2.6 | 0 | 0 | |
| Gemini 3.1 ProModel Scale=Large-scale2026.04 | 10.5 | 86.8 | 2.6 | 0 | 0 | |
| Mistral Large 3Model Scale=Large-scale2026.04 | 10.5 | 89.5 | 0 | 0 | 0 | |
| Gemini 3.1 FlashModel Scale=Smaller2026.04 | 10.5 | 86.8 | 2.6 | 0 | 0 | |
| Sabiá-4Model Scale=Large-scale2026.04 | 7.9 | 92.1 | 0 | 0 | 0 | |
| Qwen3.5-397BModel Scale=Large-scale2026.04 | 5.3 | 92.1 | 2.6 | 0 | 0 | |
| Llama 4 MaverickModel Scale=Large-scale2026.04 | 2.6 | 94.7 | 2.6 | 0 | 0 |