Question Answering on OracleProto
60.16Composite AccuracyDeepSeek-V3.2-Exp
Evaluation results
| Method | Links | |
|---|---|---|
| DeepSeek-V3.2-ExpTotal Cost (USD)=3.60, Per-Correct Cost (USD)=0.0252026.05 | 60.16 | |
| GLM 5Total Cost (USD)=7.06, Per-Correct Cost (USD)=0.0482026.05 | 60.02 | |
| Qwen3.5-FlashTotal Cost (USD)=0.45, Per-Correct Cost (USD)=0.0032026.05 | 58.96 | |
| Doubao Seed 2.0 LiteTotal Cost (USD)=0.89, Per-Correct Cost (USD)=0.0062026.05 | 58.58 | |
| Kimi K2.5Total Cost (USD)=6.79, Per-Correct Cost (USD)=0.0492026.05 | 58 | |
| MiniMax M2.5Total Cost (USD)=3.21, Per-Correct Cost (USD)=0.0242026.05 | 54.94 |