Knowledge on C-EVAL
88.12ScoreQwen3-30B-A3B-Inst-2507
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Qwen3-30B-A3B-Inst-25072026.02 | 88.12 | 100 | |
| Ling-flash-2.02026.02 | 87.54 | 100 | |
| LLaDA2.1-flashInference Mode=S Mode2026.02 | 86.93 | 271 | |
| LLaDA2.1-flashInference Mode=Q Mode2026.02 | 86.71 | 175 | |
| LLaDA2.0-flash2026.02 | 85.21 | 190 | |
| Ling-mini-2.02026.02 | 82.17 | — | |
| LLaDA2.0-mini2026.02 | 81.8 | 1.78 | |
| Qwen3-8Bno think=true2026.02 | 80.6 | — | |
| LLaDA2.1-minimode=Q Mode2026.02 | 78.59 | 1.91 | |
| LLaDA2.1-minimode=S Mode2026.02 | 78.4 | 3.39 | |
| KEELTraining=SFT, Evaluation Setting=5-shot2026.01 | 68.4 | — | |
| Pre-LNTraining=SFT, Evaluation Setting=5-shot2026.01 | 66.5 | — | |
| ADGSelector=ADG, Model=LLaMA3-8B-Instruct, Training Pool=Alpaca-GPT4-ZH, Selection Size=10K, Fine-tuning=Yes, Number of Runs=52026.04 | 45.99 | — | |
| SuperFilteringSelector=SuperFiltering, Model=LLaMA3-8B-Instruct, Training Pool=Alpaca-GPT4-ZH, Selection Size=10K, Fine-tuning=Yes, Number of Runs=52026.04 | 44.97 | — | |
| RethinkingSelector=Rethinking, Model=LLaMA3-8B-Instruct, Training Pool=Alpaca-GPT4-ZH, Selection Size=10K, Fine-tuning=Yes, Number of Runs=52026.04 | 42.27 | — | |
| All DataSelector=All Data, Model=LLaMA3-8B-Instruct, Training Pool=Alpaca-GPT4-ZH, Selection Size=42,677, Fine-tuning=Yes, Number of Runs=52026.04 | 40.56 | — | |
| RandomSelector=Random, Model=LLaMA3-8B-Instruct, Training Pool=Alpaca-GPT4-ZH, Selection Size=10K, Fine-tuning=Yes, Number of Runs=52026.04 | 40.56 | — |