Question Answering on ChGK questions (test)
44.23AccuracyQwen3-235B-A22B-Thinking-2507
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3-235B-A22B-Thinking-2507Aggregation Strategy=Talkative Team2026.05 | 44.23 | |
| Kimi-K2-ThinkingAggregation Strategy=Voting2026.05 | 43.36 | |
| Qwen3-235B-A22B-Thinking-2507Aggregation Strategy=Voting2026.05 | 43.01 | |
| DeepSeek-V3.2Aggregation Strategy=Voting2026.05 | 42.83 | |
| Qwen3-235B-A22B-Thinking-2507Aggregation Strategy=Silent Team2026.05 | 42.48 | |
| Qwen3-235B-A22BAggregation Strategy=Voting2026.05 | 42.31 | |
| Qwen3-235B-A22BAggregation Strategy=Talkative Team2026.05 | 42.31 | |
| Kimi-K2-ThinkingAggregation Strategy=Silent Team2026.05 | 42.13 | |
| DeepSeek-V3.2Aggregation Strategy=Talkative Team2026.05 | 41.61 | |
| Kimi-K2-Instruct-0905Aggregation Strategy=Voting2026.05 | 41.08 | |
| DeepSeek-R1-0528Aggregation Strategy=Voting2026.05 | 40.91 | |
| Qwen3-235B-A22BAggregation Strategy=Silent Team2026.05 | 40.03 | |
| DeepSeek-R1-0528Aggregation Strategy=Talkative Team2026.05 | 39.51 | |
| Qwen3-235B-A22B-Thinking-2507Aggregation Strategy=Single Model2026.05 | 37.41 | |
| DeepSeek-R1-0528Aggregation Strategy=Silent Team2026.05 | 37.24 | |
| Kimi-K2-Instruct-0905Aggregation Strategy=Talkative Team2026.05 | 37.24 | |
| Kimi-K2-ThinkingAggregation Strategy=Talkative Team2026.05 | 37.06 | |
| DeepSeek-V3.2Aggregation Strategy=Silent Team2026.05 | 36.19 | |
| Kimi-K2-Instruct-0905Aggregation Strategy=Silent Team2026.05 | 35.66 | |
| DeepSeek-V3.2Aggregation Strategy=Single Model2026.05 | 35.14 | |
| Qwen3-235B-A22BAggregation Strategy=Single Model2026.05 | 33.39 | |
| Kimi-K2-ThinkingAggregation Strategy=Single Model2026.05 | 30.77 | |
| DeepSeek-R1-0528Aggregation Strategy=Single Model2026.05 | 29.2 | |
| Kimi-K2-Instruct-0905Aggregation Strategy=Single Model2026.05 | 19.76 |