Factual Question Answering on TriviaQA (test)
73AccuracyPrisonBreak
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| PrisonBreakModel Name=DEEPSEEK-R1-DISTILL-QWEN-14B, Precision=FP42026.02 | 73 | 50 | — | |
| PrisonBreakModel Name=DEEPSEEK-R1-DISTILL-QWEN-14B, Precision=INT82026.02 | 71 | 50 | — | |
| PrisonBreakModel Name=QWEN3-8B, Precision=INT82026.02 | 68 | 50 | — | |
| PrisonBreakModel Name=LLAMA-3.1-8B-INSTRUCT, Precision=FP42026.02 | 67 | 50 | — | |
| PrisonBreakModel Name=QWEN3-8B, Precision=FP42026.02 | 67 | 50 | — | |
| PrisonBreakModel Name=LLAMA-3.1-8B-INSTRUCT, Precision=INT82026.02 | 61 | 50 | — | |
| TFLModel Name=QWEN3-8B, Precision=BF162026.02 | 52 | 3 | — | |
| TFLModel Name=DEEPSEEK-R1-DISTILL-QWEN-14B, Precision=INT82026.02 | 52 | 7 | — | |
| TFLModel Name=DEEPSEEK-R1-DISTILL-QWEN-14B, Precision=BF162026.02 | 51 | 7 | — | |
| TFLModel Name=QWEN3-8B, Precision=INT82026.02 | 48 | 4 | — | |
| TFLModel Name=LLAMA-3.1-8B-INSTRUCT, Precision=BF162026.02 | 37 | 14 | — | |
| TFLModel Name=LLAMA-3.1-8B-INSTRUCT, Precision=INT82026.02 | 36 | 13 | — | |
| SBFAModel Name=QWEN3-8B, Precision=INT82026.02 | 29 | 1 | — | |
| SilentStrikerModel Name=LLAMA-3.1-8B-INSTRUCT, Precision=FP42026.02 | 13 | 50 | — | |
| SilentStrikerModel Name=QWEN3-8B, Precision=FP42026.02 | 11 | 50 | — | |
| SilentStrikerModel Name=QWEN3-8B, Precision=INT82026.02 | 9 | 50 | — | |
| SilentStrikerModel Name=LLAMA-3.1-8B-INSTRUCT, Precision=INT82026.02 | 8 | 50 | — | |
| SilentStrikerModel Name=DEEPSEEK-R1-DISTILL-QWEN-14B, Precision=INT82026.02 | 5 | 50 | — | |
| SilentStrikerModel Name=DEEPSEEK-R1-DISTILL-QWEN-14B, Precision=FP42026.02 | 4 | 50 | — | |
| GenBFAModel Name=LLAMA-3.1-8B-INSTRUCT, Precision=INT82026.02 | 0 | 50 | — | |
| GenBFAModel Name=LLAMA-3.1-8B-INSTRUCT, Precision=FP42026.02 | 0 | 50 | — | |
| SBFAModel Name=LLAMA-3.1-8B-INSTRUCT, Precision=INT82026.02 | 0 | 1 | — | |
| SBFAModel Name=LLAMA-3.1-8B-INSTRUCT, Precision=BF162026.02 | 0 | 1 | — | |
| GenBFAModel Name=QWEN3-8B, Precision=INT82026.02 | 0 | 50 | — | |
| GenBFAModel Name=QWEN3-8B, Precision=FP42026.02 | 0 | 50 | — | |
| SBFAModel Name=QWEN3-8B, Precision=BF162026.02 | 0 | 1 | — | |
| GenBFAModel Name=DEEPSEEK-R1-DISTILL-QWEN-14B, Precision=INT82026.02 | 0 | 50 | — | |
| GenBFAModel Name=DEEPSEEK-R1-DISTILL-QWEN-14B, Precision=FP42026.02 | 0 | 50 | — | |
| SBFAModel Name=DEEPSEEK-R1-DISTILL-QWEN-14B, Precision=BF162026.02 | 0 | 2 | — |