diff --git a/README.md b/README.md index cb994f67db70d9b163928e8b5788ceb4812dd26a..4faf464a647de02d7bc67c9ee8b063eb8b416365 100644 --- a/README.md +++ b/README.md @@ -88,15 +88,16 @@ python main.py --task_type evaluate 受限于模型推理速度,目前只测试了pass@1指标。 -| | python | java | cpp | js | go | -|--------------|--------|--------|--------|--------|--------| -| chatgpt | 64.02% | 15.85% | 26.22% | 47.00% | 31.70% | -| bbt-7B | 0.61% | 1.83% | 1.22% | 1.83% | 0.00% | -| bbt-13B | 2.49% | 0.00% | 1.90% | 1.83% | 0.61% | -| chatglm2-6B | 7.93% | 5.45% | 0.61% | 6.70% | 1.83% | -| codegeex2-6B | 29.90% | 27.43% | 6.70% | 24.40% | 17.68% | -| llama2-7B | 5.49% | 8.54% | 1.22% | 3.66% | 6.10% | -| baichuan-7B | 7.93% | 1.83% | 0.00% | 6.71% | 6.71% | +| | python | java | cpp | js | go | +|----------------------|--------|--------|--------|--------|--------| +| chatgpt | 64.02% | 15.85% | 26.22% | 47.00% | 31.70% | +| bbt-7B | 0.61% | 1.83% | 1.22% | 1.83% | 0.00% | +| bbt-13B | 2.49% | 0.00% | 1.90% | 1.83% | 0.61% | +| chatglm2-6B | 7.93% | 5.45% | 0.61% | 6.70% | 1.83% | +| codegeex2-6B | 29.90% | 27.43% | 6.70% | 24.40% | 17.68% | +| llama2-7B | 5.49% | 8.54% | 1.22% | 3.66% | 6.10% | +| baichuan-7B | 7.93% | 1.83% | 0.00% | 6.71% | 6.71% | +| chatgpt+codegeex2-6B | 60.02% | 40.85% | 30.49% | 50.66% | 44.51% |