The typical standard errors between pairs of models on this dataset as a function of the absolute accuracy.
The standard error of each model pair against their observed accuracy difference. Pairs below a reference line differ by more than the corresponding number of standard errors, i.e. they are statistically distinguishable at that level.
| model | pass1 | pass@count | win_rate | count | SE(A) | SE_x(A) | SE_pred(A) |
|---|---|---|---|---|---|---|---|
| qwen3-32b | 94.2 | 100 | 40.7 | 11 | 2.4 | 1.8 | 1.6 |
| qwen3-14b | 90.9 | 98.9 | 38.2 | 12 | 3 | 2.4 | 1.8 |
| qwen3-8b | 87 | 100 | 36.3 | 12 | 3.5 | 2.6 | 2.4 |
| qwen2.5-coder-32b-instruct | 87 | 95.7 | 35.5 | 11 | 3.5 | 2.9 | 2 |
| qwen2-72b-instruct | 84.8 | 96.7 | 34.8 | 11 | 3.7 | 2.8 | 2.4 |
| google_gemma_3_27b_it | 84 | 92.4 | 33.3 | 12 | 3.8 | 3.4 | 1.8 |
| deepseek_r1_distill_qwen_32b | 83.6 | 92.4 | 34.6 | 11 | 3.9 | 3.1 | 2.3 |
| deepseek_r1_distill_llama_70b | 83.1 | 92.4 | 34.4 | 11 | 3.9 | 3.2 | 2.2 |
| deepseek_r1_distill_qwen_14b | 80.6 | 92.4 | 32.7 | 11 | 4.1 | 3.3 | 2.5 |
| qwen3-4b | 80 | 93.5 | 31.3 | 12 | 4.2 | 3.3 | 2.6 |
| google_gemma_3_12b_it | 78.5 | 87 | 30.7 | 11 | 4.3 | 3.8 | 2 |
| qwen2.5-coder-14b-instruct | 78.2 | 96.7 | 30.7 | 12 | 4.3 | 3 | 3 |
| google_gemma_2_27b_it | 75 | 94.6 | 29.4 | 10 | 4.5 | 3.4 | 2.9 |
| qwen2-math-72b-instruct | 74.6 | 100 | 29.9 | 11 | 4.5 | 2.7 | 3.7 |
| mistralai_mixtral_8x22b_instruct_v0.1 | 74 | 93.5 | 29.7 | 11 | 4.6 | 3.3 | 3.2 |
| qwen1.5-72b-chat | 70.6 | 92.4 | 27.1 | 11 | 4.8 | 3.3 | 3.4 |
| qwen1.5-32b-chat | 70.3 | 93.5 | 26.8 | 11 | 4.8 | 3.3 | 3.4 |
| google_gemma_2_9b_it | 69.9 | 89.1 | 26.3 | 11 | 4.8 | 3.6 | 3.2 |
| deepseek_r1_distill_qwen_7b | 67.3 | 92.4 | 25.8 | 11 | 4.9 | 3.6 | 3.3 |
| deepseek_r1_distill_llama_8b | 66.8 | 92.4 | 25.5 | 13 | 4.9 | 3.4 | 3.5 |
| google_gemma_3_4b_it | 66.1 | 87 | 24.8 | 13 | 4.9 | 3.8 | 3.2 |
| llama-3.1-8B-instruct | 65.2 | 65.2 | 24.2 | 15 | 5 | 5 | 0 |
| qwen2.5-coder-7b-instruct | 62.5 | 95.7 | 23.3 | 10 | 5 | 3.2 | 3.9 |
| qwen3-1.7b | 60.3 | 90.2 | 22.1 | 12 | 5.1 | 3.6 | 3.7 |
| mistralai_mathstral_7b_v0.1 | 58.3 | 91.3 | 21.6 | 11 | 5.1 | 3.3 | 4 |
| qwen1.5-14b-chat | 57.5 | 89.1 | 21 | 12 | 5.2 | 3.5 | 3.8 |
| llama-3.2-3B-instruct | 56.5 | 56.5 | 20.1 | 17 | 5.2 | 5.2 | 0 |
| qwen2-math-7b-instruct | 55.4 | 85.9 | 20.5 | 6 | 5.2 | 3.3 | 4 |
| qwen2-7b-instruct | 55.3 | 92.4 | 19.9 | 11 | 5.2 | 3.1 | 4.2 |
| mistralai_mixtral_8x7b_instruct_v0.1 | 53.9 | 92.4 | 20.7 | 12 | 5.2 | 3.2 | 4.1 |
| mistralai_ministral_8b_instruct_2410 | 53.8 | 95.7 | 19.7 | 11 | 5.2 | 2.9 | 4.3 |
| qwen3-0.6b | 47.2 | 84.8 | 17.2 | 13 | 5.2 | 3.7 | 3.7 |
| mistralai_mistral_7b_instruct_v0.3 | 45.8 | 85.9 | 16.6 | 11 | 5.2 | 3.2 | 4.1 |
| mistralai_mistral_7b_instruct_v0.2 | 42.7 | 78.3 | 15.6 | 10 | 5.2 | 3.4 | 3.9 |
| qwen2.5-coder-3b-instruct | 42.2 | 87 | 14.2 | 12 | 5.1 | 3.1 | 4.1 |
| deepseek_v2_lite_chat | 41.7 | 78.3 | 14.8 | 11 | 5.1 | 3.4 | 3.8 |
| qwen1.5-7b-chat | 36.9 | 90.2 | 13.3 | 12 | 5 | 2.9 | 4.1 |
| google_codegemma_1.1_7b_it | 36.2 | 73.9 | 12 | 13 | 5 | 3.3 | 3.8 |
| google_gemma_7b_it | 35.7 | 67.4 | 12.7 | 13 | 5 | 3.6 | 3.4 |
| google_gemma_3_1b_it | 34.8 | 78.3 | 11.9 | 13 | 5 | 3.2 | 3.8 |
| mistralai_mistral_7b_instruct_v0.1 | 33.9 | 83.7 | 11.8 | 11 | 4.9 | 2.8 | 4 |
| google_gemma_2b_it | 33.3 | 43.5 | 10.8 | 13 | 4.9 | 4.6 | 1.8 |
| qwen2-1.5b-instruct | 28.6 | 72.8 | 10 | 13 | 4.7 | 2.7 | 3.9 |
| deepseek_r1_distill_qwen_1.5b | 28.3 | 81.5 | 10.2 | 13 | 4.7 | 2.3 | 4.1 |
| qwen2.5-coder-1.5b-instruct | 28.3 | 81.5 | 9.78 | 11 | 4.7 | 2.4 | 4.1 |
| llama-3.2-1B-instruct | 25 | 25 | 9.95 | 12 | 4.5 | 4.5 | 0 |
| qwen1.5-1.8b-chat | 19.4 | 73.9 | 7.2 | 11 | 4.1 | 1.9 | 3.7 |
| qwen2-0.5b-instruct | 15.9 | 76.1 | 6.2 | 13 | 3.8 | 1.2 | 3.6 |
| qwen2.5-coder-0.5b-instruct | 13.4 | 80.4 | 5.35 | 13 | 3.5 | 0.58 | 3.5 |
| qwen2-math-1.5b-instruct | 12.2 | 29.3 | 4.41 | 4 | 3.4 | 1.9 | 2.8 |
| qwen1.5-0.5b-chat | 9.95 | 59.8 | 4.46 | 13 | 3.1 | 0.79 | 3 |