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 | 87.5 | 97.6 | 42.9 | 11 | 2.6 | 1.9 | 1.8 |
| google_gemma_3_27b_it | 86.5 | 89.6 | 41.4 | 12 | 2.7 | 2.5 | 0.79 |
| qwen3-14b | 86 | 94.5 | 41.7 | 12 | 2.7 | 2.3 | 1.5 |
| qwen2.5-coder-32b-instruct | 83.3 | 95.7 | 41 | 11 | 2.9 | 1.9 | 2.2 |
| google_gemma_3_12b_it | 82.8 | 87.8 | 38.7 | 11 | 2.9 | 2.7 | 1.1 |
| qwen2.5-coder-14b-instruct | 82.3 | 95.7 | 39.9 | 12 | 3 | 1.9 | 2.3 |
| qwen3-4b | 78.9 | 92.1 | 36.7 | 12 | 3.2 | 2.7 | 1.7 |
| qwen3-8b | 77.6 | 95.1 | 36.6 | 12 | 3.3 | 2.5 | 2.1 |
| google_gemma_2_27b_it | 75.2 | 82.3 | 33.7 | 10 | 3.4 | 3.1 | 1.4 |
| mistralai_mixtral_8x22b_instruct_v0.1 | 74.2 | 90.2 | 33.4 | 11 | 3.4 | 2.6 | 2.2 |
| qwen2-math-72b-instruct | 70.6 | 93.3 | 31.8 | 11 | 3.6 | 2.4 | 2.6 |
| deepseek_r1_distill_qwen_32b | 70.2 | 97.6 | 33.8 | 11 | 3.6 | 1.8 | 3.1 |
| google_gemma_3_4b_it | 69.6 | 77.4 | 30.5 | 13 | 3.6 | 3.3 | 1.4 |
| llama-3.1-8B-instruct | 65.9 | 65.9 | 28 | 15 | 3.7 | 3.7 | 0 |
| google_gemma_2_9b_it | 63.1 | 71.3 | 26.6 | 11 | 3.8 | 3.5 | 1.4 |
| deepseek_r1_distill_qwen_14b | 58.6 | 94.5 | 27.7 | 11 | 3.8 | 2 | 3.3 |
| qwen2-7b-instruct | 57.7 | 92.7 | 24.7 | 11 | 3.9 | 2.3 | 3.1 |
| qwen3-1.7b | 57.1 | 81.7 | 23.9 | 12 | 3.9 | 3.2 | 2.1 |
| google_codegemma_1.1_7b_it | 56.4 | 78.7 | 22.3 | 13 | 3.9 | 3.1 | 2.3 |
| qwen2-72b-instruct | 55 | 95.1 | 25.6 | 11 | 3.9 | 2 | 3.3 |
| deepseek_r1_distill_llama_70b | 54.4 | 93.3 | 25.1 | 11 | 3.9 | 2 | 3.3 |
| qwen2.5-coder-7b-instruct | 54 | 92.7 | 23.5 | 10 | 3.9 | 2.1 | 3.3 |
| qwen1.5-14b-chat | 52.1 | 79.9 | 20.3 | 12 | 3.9 | 3.1 | 2.4 |
| qwen2.5-coder-3b-instruct | 50 | 91.5 | 21.3 | 12 | 3.9 | 2.2 | 3.2 |
| deepseek_v2_lite_chat | 48.8 | 81.7 | 19.2 | 11 | 3.9 | 2.7 | 2.8 |
| qwen1.5-32b-chat | 48.2 | 73.8 | 19.1 | 11 | 3.9 | 3.2 | 2.3 |
| mistralai_ministral_8b_instruct_2410 | 46.1 | 87.8 | 19.2 | 11 | 3.9 | 2.3 | 3.1 |
| llama-3.2-3B-instruct | 45.7 | 45.7 | 16.9 | 17 | 3.9 | 3.9 | 0 |
| mistralai_mathstral_7b_v0.1 | 44 | 82.3 | 17.1 | 11 | 3.9 | 2.3 | 3.1 |
| qwen2.5-coder-1.5b-instruct | 43.1 | 84.8 | 16.6 | 11 | 3.9 | 2.3 | 3.1 |
| deepseek_r1_distill_llama_8b | 42.6 | 88.4 | 18.1 | 13 | 3.9 | 2.2 | 3.2 |
| qwen1.5-72b-chat | 42.6 | 70.1 | 16.6 | 11 | 3.9 | 3 | 2.5 |
| mistralai_mistral_7b_instruct_v0.3 | 41.6 | 67.7 | 14.8 | 11 | 3.8 | 3.1 | 2.2 |
| google_gemma_3_1b_it | 41.3 | 50 | 15.4 | 13 | 3.8 | 3.6 | 1.4 |
| qwen1.5-7b-chat | 39.8 | 69.5 | 14.4 | 12 | 3.8 | 2.9 | 2.4 |
| mistralai_mixtral_8x7b_instruct_v0.1 | 38.7 | 67.1 | 14.9 | 12 | 3.8 | 2.8 | 2.6 |
| qwen2.5-coder-0.5b-instruct | 36.4 | 77.4 | 13.6 | 13 | 3.8 | 2.3 | 3 |
| qwen2-math-7b-instruct | 32.2 | 65.9 | 12.4 | 6 | 3.6 | 2.4 | 2.8 |
| deepseek_r1_distill_qwen_7b | 31.8 | 75.6 | 13 | 11 | 3.6 | 2 | 3 |
| llama-3.2-1B-instruct | 30.5 | 30.5 | 10.6 | 12 | 3.6 | 3.6 | 0 |
| mistralai_mistral_7b_instruct_v0.1 | 28.3 | 63.4 | 9.4 | 11 | 3.5 | 2.4 | 2.6 |
| google_gemma_7b_it | 26.3 | 45.7 | 8.58 | 13 | 3.4 | 2.9 | 1.9 |
| qwen3-0.6b | 25.1 | 56.1 | 8.03 | 13 | 3.4 | 2.5 | 2.3 |
| google_gemma_2b_it | 17 | 31.7 | 4.73 | 13 | 2.9 | 2.4 | 1.6 |
| qwen2-1.5b-instruct | 16.4 | 65.2 | 6.09 | 13 | 2.9 | 1.2 | 2.6 |
| qwen2-0.5b-instruct | 10.3 | 35.4 | 2.82 | 13 | 2.4 | 1.4 | 1.9 |
| mistralai_mistral_7b_instruct_v0.2 | 9.15 | 33.5 | 2.69 | 10 | 2.3 | 1.2 | 1.9 |
| qwen1.5-1.8b-chat | 7.43 | 28 | 2.09 | 11 | 2 | 1.1 | 1.7 |
| qwen2-math-1.5b-instruct | 3.96 | 9.76 | 1.45 | 4 | 1.5 | 0.98 | 1.2 |
| qwen1.5-0.5b-chat | 2.91 | 12.8 | 0.517 | 13 | 1.3 | 0.75 | 1.1 |
| deepseek_r1_distill_qwen_1.5b | 2.67 | 19.5 | 0.804 | 13 | 1.3 | 0.39 | 1.2 |