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 | 78.5 | 89 | 40.4 | 11 | 3.2 | 2.7 | 1.8 |
| qwen3-14b | 77.8 | 86.6 | 39.9 | 12 | 3.2 | 2.9 | 1.4 |
| qwen2.5-coder-14b-instruct | 76 | 88.4 | 39 | 12 | 3.3 | 2.7 | 2 |
| google_gemma_3_27b_it | 75.6 | 80.5 | 37.7 | 12 | 3.4 | 3.2 | 1.1 |
| qwen2.5-coder-32b-instruct | 75.1 | 86.6 | 38.6 | 11 | 3.4 | 2.7 | 2 |
| google_gemma_3_12b_it | 73.2 | 77.4 | 35.9 | 11 | 3.5 | 3.3 | 1.1 |
| qwen3-8b | 69.9 | 87.2 | 35.4 | 12 | 3.6 | 2.9 | 2.1 |
| qwen3-4b | 69.7 | 82.9 | 34 | 12 | 3.6 | 3.2 | 1.6 |
| google_gemma_2_27b_it | 67.1 | 75 | 31.7 | 10 | 3.7 | 3.4 | 1.5 |
| mistralai_mixtral_8x22b_instruct_v0.1 | 65.6 | 83.5 | 31.1 | 11 | 3.7 | 3 | 2.1 |
| qwen2-math-72b-instruct | 62.1 | 82.3 | 29.5 | 11 | 3.8 | 2.9 | 2.4 |
| deepseek_r1_distill_qwen_32b | 61 | 87.8 | 30.9 | 11 | 3.8 | 2.3 | 3 |
| google_gemma_3_4b_it | 60.6 | 68.9 | 28.2 | 13 | 3.8 | 3.6 | 1.3 |
| llama-3.1-8B-instruct | 57.3 | 57.3 | 26 | 15 | 3.9 | 3.9 | 0 |
| google_gemma_2_9b_it | 55.9 | 65.9 | 25.2 | 11 | 3.9 | 3.6 | 1.4 |
| deepseek_r1_distill_qwen_14b | 53 | 86 | 26.7 | 11 | 3.9 | 2.3 | 3.1 |
| qwen3-1.7b | 50.4 | 73.8 | 22.6 | 12 | 3.9 | 3.3 | 2 |
| qwen2-7b-instruct | 50 | 84.8 | 22.9 | 11 | 3.9 | 2.5 | 3 |
| deepseek_r1_distill_llama_70b | 49.6 | 86 | 24.9 | 11 | 3.9 | 2.2 | 3.2 |
| qwen2-72b-instruct | 48.2 | 84.1 | 23.3 | 11 | 3.9 | 2.2 | 3.2 |
| qwen2.5-coder-7b-instruct | 48.1 | 86.6 | 22.5 | 10 | 3.9 | 2.2 | 3.3 |
| google_codegemma_1.1_7b_it | 47.4 | 70.1 | 20 | 13 | 3.9 | 3.1 | 2.3 |
| qwen1.5-14b-chat | 45.1 | 75.6 | 19.1 | 12 | 3.9 | 3 | 2.5 |
| qwen2.5-coder-3b-instruct | 43.5 | 81.7 | 19.7 | 12 | 3.9 | 2.3 | 3.1 |
| deepseek_v2_lite_chat | 42.8 | 73.8 | 18 | 11 | 3.9 | 2.8 | 2.7 |
| qwen1.5-32b-chat | 40.9 | 65.2 | 17.5 | 11 | 3.8 | 3.1 | 2.2 |
| mistralai_ministral_8b_instruct_2410 | 39.7 | 80.5 | 17.5 | 11 | 3.8 | 2.3 | 3.1 |
| llama-3.2-3B-instruct | 37.8 | 37.8 | 14.7 | 17 | 3.8 | 3.8 | 0 |
| qwen1.5-72b-chat | 37.7 | 62.2 | 15.6 | 11 | 3.8 | 2.9 | 2.4 |
| deepseek_r1_distill_llama_8b | 37 | 76.8 | 16.6 | 13 | 3.8 | 2.4 | 2.9 |
| google_gemma_3_1b_it | 36 | 43.3 | 14.5 | 13 | 3.7 | 3.5 | 1.3 |
| mistralai_mathstral_7b_v0.1 | 35.9 | 74.4 | 14.9 | 11 | 3.7 | 2.3 | 2.9 |
| qwen2.5-coder-1.5b-instruct | 34.8 | 76.8 | 14.4 | 11 | 3.7 | 2.3 | 2.9 |
| qwen1.5-7b-chat | 34.1 | 65.2 | 13.4 | 12 | 3.7 | 2.9 | 2.3 |
| mistralai_mistral_7b_instruct_v0.3 | 31.6 | 59.1 | 11.8 | 11 | 3.6 | 2.8 | 2.3 |
| mistralai_mixtral_8x7b_instruct_v0.1 | 31.6 | 54.9 | 13 | 12 | 3.6 | 2.8 | 2.3 |
| qwen2.5-coder-0.5b-instruct | 31 | 68.3 | 12.7 | 13 | 3.6 | 2.3 | 2.8 |
| qwen2-math-7b-instruct | 29.6 | 56.1 | 12 | 6 | 3.6 | 2.5 | 2.5 |
| deepseek_r1_distill_qwen_7b | 26.9 | 71.3 | 11.9 | 11 | 3.5 | 2 | 2.9 |
| llama-3.2-1B-instruct | 25.6 | 25.6 | 9.17 | 12 | 3.4 | 3.4 | 0 |
| mistralai_mistral_7b_instruct_v0.1 | 22.4 | 51.8 | 7.7 | 11 | 3.3 | 2.3 | 2.3 |
| qwen3-0.6b | 21.4 | 48.2 | 7.64 | 13 | 3.2 | 2.3 | 2.3 |
| google_gemma_7b_it | 20.3 | 40.2 | 6.93 | 13 | 3.1 | 2.6 | 1.8 |
| qwen2-1.5b-instruct | 14.1 | 57.9 | 5.9 | 13 | 2.7 | 1.2 | 2.4 |
| google_gemma_2b_it | 13.9 | 26.2 | 4.02 | 13 | 2.7 | 2.3 | 1.4 |
| qwen2-0.5b-instruct | 7.41 | 30.5 | 2.27 | 13 | 2 | 1.1 | 1.7 |
| mistralai_mistral_7b_instruct_v0.2 | 6.95 | 28.7 | 2.49 | 10 | 2 | 0.98 | 1.7 |
| qwen1.5-1.8b-chat | 4.99 | 22.6 | 1.51 | 11 | 1.7 | 0.88 | 1.5 |
| qwen2-math-1.5b-instruct | 3.35 | 8.54 | 1.35 | 4 | 1.4 | 0.89 | 1.1 |
| deepseek_r1_distill_qwen_1.5b | 2.58 | 19.5 | 0.799 | 13 | 1.2 | 0.42 | 1.2 |
| qwen1.5-0.5b-chat | 1.92 | 7.93 | 0.349 | 13 | 1.1 | 0.77 | 0.74 |