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) |
|---|---|---|---|---|---|---|---|
| google_gemma_3_27b_it | 85.3 | 94.2 | 42.2 | 11 | 1.6 | 1.3 | 0.92 |
| deepseek_r1_distill_qwen_32b | 83.9 | 95.2 | 41.3 | 10 | 1.6 | 1.2 | 1.1 |
| qwen3-32b | 81.9 | 92.8 | 39.4 | 9 | 1.7 | 1.3 | 1.1 |
| deepseek_r1_distill_llama_70b | 81.1 | 94.2 | 39.4 | 10 | 1.7 | 1.3 | 1.2 |
| qwen3-14b | 81 | 93 | 38.7 | 11 | 1.8 | 1.4 | 1.1 |
| qwen2-math-72b-instruct | 80.4 | 91.4 | 38.1 | 7 | 1.8 | 1.5 | 1 |
| qwen3-8b | 79.2 | 93.4 | 37.3 | 11 | 1.8 | 1.5 | 1.1 |
| google_gemma_3_12b_it | 79 | 92 | 37.3 | 12 | 1.8 | 1.5 | 1 |
| deepseek_r1_distill_qwen_14b | 78.9 | 94.2 | 37.9 | 12 | 1.8 | 1.3 | 1.3 |
| qwen3-4b | 77.2 | 92.2 | 36 | 12 | 1.9 | 1.5 | 1.1 |
| deepseek_r1_distill_qwen_7b | 77.1 | 93 | 36.5 | 12 | 1.9 | 1.4 | 1.3 |
| qwen2.5-coder-32b-instruct | 76.1 | 90.2 | 35 | 10 | 1.9 | 1.5 | 1.2 |
| qwen2.5-coder-14b-instruct | 71.3 | 89 | 31.7 | 11 | 2 | 1.6 | 1.2 |
| deepseek_r1_distill_llama_8b | 70.4 | 91.2 | 32.7 | 12 | 2 | 1.5 | 1.4 |
| qwen2-math-1.5b-instruct | 68 | 68 | 29.7 | 1 | 2.1 | NaN | NaN |
| deepseek_r1_distill_qwen_1.5b | 67.6 | 89.6 | 30.1 | 12 | 2.1 | 1.5 | 1.4 |
| qwen3-1.7b | 66.7 | 87 | 29.1 | 12 | 2.1 | 1.6 | 1.3 |
| llama-3.1-70B-instruct | 65.6 | 65.8 | 28.7 | 12 | 2.1 | 2.1 | 0.21 |
| google_gemma_3_4b_it | 65.1 | 84.8 | 29.1 | 12 | 2.1 | 1.7 | 1.3 |
| qwen2-72b-instruct | 64.5 | 83.6 | 27.2 | 10 | 2.1 | 1.7 | 1.3 |
| qwen2.5-coder-7b-instruct | 61 | 86.8 | 25.7 | 12 | 2.2 | 1.6 | 1.5 |
| google_gemma_2_27b_it | 52.3 | 74.2 | 20.4 | 10 | 2.2 | 1.9 | 1.2 |
| qwen2-7b-instruct | 51.7 | 80.2 | 20.1 | 12 | 2.2 | 1.7 | 1.5 |
| mistralai_ministral_8b_instruct_2410 | 49.3 | 79.2 | 18.9 | 12 | 2.2 | 1.7 | 1.5 |
| mistralai_mixtral_8x22b_instruct_v0.1 | 48.1 | 77.8 | 18.4 | 9 | 2.2 | 1.7 | 1.5 |
| llama-3.1-8B-instruct | 47.6 | 58.6 | 18 | 13 | 2.2 | 2 | 1.1 |
| mistralai_mathstral_7b_v0.1 | 47 | 76.6 | 17.7 | 12 | 2.2 | 1.7 | 1.5 |
| qwen2.5-coder-3b-instruct | 46.9 | 80 | 18.4 | 11 | 2.2 | 1.5 | 1.6 |
| google_gemma_2_9b_it | 46.4 | 67.8 | 16.9 | 11 | 2.2 | 1.9 | 1.2 |
| llama-3.2-3B-instruct | 44.1 | 55.6 | 16.6 | 18 | 2.2 | 1.9 | 1.1 |
| qwen1.5-72b-chat | 40.3 | 73 | 14.7 | 10 | 2.2 | 1.6 | 1.5 |
| qwen1.5-32b-chat | 38.9 | 70.4 | 14.1 | 9 | 2.2 | 1.6 | 1.5 |
| qwen3-0.6b | 33.7 | 71.4 | 12.2 | 13 | 2.1 | 1.5 | 1.5 |
| qwen2.5-coder-1.5b-instruct | 32.8 | 66.4 | 11.3 | 12 | 2.1 | 1.5 | 1.5 |
| qwen1.5-14b-chat | 30.5 | 63.6 | 10.3 | 11 | 2.1 | 1.5 | 1.4 |
| llama-3.2-1B-instruct | 27.9 | 28.2 | 9.67 | 11 | 2 | 2 | 0.23 |
| mistralai_mixtral_8x7b_instruct_v0.1 | 25.2 | 61.2 | 8.44 | 11 | 1.9 | 1.3 | 1.4 |
| deepseek_v2_lite_chat | 22.5 | 55.8 | 7.25 | 9 | 1.9 | 1.2 | 1.4 |
| google_codegemma_1.1_7b_it | 20.8 | 52 | 6.55 | 12 | 1.8 | 1.3 | 1.3 |
| qwen1.5-7b-chat | 16.5 | 45.4 | 5.19 | 11 | 1.7 | 1.1 | 1.3 |
| google_gemma_3_1b_it | 14.5 | 43.2 | 5.93 | 12 | 1.6 | 1 | 1.2 |
| mistralai_mistral_7b_instruct_v0.3 | 12.9 | 41 | 3.86 | 12 | 1.5 | 0.95 | 1.2 |
| mistralai_mistral_7b_instruct_v0.2 | 10.1 | 37.6 | 2.98 | 12 | 1.3 | 0.82 | 1.1 |
| qwen2.5-coder-0.5b-instruct | 8.03 | 32.6 | 2.48 | 13 | 1.2 | 0.7 | 1 |
| qwen2-1.5b-instruct | 6.8 | 31.6 | 1.96 | 12 | 1.1 | 0.53 | 0.99 |
| mistralai_mistral_7b_instruct_v0.1 | 6.4 | 26.8 | 1.99 | 12 | 1.1 | 0.58 | 0.93 |
| google_gemma_7b_it | 5.77 | 21.4 | 1.68 | 12 | 1 | 0.68 | 0.79 |
| qwen2-0.5b-instruct | 2.91 | 19.4 | 0.985 | 13 | 0.75 | 0.31 | 0.69 |
| qwen1.5-1.8b-chat | 1.42 | 10.6 | 0.434 | 11 | 0.53 | 0.16 | 0.5 |
| qwen1.5-0.5b-chat | 0.8 | 6.6 | 0.307 | 12 | 0.4 | 0.11 | 0.38 |
| google_gemma_2b_it | 0.117 | 1.4 | 0.047 | 12 | 0.15 | 0 | 0.15 |