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) |
|---|---|---|---|---|---|---|---|
| qwen3-14b | 77.2 | 84.1 | 44.4 | 3 | 3.3 | 2.8 | 1.7 |
| google_gemma_3_27b_it | 75 | 78.7 | 41.8 | 3 | 3.4 | 3.2 | 1.2 |
| qwen2.5-coder-32b-instruct | 74.1 | 82.9 | 42.6 | 2 | 3.4 | 2.5 | 2.3 |
| qwen3-32b | 73.4 | 83.5 | 41.7 | 3 | 3.5 | 2.6 | 2.3 |
| google_gemma_3_12b_it | 72.9 | 76.8 | 40.2 | 4 | 3.5 | 3.3 | 1.2 |
| qwen3-4b | 69.4 | 78.7 | 38.1 | 4 | 3.6 | 3.1 | 1.8 |
| qwen3-8b | 68.9 | 81.7 | 38.7 | 3 | 3.6 | 2.8 | 2.3 |
| qwen2.5-coder-14b-instruct | 68.1 | 85.4 | 38.7 | 3 | 3.6 | 2.3 | 2.9 |
| google_gemma_2_27b_it | 66.8 | 72 | 35.9 | 2 | 3.7 | 3.2 | 1.8 |
| google_gemma_3_4b_it | 60.9 | 67.1 | 32.1 | 5 | 3.8 | 3.5 | 1.5 |
| mistralai_mixtral_8x22b_instruct_v0.1 | 60 | 76.2 | 31.4 | 3 | 3.8 | 2.7 | 2.7 |
| google_gemma_2_9b_it | 56.1 | 65.2 | 29 | 4 | 3.9 | 3.5 | 1.7 |
| llama-3.1-8B-instruct | 50.6 | 50.6 | 24.8 | 7 | 3.9 | 3.9 | 0 |
| qwen3-1.7b | 50.5 | 67.1 | 25.6 | 4 | 3.9 | 3.2 | 2.2 |
| deepseek_r1_distill_qwen_32b | 47 | 67.7 | 25.4 | 2 | 3.9 | 1.6 | 3.6 |
| qwen2-math-72b-instruct | 45.7 | 61.6 | 24.4 | 2 | 3.9 | 2.3 | 3.1 |
| google_codegemma_1.1_7b_it | 44.9 | 64 | 21.4 | 5 | 3.9 | 3.1 | 2.4 |
| qwen2-72b-instruct | 43.3 | 62.8 | 23.2 | 2 | 3.9 | 1.8 | 3.4 |
| deepseek_r1_distill_qwen_14b | 43.1 | 76.2 | 23.8 | 4 | 3.9 | 1.8 | 3.4 |
| deepseek_r1_distill_llama_70b | 43 | 61 | 24.1 | 2 | 3.9 | 2 | 3.3 |
| qwen1.5-14b-chat | 42.3 | 59.8 | 19.9 | 3 | 3.9 | 2.9 | 2.5 |
| qwen1.5-32b-chat | 41.5 | 57.9 | 20.7 | 3 | 3.8 | 2.8 | 2.6 |
| deepseek_v2_lite_chat | 36.2 | 54.3 | 17 | 3 | 3.8 | 2.6 | 2.7 |
| qwen2-7b-instruct | 35.5 | 67.1 | 17.9 | 4 | 3.7 | 1.9 | 3.2 |
| google_gemma_3_1b_it | 35.5 | 39 | 16.4 | 4 | 3.7 | 3.5 | 1.3 |
| qwen2.5-coder-7b-instruct | 35.4 | 66.5 | 17.5 | 4 | 3.7 | 2.1 | 3.1 |
| qwen1.5-72b-chat | 34.1 | 46.3 | 16.1 | 2 | 3.7 | 2.5 | 2.7 |
| qwen2.5-coder-3b-instruct | 33.7 | 67.1 | 17.4 | 4 | 3.7 | 1.8 | 3.2 |
| llama-3.2-3B-instruct | 33.5 | 33.5 | 15.1 | 10 | 3.7 | 3.7 | 0 |
| mistralai_ministral_8b_instruct_2410 | 32 | 63.4 | 15.7 | 4 | 3.6 | 1.9 | 3.1 |
| mistralai_mixtral_8x7b_instruct_v0.1 | 30.3 | 45.1 | 14.2 | 3 | 3.6 | 2.7 | 2.4 |
| mistralai_mistral_7b_instruct_v0.3 | 30.2 | 52.4 | 13.2 | 4 | 3.6 | 2.6 | 2.5 |
| qwen1.5-7b-chat | 29.7 | 45.7 | 13.3 | 3 | 3.6 | 2.5 | 2.5 |
| deepseek_r1_distill_llama_8b | 24.4 | 55.5 | 12.2 | 4 | 3.4 | 1.6 | 2.9 |
| mistralai_mathstral_7b_v0.1 | 23.8 | 49.4 | 10.4 | 4 | 3.3 | 1.8 | 2.8 |
| qwen2-math-7b-instruct | 23.5 | 34.1 | 10.9 | 2 | 3.3 | 2.1 | 2.6 |
| qwen2.5-coder-1.5b-instruct | 22.4 | 50.6 | 10.3 | 4 | 3.3 | 1.6 | 2.8 |
| deepseek_r1_distill_qwen_7b | 20.7 | 48.8 | 10.2 | 4 | 3.2 | 1.5 | 2.8 |
| google_gemma_7b_it | 20.4 | 32.3 | 8.83 | 4 | 3.1 | 2.5 | 1.9 |
| llama-3.2-1B-instruct | 20.1 | 20.1 | 8.17 | 13 | 3.1 | 3.1 | 0 |
| qwen2.5-coder-0.5b-instruct | 18.4 | 45.7 | 8.18 | 5 | 3 | 1.4 | 2.7 |
| qwen3-0.6b | 17.1 | 39.6 | 7.15 | 5 | 2.9 | 1.9 | 2.3 |
| mistralai_mistral_7b_instruct_v0.1 | 13.6 | 29.9 | 5.29 | 4 | 2.7 | 1.5 | 2.2 |
| google_gemma_2b_it | 13.3 | 20.7 | 4.63 | 4 | 2.6 | 2.2 | 1.5 |
| mistralai_mistral_7b_instruct_v0.2 | 7.93 | 20.1 | 2.95 | 4 | 2.1 | 1.1 | 1.8 |
| qwen2-1.5b-instruct | 5.79 | 18.9 | 2.42 | 4 | 1.8 | 0.54 | 1.7 |
| qwen1.5-1.8b-chat | 3.66 | 7.93 | 1.27 | 3 | 1.5 | 0.73 | 1.3 |
| qwen2-0.5b-instruct | 2.68 | 8.54 | 0.851 | 5 | 1.3 | 0.57 | 1.1 |
| qwen2-math-1.5b-instruct | 1.63 | 3.05 | 0.621 | 3 | 0.99 | 0.69 | 0.7 |
| qwen1.5-0.5b-chat | 1.22 | 3.66 | 0.356 | 5 | 0.86 | 0.42 | 0.75 |
| deepseek_r1_distill_qwen_1.5b | 0.457 | 1.83 | 0.162 | 4 | 0.53 | 0 | 0.53 |