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) |
|---|---|---|---|---|---|---|---|
| qwen2-72b-instruct | 79.3 | 81.3 | 46.4 | 2 | 4.7 | 4.4 | 1.6 |
| google_gemma_3_27b_it | 72 | 82.7 | 42 | 3 | 5.2 | 4.1 | 3.2 |
| qwen2-math-72b-instruct | 71.3 | 85.3 | 41.2 | 2 | 5.2 | 2.9 | 4.3 |
| qwen3-8b | 70.2 | 81.3 | 40.1 | 3 | 5.3 | 4.1 | 3.3 |
| qwen3-4b | 70 | 86.7 | 39.9 | 4 | 5.3 | 3.8 | 3.7 |
| qwen3-14b | 69.3 | 77.3 | 39 | 3 | 5.3 | 4.6 | 2.7 |
| qwen3-32b | 65.8 | 84 | 37.1 | 3 | 5.5 | 3.7 | 4 |
| qwen2.5-coder-32b-instruct | 62 | 72 | 34.8 | 2 | 5.6 | 4.3 | 3.7 |
| google_gemma_2_27b_it | 58 | 70.7 | 31.9 | 2 | 5.7 | 3.9 | 4.1 |
| google_gemma_3_12b_it | 57.3 | 78.7 | 31.9 | 4 | 5.7 | 4.1 | 3.9 |
| qwen2.5-coder-14b-instruct | 56.9 | 73.3 | 30.7 | 3 | 5.7 | 4.3 | 3.8 |
| mistralai_mixtral_8x22b_instruct_v0.1 | 56 | 74.7 | 30.6 | 3 | 5.7 | 4 | 4.1 |
| qwen1.5-72b-chat | 55.3 | 64 | 30.3 | 2 | 5.7 | 4.6 | 3.4 |
| qwen1.5-32b-chat | 55.1 | 66.7 | 29.4 | 3 | 5.7 | 4.8 | 3.1 |
| qwen1.5-14b-chat | 50.7 | 66.7 | 27.2 | 3 | 5.8 | 4.3 | 3.8 |
| qwen2.5-coder-7b-instruct | 48 | 77.3 | 26.4 | 4 | 5.8 | 3.4 | 4.7 |
| qwen2-math-7b-instruct | 47.3 | 58.7 | 25.5 | 2 | 5.8 | 4.3 | 3.9 |
| qwen2-7b-instruct | 46 | 66.7 | 24.6 | 4 | 5.8 | 4.3 | 3.8 |
| qwen3-1.7b | 44.3 | 64 | 23 | 4 | 5.7 | 4.4 | 3.7 |
| google_gemma_2_9b_it | 44 | 73.3 | 24.6 | 4 | 5.7 | 3.4 | 4.6 |
| qwen1.5-7b-chat | 43.1 | 58.7 | 23.6 | 3 | 5.7 | 4.2 | 3.9 |
| mistralai_mathstral_7b_v0.1 | 39.3 | 65.3 | 20.7 | 4 | 5.6 | 3.7 | 4.3 |
| llama-3.1-8B-instruct | 38.7 | 38.7 | 20.8 | 7 | 5.6 | 5.6 | 0 |
| deepseek_v2_lite_chat | 37.8 | 62.7 | 21.1 | 3 | 5.6 | 3.4 | 4.4 |
| mistralai_mistral_7b_instruct_v0.3 | 37.7 | 54.7 | 18.9 | 4 | 5.6 | 4.4 | 3.4 |
| qwen3-0.6b | 37.3 | 65.3 | 20.3 | 5 | 5.6 | 3.6 | 4.2 |
| mistralai_ministral_8b_instruct_2410 | 36.7 | 78.7 | 19.8 | 4 | 5.6 | 2.5 | 5 |
| google_gemma_3_4b_it | 36 | 53.3 | 19.6 | 5 | 5.5 | 4.2 | 3.6 |
| llama-3.2-3B-instruct | 32 | 32 | 16 | 10 | 5.4 | 5.4 | 0 |
| qwen2.5-coder-3b-instruct | 31.7 | 62.7 | 16.5 | 4 | 5.4 | 2.9 | 4.5 |
| qwen2-math-1.5b-instruct | 29.8 | 49.3 | 16.2 | 3 | 5.3 | 3.3 | 4.1 |
| mistralai_mixtral_8x7b_instruct_v0.1 | 27.6 | 50.7 | 15.3 | 3 | 5.2 | 3 | 4.2 |
| google_codegemma_1.1_7b_it | 26.1 | 61.3 | 14.2 | 5 | 5.1 | 2.8 | 4.2 |
| qwen2.5-coder-1.5b-instruct | 25 | 68 | 14.3 | 4 | 5 | 0 | 5 |
| google_gemma_7b_it | 23.7 | 37.3 | 11.9 | 4 | 4.9 | 3.8 | 3.1 |
| mistralai_mistral_7b_instruct_v0.2 | 23.3 | 41.3 | 11.5 | 4 | 4.9 | 3.2 | 3.7 |
| qwen2-1.5b-instruct | 21.7 | 52 | 11.7 | 4 | 4.8 | 2 | 4.3 |
| mistralai_mistral_7b_instruct_v0.1 | 20 | 52 | 10.5 | 4 | 4.6 | 1.9 | 4.2 |
| llama-3.2-1B-instruct | 18.7 | 18.7 | 10.1 | 13 | 4.5 | 4.5 | 0 |
| google_gemma_2b_it | 17.7 | 33.3 | 10.7 | 4 | 4.4 | 2.9 | 3.3 |
| qwen1.5-0.5b-chat | 17.3 | 57.3 | 11.1 | 5 | 4.4 | 1.2 | 4.2 |
| deepseek_r1_distill_llama_70b | 16.7 | 24 | 8.03 | 2 | 4.3 | 3 | 3.1 |
| qwen2.5-coder-0.5b-instruct | 16.3 | 57.3 | 10.6 | 5 | 4.3 | 0.17 | 4.3 |
| qwen2-0.5b-instruct | 16 | 57.3 | 9.53 | 5 | 4.2 | 0.57 | 4.2 |
| google_gemma_3_1b_it | 16 | 33.3 | 10.2 | 4 | 4.2 | 2.7 | 3.3 |
| qwen1.5-1.8b-chat | 13.8 | 34.7 | 7.67 | 3 | 4 | 1 | 3.8 |
| deepseek_r1_distill_qwen_32b | 12.7 | 22.7 | 6.6 | 2 | 3.8 | 1.2 | 3.7 |
| deepseek_r1_distill_qwen_14b | 8.67 | 28 | 4.49 | 4 | 3.2 | 0.69 | 3.2 |
| deepseek_r1_distill_qwen_7b | 7.33 | 21.3 | 3.17 | 4 | 3 | 1.4 | 2.7 |
| deepseek_r1_distill_llama_8b | 7 | 21.3 | 3.19 | 4 | 2.9 | 0.91 | 2.8 |
| deepseek_r1_distill_qwen_1.5b | 4.67 | 14.7 | 2.2 | 4 | 2.4 | 0.77 | 2.3 |