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 | 85.9 | 35.4 | 2 | 2 | 1.5 | 1.3 |
| qwen3-14b | 75.2 | 83.6 | 32.8 | 3 | 2.2 | 1.8 | 1.2 |
| qwen2-72b-instruct | 74.7 | 74.7 | 33 | 1 | 2.2 | NaN | NaN |
| llama-3.1-70B-instruct | 73.9 | 73.9 | 32.6 | 4 | 2.2 | 2.2 | 0 |
| qwen3-8b | 72.1 | 84.9 | 31 | 3 | 2.2 | 1.7 | 1.4 |
| deepseek_r1_distill_llama_70b | 72 | 76.4 | 30.5 | 2 | 2.2 | 2 | 1.1 |
| qwen3-4b | 69.9 | 82.6 | 29.9 | 4 | 2.3 | 1.8 | 1.3 |
| deepseek_r1_distill_qwen_32b | 68.7 | 75.9 | 28.8 | 2 | 2.3 | 1.9 | 1.3 |
| qwen2.5-coder-32b-instruct | 68.6 | 76.2 | 28.8 | 2 | 2.3 | 1.9 | 1.4 |
| google_gemma_3_12b_it | 68.2 | 74.9 | 28.5 | 2 | 2.3 | 1.9 | 1.3 |
| deepseek_r1_distill_qwen_14b | 64.1 | 78.9 | 25.9 | 4 | 2.4 | 1.8 | 1.5 |
| mistralai_mixtral_8x22b_instruct_v0.1 | 63.8 | 71.2 | 25.7 | 2 | 2.4 | 2 | 1.4 |
| qwen2.5-coder-14b-instruct | 61 | 74.9 | 24.3 | 3 | 2.4 | 1.9 | 1.5 |
| qwen1.5-14b-chat | 57.6 | 67.5 | 22.4 | 3 | 2.5 | 2.1 | 1.2 |
| mistralai_mixtral_8x7b_instruct_v0.1 | 57.5 | 65 | 22.1 | 3 | 2.5 | 2.2 | 1 |
| qwen2-7b-instruct | 56.5 | 72 | 21.9 | 4 | 2.5 | 2 | 1.4 |
| qwen2.5-coder-7b-instruct | 53.4 | 70.5 | 20.3 | 4 | 2.5 | 2 | 1.5 |
| llama-3.1-8B-instruct | 51.9 | 51.9 | 20 | 7 | 2.5 | 2.5 | 0 |
| qwen3-1.7b | 50.7 | 73.4 | 20.1 | 4 | 2.5 | 1.8 | 1.7 |
| qwen1.5-7b-chat | 49.1 | 61.8 | 18.3 | 3 | 2.5 | 2.1 | 1.4 |
| mistralai_mistral_7b_instruct_v0.3 | 48.9 | 63.5 | 17.8 | 4 | 2.5 | 2.1 | 1.3 |
| google_gemma_3_4b_it | 47.3 | 67.7 | 18.1 | 5 | 2.5 | 2 | 1.5 |
| mistralai_mistral_7b_instruct_v0.2 | 47 | 53.1 | 17.5 | 4 | 2.5 | 2.3 | 0.92 |
| mistralai_mathstral_7b_v0.1 | 46.5 | 71.5 | 18.1 | 4 | 2.5 | 1.7 | 1.8 |
| mistralai_ministral_8b_instruct_2410 | 46 | 74.9 | 17.5 | 4 | 2.5 | 1.5 | 2 |
| deepseek_v2_lite_chat | 44.5 | 56.1 | 17.1 | 2 | 2.5 | 1.8 | 1.7 |
| deepseek_r1_distill_llama_8b | 43.9 | 73.7 | 16.3 | 4 | 2.5 | 1.5 | 1.9 |
| llama-3.2-3B-instruct | 43.9 | 43.9 | 16.7 | 8 | 2.5 | 2.5 | 0 |
| deepseek_r1_distill_qwen_7b | 41.4 | 67.7 | 15.7 | 4 | 2.5 | 1.5 | 1.9 |
| qwen2-math-7b-instruct | 40.5 | 60.8 | 15.9 | 3 | 2.4 | 1.7 | 1.8 |
| qwen2.5-coder-3b-instruct | 35.7 | 69 | 13.7 | 4 | 2.4 | 1.3 | 2 |
| qwen3-0.6b | 35 | 56.6 | 13.7 | 5 | 2.4 | 1.8 | 1.5 |
| mistralai_mistral_7b_instruct_v0.1 | 34 | 66.3 | 13 | 4 | 2.4 | 1.3 | 1.9 |
| qwen2-1.5b-instruct | 32.3 | 62.5 | 12.3 | 4 | 2.3 | 1.4 | 1.9 |
| llama-3.2-1B-instruct | 27 | 27 | 11.3 | 11 | 2.2 | 2.2 | 0 |
| qwen2.5-coder-1.5b-instruct | 25.8 | 62.8 | 11.3 | 4 | 2.2 | 0.85 | 2 |
| qwen1.5-1.8b-chat | 25.8 | 48.9 | 10.6 | 3 | 2.2 | 1.1 | 1.9 |
| qwen2-math-1.5b-instruct | 22 | 45.2 | 9.81 | 3 | 2.1 | 0.98 | 1.8 |
| qwen2.5-coder-0.5b-instruct | 20.3 | 67.5 | 9.97 | 5 | 2 | 0.077 | 2 |
| deepseek_r1_distill_qwen_1.5b | 20.3 | 50.6 | 8.72 | 4 | 2 | 0.79 | 1.8 |
| qwen2-0.5b-instruct | 19.8 | 61 | 9.09 | 5 | 2 | 0.6 | 1.9 |
| qwen1.5-0.5b-chat | 19.2 | 61.8 | 9.3 | 5 | 2 | 0.42 | 1.9 |