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_12b_it | 27.6 | 56.9 | 22.9 | 11 | 2 | 1.4 | 1.4 |
| qwen2-72b-instruct | 25.4 | 59 | 21 | 10 | 1.9 | 1.3 | 1.4 |
| qwen3-32b | 24.9 | 58.6 | 20.6 | 10 | 1.9 | 1.3 | 1.4 |
| qwen3-14b | 24.6 | 53.4 | 20.1 | 12 | 1.9 | 1.4 | 1.3 |
| qwen2.5-coder-32b-instruct | 23.7 | 51.1 | 19.2 | 10 | 1.9 | 1.3 | 1.3 |
| qwen3-4b | 21.7 | 49.9 | 17.5 | 12 | 1.8 | 1.3 | 1.3 |
| qwen3-8b | 17.4 | 46.4 | 14 | 12 | 1.7 | 1.2 | 1.2 |
| qwen2.5-coder-14b-instruct | 16.8 | 48.5 | 13.3 | 12 | 1.6 | 1 | 1.3 |
| qwen1.5-32b-chat | 13.5 | 44.1 | 10.9 | 11 | 1.5 | 0.93 | 1.2 |
| qwen1.5-72b-chat | 13.4 | 41.4 | 10.7 | 10 | 1.5 | 0.92 | 1.2 |
| google_gemma_7b_it | 13 | 33.4 | 10.9 | 13 | 1.5 | 1.1 | 1 |
| google_gemma_2_27b_it | 12.7 | 37.7 | 10.4 | 10 | 1.5 | 0.99 | 1.1 |
| qwen2-math-72b-instruct | 11.4 | 22.9 | 9.05 | 10 | 1.4 | 1.1 | 0.85 |
| qwen2.5-coder-7b-instruct | 11.2 | 39.8 | 8.76 | 10 | 1.4 | 0.75 | 1.2 |
| google_gemma_3_4b_it | 11.1 | 38.1 | 8.85 | 13 | 1.4 | 0.86 | 1.1 |
| llama-3.1-8B-instruct | 10.5 | 10.5 | 8.59 | 15 | 1.4 | 1.4 | 0 |
| google_gemma_2_9b_it | 9.29 | 29.5 | 7.51 | 11 | 1.3 | 0.87 | 0.94 |
| qwen1.5-14b-chat | 9.17 | 38.8 | 7.42 | 12 | 1.3 | 0.69 | 1.1 |
| mistralai_mixtral_8x22b_instruct_v0.1 | 8.93 | 37.5 | 7.07 | 11 | 1.3 | 0.65 | 1.1 |
| qwen2-1.5b-instruct | 7.57 | 38.4 | 6.5 | 13 | 1.2 | 0.59 | 1 |
| google_codegemma_1.1_7b_it | 7.45 | 38.3 | 6 | 13 | 1.2 | 0.5 | 1 |
| qwen2-7b-instruct | 7.13 | 31.1 | 5.52 | 11 | 1.1 | 0.59 | 0.97 |
| deepseek_r1_distill_qwen_32b | 6.64 | 19.8 | 4.9 | 10 | 1.1 | 0.73 | 0.82 |
| mistralai_mistral_7b_instruct_v0.3 | 6.62 | 28.7 | 5.33 | 11 | 1.1 | 0.55 | 0.95 |
| qwen3-1.7b | 6.62 | 22.7 | 5.05 | 12 | 1.1 | 0.74 | 0.81 |
| qwen1.5-7b-chat | 6.57 | 34.4 | 5.29 | 12 | 1.1 | 0.5 | 0.97 |
| llama-3.2-3B-instruct | 6.41 | 6.41 | 5.07 | 17 | 1.1 | 1.1 | 0 |
| deepseek_v2_lite_chat | 6.41 | 31.5 | 5.21 | 11 | 1.1 | 0.47 | 0.97 |
| qwen2-math-7b-instruct | 6.15 | 14 | 4.61 | 6 | 1.1 | 0.76 | 0.74 |
| deepseek_r1_distill_qwen_14b | 6.02 | 19.2 | 4.48 | 11 | 1 | 0.68 | 0.79 |
| mistralai_ministral_8b_instruct_2410 | 5.63 | 31.1 | 4.41 | 11 | 1 | 0.45 | 0.91 |
| mistralai_mistral_7b_instruct_v0.1 | 5.53 | 28.2 | 4.49 | 11 | 1 | 0.45 | 0.9 |
| deepseek_r1_distill_llama_70b | 5.48 | 17.3 | 3.98 | 10 | 1 | 0.66 | 0.75 |
| mistralai_mistral_7b_instruct_v0.2 | 5.32 | 23.5 | 4.33 | 10 | 0.99 | 0.5 | 0.85 |
| qwen2.5-coder-3b-instruct | 5.16 | 29.5 | 3.92 | 12 | 0.97 | 0.42 | 0.88 |
| google_gemma_2b_it | 5.11 | 13.2 | 4.1 | 13 | 0.97 | 0.74 | 0.62 |
| mistralai_mathstral_7b_v0.1 | 5.07 | 28 | 3.98 | 11 | 0.97 | 0.38 | 0.89 |
| qwen2-0.5b-instruct | 4.9 | 27 | 4.03 | 13 | 0.95 | 0.41 | 0.86 |
| qwen1.5-1.8b-chat | 4.31 | 22.3 | 3.5 | 11 | 0.89 | 0.35 | 0.82 |
| llama-3.2-1B-instruct | 4.27 | 4.27 | 3.47 | 12 | 0.89 | 0.89 | 0 |
| google_gemma_3_1b_it | 4.22 | 19.2 | 3.15 | 12 | 0.89 | 0.51 | 0.72 |
| deepseek_r1_distill_qwen_7b | 4.17 | 12.6 | 2.95 | 11 | 0.88 | 0.59 | 0.66 |
| qwen2-math-1.5b-instruct | 4.03 | 9.13 | 2.95 | 4 | 0.87 | 0.54 | 0.67 |
| qwen1.5-0.5b-chat | 3.91 | 20.6 | 3.26 | 13 | 0.85 | 0.37 | 0.77 |
| deepseek_r1_distill_llama_8b | 3.54 | 17.1 | 2.57 | 12 | 0.81 | 0.43 | 0.69 |
| qwen3-0.6b | 2.66 | 15.5 | 1.94 | 13 | 0.71 | 0.37 | 0.61 |
| deepseek_r1_distill_qwen_1.5b | 2.25 | 10.3 | 1.57 | 12 | 0.65 | 0.35 | 0.55 |
| qwen2.5-coder-1.5b-instruct | 1.8 | 11.8 | 1.33 | 11 | 0.59 | 0.23 | 0.54 |
| qwen2.5-coder-0.5b-instruct | 1.69 | 13.2 | 1.33 | 13 | 0.57 | 0.17 | 0.54 |