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 | 49.4 | 83 | 31.9 | 11 | 2.4 | 1.7 | 1.6 |
| llama-3.1-70B-instruct | 43.8 | 43.8 | 27.6 | 13 | 2.3 | 2.3 | 0 |
| google_gemma_3_27b_it | 43.4 | 71 | 27.5 | 7 | 2.3 | 1.7 | 1.6 |
| qwen3-14b | 41.7 | 67.2 | 25.7 | 11 | 2.3 | 1.9 | 1.4 |
| qwen2-math-72b-instruct | 40.6 | 80.4 | 25.4 | 10 | 2.3 | 1.5 | 1.7 |
| qwen3-8b | 40.1 | 66.3 | 24.8 | 11 | 2.3 | 1.8 | 1.4 |
| qwen2.5-coder-32b-instruct | 39.5 | 72.3 | 24.3 | 10 | 2.3 | 1.7 | 1.6 |
| qwen2-72b-instruct | 39 | 70.1 | 23.5 | 10 | 2.3 | 1.8 | 1.5 |
| google_gemma_3_12b_it | 37.4 | 76.8 | 23.4 | 12 | 2.3 | 1.6 | 1.6 |
| qwen3-4b | 36.7 | 63.2 | 22.5 | 12 | 2.3 | 1.8 | 1.3 |
| qwen2.5-coder-14b-instruct | 34.6 | 82.1 | 21.3 | 11 | 2.2 | 1.3 | 1.8 |
| qwen1.5-32b-chat | 32.5 | 75.9 | 19.7 | 11 | 2.2 | 1.4 | 1.7 |
| mistralai_mixtral_8x22b_instruct_v0.1 | 32.2 | 74.6 | 19.6 | 11 | 2.2 | 1.4 | 1.7 |
| llama-3.1-8B-instruct | 31.7 | 31.7 | 19.9 | 15 | 2.2 | 2.2 | 0 |
| qwen3-1.7b | 31.6 | 66.7 | 20.2 | 12 | 2.2 | 1.6 | 1.5 |
| qwen1.5-72b-chat | 31.5 | 67.4 | 19 | 10 | 2.2 | 1.5 | 1.6 |
| deepseek_r1_distill_qwen_32b | 31.5 | 53.6 | 19 | 10 | 2.2 | 1.8 | 1.3 |
| qwen2.5-coder-7b-instruct | 30.9 | 88.2 | 19.5 | 11 | 2.2 | 1.1 | 1.9 |
| mistralai_mathstral_7b_v0.1 | 30.8 | 81.2 | 19 | 11 | 2.2 | 1.2 | 1.8 |
| mistralai_ministral_8b_instruct_2410 | 30.8 | 81.5 | 19.3 | 12 | 2.2 | 1.2 | 1.9 |
| google_gemma_2_9b_it | 30.7 | 65.6 | 18.1 | 12 | 2.2 | 1.6 | 1.5 |
| google_gemma_3_4b_it | 30.4 | 72.8 | 19.2 | 13 | 2.2 | 1.5 | 1.6 |
| mistralai_mixtral_8x7b_instruct_v0.1 | 29.8 | 74.1 | 18 | 11 | 2.2 | 1.3 | 1.7 |
| llama-3.2-3B-instruct | 29.7 | 29.7 | 18.7 | 17 | 2.2 | 2.2 | 0 |
| deepseek_r1_distill_qwen_14b | 28.6 | 51.6 | 17 | 11 | 2.1 | 1.7 | 1.3 |
| qwen1.5-14b-chat | 28.6 | 68.8 | 17.6 | 11 | 2.1 | 1.4 | 1.6 |
| qwen2-math-7b-instruct | 28.5 | 81.7 | 18.3 | 12 | 2.1 | 1.1 | 1.9 |
| google_codegemma_1.1_7b_it | 28.1 | 76.6 | 18.2 | 13 | 2.1 | 1.2 | 1.7 |
| qwen2-7b-instruct | 27.7 | 76.3 | 17.1 | 11 | 2.1 | 1.2 | 1.7 |
| mistralai_mistral_7b_instruct_v0.3 | 27.4 | 73.7 | 16.8 | 11 | 2.1 | 1.3 | 1.7 |
| qwen2.5-coder-3b-instruct | 27 | 89.1 | 17.7 | 12 | 2.1 | 0.75 | 2 |
| google_gemma_7b_it | 26.7 | 60.9 | 17.1 | 12 | 2.1 | 1.5 | 1.5 |
| deepseek_r1_distill_llama_70b | 26.3 | 44.9 | 15.3 | 10 | 2.1 | 1.7 | 1.2 |
| mistralai_mistral_7b_instruct_v0.1 | 25.2 | 83.7 | 16.7 | 11 | 2.1 | 0.85 | 1.9 |
| google_gemma_3_1b_it | 24.6 | 73.7 | 16.7 | 12 | 2 | 1 | 1.7 |
| deepseek_v2_lite_chat | 24.5 | 78.1 | 15.8 | 11 | 2 | 0.99 | 1.8 |
| deepseek_r1_distill_qwen_7b | 24.4 | 50.2 | 14.3 | 11 | 2 | 1.5 | 1.3 |
| mistralai_mistral_7b_instruct_v0.2 | 24.1 | 70.8 | 14.8 | 11 | 2 | 1.2 | 1.7 |
| deepseek_r1_distill_llama_8b | 23.8 | 52.5 | 13.6 | 12 | 2 | 1.5 | 1.4 |
| qwen3-0.6b | 23.6 | 68.3 | 15.6 | 13 | 2 | 1.2 | 1.6 |
| qwen2-math-1.5b-instruct | 23.1 | 81.5 | 15.3 | 11 | 2 | 0.79 | 1.8 |
| qwen1.5-7b-chat | 20.4 | 72.5 | 12.9 | 12 | 1.9 | 0.85 | 1.7 |
| qwen2.5-coder-1.5b-instruct | 19.1 | 88.8 | 13.1 | 12 | 1.9 | 0.34 | 1.8 |
| qwen2.5-coder-0.5b-instruct | 18 | 88.2 | 13 | 13 | 1.8 | 0.36 | 1.8 |
| llama-3.2-1B-instruct | 15.4 | 15.4 | 10.8 | 12 | 1.7 | 1.7 | 0 |
| qwen2-1.5b-instruct | 12.5 | 70.3 | 8.35 | 12 | 1.6 | 0.36 | 1.5 |
| google_gemma_2b_it | 12.1 | 50 | 8.34 | 12 | 1.5 | 0.72 | 1.4 |
| qwen2-0.5b-instruct | 12 | 75 | 8.48 | 13 | 1.5 | 0.28 | 1.5 |
| deepseek_r1_distill_qwen_1.5b | 10.9 | 40.2 | 6.08 | 12 | 1.5 | 0.81 | 1.2 |
| qwen1.5-0.5b-chat | 8.6 | 63.4 | 6.18 | 13 | 1.3 | 0.2 | 1.3 |
| qwen1.5-1.8b-chat | 7.92 | 54.5 | 5.37 | 12 | 1.3 | 0.29 | 1.2 |