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) |
|---|---|---|---|---|---|---|---|
| deepseek_r1_distill_qwen_32b | 37.9 | 73.3 | 32.4 | 11 | 8.9 | 6.4 | 6.1 |
| deepseek_r1_distill_llama_70b | 34.2 | 66.7 | 29.1 | 11 | 8.7 | 6.3 | 5.9 |
| deepseek_r1_distill_qwen_7b | 28.5 | 46.7 | 23.8 | 11 | 8.2 | 6.5 | 5.1 |
| deepseek_r1_distill_qwen_14b | 27.6 | 43.3 | 22.7 | 11 | 8.2 | 6.9 | 4.4 |
| google_gemma_3_27b_it | 25.6 | 56.7 | 20.8 | 12 | 8 | 5.4 | 5.9 |
| qwen3-14b | 24.4 | 33.3 | 19.5 | 12 | 7.8 | 6.7 | 4 |
| qwen3-32b | 22.7 | 43.3 | 18.1 | 11 | 7.7 | 5.9 | 4.9 |
| llama-3.1-70B-instruct | 20 | 20 | 16.6 | 13 | 7.3 | 7.3 | 0 |
| deepseek_r1_distill_llama_8b | 19 | 40 | 15.3 | 13 | 7.2 | 5.2 | 4.9 |
| qwen2-math-72b-instruct | 18.3 | 36.7 | 14.4 | 6 | 7.1 | 5.1 | 4.9 |
| google_gemma_3_12b_it | 18.2 | 46.7 | 14.6 | 11 | 7 | 5.2 | 4.7 |
| qwen3-8b | 17.5 | 50 | 14.2 | 12 | 6.9 | 5.3 | 4.4 |
| qwen2.5-coder-32b-instruct | 13 | 30 | 9.68 | 11 | 6.1 | 4.6 | 4 |
| qwen3-4b | 11.9 | 23.3 | 8.86 | 12 | 5.9 | 4.5 | 3.9 |
| deepseek_r1_distill_qwen_1.5b | 11.5 | 23.3 | 8.78 | 13 | 5.8 | 4.7 | 3.5 |
| qwen2.5-coder-14b-instruct | 10.8 | 20 | 7.77 | 12 | 5.7 | 4.5 | 3.4 |
| llama-3.2-3B-instruct | 10 | 10 | 7.48 | 18 | 5.5 | 5.5 | 0 |
| qwen3-1.7b | 9.44 | 23.3 | 7.16 | 12 | 5.3 | 3.9 | 3.7 |
| qwen2-math-7b-instruct | 8.33 | 13.3 | 6.38 | 6 | 5 | 4.3 | 2.7 |
| qwen2-math-1.5b-instruct | 7.5 | 13.3 | 5.05 | 4 | 4.8 | 3.8 | 2.9 |
| google_gemma_3_4b_it | 7.18 | 23.3 | 5.57 | 13 | 4.7 | 2.5 | 4 |
| qwen2-72b-instruct | 6.06 | 20 | 4.19 | 11 | 4.4 | 2.8 | 3.3 |
| qwen2.5-coder-7b-instruct | 4.55 | 10 | 3.19 | 11 | 3.8 | 2.4 | 2.9 |
| llama-3.1-8B-instruct | 3.33 | 3.33 | 2.36 | 15 | 3.3 | 3.3 | 0 |
| llama-3.2-1B-instruct | 3.33 | 3.33 | 2.29 | 21 | 3.3 | 3.3 | 0 |
| qwen2-7b-instruct | 3.03 | 6.67 | 2.23 | 11 | 3.1 | 2 | 2.4 |
| google_gemma_2_27b_it | 3 | 13.3 | 2 | 10 | 3.1 | 1.8 | 2.5 |
| qwen2.5-coder-3b-instruct | 2.22 | 6.67 | 1.53 | 12 | 2.7 | 1.4 | 2.3 |
| google_gemma_3_1b_it | 1.54 | 3.33 | 1.04 | 13 | 2.2 | 1.4 | 1.7 |
| mistralai_mathstral_7b_v0.1 | 1.52 | 6.67 | 1.12 | 11 | 2.2 | 0.86 | 2.1 |
| mistralai_mixtral_8x22b_instruct_v0.1 | 1.52 | 13.3 | 1.06 | 11 | 2.2 | 0.35 | 2.2 |
| deepseek_v2_lite_chat | 1.21 | 3.33 | 0.818 | 11 | 2 | 1.1 | 1.7 |
| qwen3-0.6b | 1.03 | 3.33 | 0.691 | 13 | 1.8 | 0.91 | 1.6 |
| qwen1.5-72b-chat | 0.606 | 3.33 | 0.363 | 11 | 1.4 | 0.44 | 1.3 |
| qwen1.5-32b-chat | 0.606 | 6.67 | 0.384 | 11 | 1.4 | 0 | 1.4 |
| google_gemma_2_9b_it | 0.303 | 3.33 | 0.203 | 11 | 1 | 0 | 1 |
| mistralai_mistral_7b_instruct_v0.2 | 0.303 | 3.33 | 0.252 | 11 | 1 | 0 | 1 |
| mistralai_mixtral_8x7b_instruct_v0.1 | 0.278 | 3.33 | 0.231 | 12 | 0.96 | 0 | 0.96 |
| google_codegemma_1.1_7b_it | 0 | 0 | 0 | 13 | 0 | 0 | 0 |
| google_gemma_2b_it | 0 | 0 | 0 | 13 | 0 | 0 | 0 |
| google_gemma_7b_it | 0 | 0 | 0 | 13 | 0 | 0 | 0 |
| qwen2-1.5b-instruct | 0 | 0 | 0 | 13 | 0 | 0 | 0 |
| mistralai_mistral_7b_instruct_v0.3 | 0 | 0 | 0 | 11 | 0 | 0 | 0 |
| qwen1.5-0.5b-chat | 0 | 0 | 0 | 13 | 0 | 0 | 0 |
| mistralai_mistral_7b_instruct_v0.1 | 0 | 0 | 0 | 11 | 0 | 0 | 0 |
| qwen2-0.5b-instruct | 0 | 0 | 0 | 13 | 0 | 0 | 0 |
| qwen1.5-7b-chat | 0 | 0 | 0 | 12 | 0 | 0 | 0 |
| qwen1.5-1.8b-chat | 0 | 0 | 0 | 11 | 0 | 0 | 0 |
| qwen1.5-14b-chat | 0 | 0 | 0 | 12 | 0 | 0 | 0 |
| mistralai_ministral_8b_instruct_2410 | 0 | 0 | 0 | 11 | 0 | 0 | 0 |
| qwen2.5-coder-0.5b-instruct | 0 | 0 | 0 | 13 | 0 | 0 | 0 |
| qwen2.5-coder-1.5b-instruct | 0 | 0 | 0 | 11 | 0 | 0 | 0 |