跳到正文
原文
Simon Willison·· 11 天前AI 评分38

Qwen3.8 27B 英文单词加法测试

Qwen3.8 27B addition in words

AI 导读

Simon Willison 在 DGX Spark 上测试了 Qwen3.8-27B-Q4_K_M.gguf 的英文单词加法能力。禁用推理时,5,070 个测试的数值准确率仅 23.57%,随操作数位数增加从 97.04% 降至 6.44%,格式合规率为 96.17%。开启中等推理后,169 次单次测试中答对 167 次,准确率大幅提升。

正文 · AI 翻译

研究 Qwen3.8 27B 用英文单词表示加法 —— 一项基准测试检验了本地 `Qwen3.8-27B-Q4_K_M.gguf` 模型能否将正整数相加,并仅用英文单词表示精确结果,测试使用了 5,070 个禁用推理的用例,并与 169 个用例的中等推理版本进行了配对比较。在禁用推理的情况下,其数字准确率为 23.57%,尽管格式合规率高达 96.17%,但表现从一到三位操作数的 97.04% 下降到了十到十三位操作数的 6.44%。

Colin Frasier 在 Bluesky 上发帖,谈到了他两年多前用 GPT-4o 做的一个实验,想看看它在越来越大的数字上能多好地“计算出总和并用单词返回答案”。这是他分享的那些结果图表:

Heatmap chart of accuracy on an addition prompt, colored from dark green (high) through yellow to dark red (low). Title: "What is {a} + {b}? Please write your answer in words. Do not include any other text or information, just the answer in words." Subtitle: 30 randomly selected pairs for each digit combination (n = 30 * 13 * 13 = 5070). X axis: Number of digits in a, 1 to 13. Y axis: Number of digits in b, 1 to 13. Legend: Accuracy, 1.00, 0.75, 0.50, 0.25, 0.00. Values by row, listed for a = 1 to 13. b = 13: 100%, 77%, 27%, 20%, 0%, 0%, 0%, 0%, 0%, 0%, 0%, 0%, 0%. b = 12: 97%, 80%, 80%, 40%, 23%, 20%, 7%, 13%, 20%, 27%, 67%, 63%, 3%. b = 11: 97%, 97%, 53%, 17%, 0%, 0%, 0%, 0%, 0%, 0%, 0%, 37%, 0%. b = 10: 100%, 90%, 47%, 20%, 7%, 0%, 0%, 0%, 3%, 0%, 0%, 7%, 0%. b = 9: 97%, 93%, 80%, 77%, 53%, 67%, 47%, 87%, 97%, 3%, 0%, 13%, 0%. b = 8: 93%, 87%, 53%, 43%, 7%, 0%, 0%, 13%, 87%, 0%, 0%, 0%, 0%. b = 7: 93%, 93%, 47%, 10%, 13%, 20%, 23%, 0%, 70%, 0%, 0%, 0%, 0%. b = 6: 100%, 100%, 100%, 83%, 97%, 97%, 23%, 0%, 53%, 3%, 0%, 10%, 0%. b = 5: 100%, 100%, 80%, 70%, 73%, 100%, 13%, 13%, 70%, 0%, 20%, 30%, 0%. b = 4: 100%, 100%, 93%, 100%, 60%, 97%, 20%, 50%, 67%, 53%, 40%, 40%, 40%. b = 3: 100%, 100%, 97%, 90%, 83%, 100%, 63%, 50%, 63%, 53%, 60%, 60%, 30%. b = 2: 100%, 100%, 90%, 97%, 93%, 100%, 93%, 83%, 90%, 83%, 87%, 87%, 83%. b = 1: 100%, 100%, 100%, 97%, 100%, 97%, 97%, 97%, 100%, 100%, 100%, 97%, 100%.

我确信 GPT-4o 没有作弊使用计算器,尤其因为它算错了那么多道题,但我受到启发,在本地硬件(一台 DGX Spark)上重新运行了这个实验,以便在完全受控的环境中探索这一效应。

我把他的图片粘贴到一个 Codex Remote 会话(GPT-6 Astra)中,让它用 Qwen3.8-27B-Q4_K_M.gguf 运行同样的实验。以下是每种组合禁用推理、运行 30 次尝试后的结果:

Heatmap in the same layout as the previous chart, using an orange (low) to white to blue (high) color scale, showing much lower accuracy overall. Title: Addition in words — Qwen3.8 27B Q4_K_M. Subtitle: Reasoning disabled · 30 fixed pairs per ordered digit-length cell (n = 5,070). Overall numeric accuracy: 1,195 / 5,070 (23.57%). X axis: Number of digits in a, 1 to 13. Y axis: Number of digits in b, 1 to 13. Legend: Accuracy, 100%, 75%, 50%, 25%, 0%. Values by row, listed for a = 1 to 13. b = 13: 17%, 13%, 0%, 0%, 0%, 0%, 0%, 0%, 0%, 0%, 0%, 0%, 0%. b = 12: 53%, 20%, 0%, 0%, 0%, 0%, 0%, 0%, 0%, 0%, 0%, 0%, 0%. b = 11: 47%, 10%, 0%, 0%, 0%, 0%, 0%, 0%, 0%, 0%, 0%, 0%, 0%. b = 10: 70%, 27%, 3%, 0%, 0%, 0%, 0%, 0%, 0%, 13%, 0%, 0%, 0%. b = 9: 77%, 47%, 3%, 0%, 0%, 0%, 0%, 3%, 7%, 0%, 0%, 0%, 0%. b = 8: 53%, 20%, 0%, 0%, 0%, 0%, 7%, 13%, 0%, 0%, 0%, 0%, 0%. b = 7: 53%, 23%, 17%, 10%, 3%, 3%, 13%, 3%, 0%, 0%, 0%, 0%, 0%. b = 6: 60%, 60%, 33%, 10%, 53%, 47%, 7%, 3%, 0%, 0%, 0%, 0%, 0%. b = 5: 73%, 67%, 87%, 80%, 53%, 40%, 0%, 0%, 3%, 0%, 0%, 0%, 0%. b = 4: 83%, 93%, 90%, 93%, 53%, 13%, 0%, 0%, 0%, 0%, 0%, 0%, 0%. b = 3: 100%, 93%, 90%, 80%, 67%, 37%, 17%, 0%, 0%, 3%, 0%, 0%, 0%. b = 2: 100%, 100%, 93%, 90%, 77%, 77%, 43%, 50%, 63%, 43%, 40%, 13%, 23%. b = 1: 97%, 100%, 100%, 100%, 80%, 67%, 77%, 80%, 80%, 60%, 43%, 30%, 37%. Footnote: Colorblind-safe orange–blue scale; percentages provide a redundant non-color encoding.

然后我开启了推理又跑了一遍。每对数字耗时长得多,所以每个方格我没有跑 30 个样本,而是只跑了 1 个——这导致热力图在视觉上大打折扣,因为每个方格要么是 100%,要么是 0%:

Heatmap in the same layout as the previous charts, almost entirely blue. Title: Addition in words — Qwen3.8 27B — medium reasoning pilot. Subtitle: 1 fixed pair per ordered digit-length cell · easiest first (n = 169). X axis: Number of digits in a, 1 to 13. Y axis: Number of digits in b, 1 to 13. Legend: Accuracy, 1.00, 0.75, 0.50, 0.25, 0.00. Every cell shows 100% except two orange cells showing 0%: a = 2 with b = 8, and a = 12 with b = 9.

它在 169 次尝试中有 167 次给出了正确答案,而且由于这些都是一次性运行,我确信再跑一次会得出不同的结果。

这是一个报告版本,其中包含了一些较大计算的推理轨迹,内容类似这样:

Wait, let me redo this more carefully.

4,299,366,105,622
6,088,794,067,970

Let me align them:
4 2 9 9 3 6 6 1 0 5 6 2 2
6 0 8 8 7 9 4 0 6 7 9 7 0

Adding from right to left:
Position 1 (units): 2 + 0 = 2
Position 2 (tens): 2 + 7 = 9
Position 3 (hundreds): 6 + 9 = 15, write 5, carry 1

来源:Simon Willison · simonwillison.net