GPT-5 · MMLU Language (0-shot) · OpenAI GPT-5 system card, 2025-08-07; MMLU test set translated by professional human translators; chain-of-thought prompting. Section 3.10 says 13 languages, but Table 10 lists 14 language rows. · 成绩与配置
GPT-5 的 MMLU Language (0-shot) · OpenAI GPT-5 system card, 2025-08-07; MMLU test set translated by professional human translators; chain-of-thought prompting. Section 3.10 says 13 languages, but Table 10 lists 14 language rows. 记录。本次发布有 28 条成绩记录,含 28 条精确值(可含历史记录),附 56 条来源定位。
成绩与评测条件
| 指标与成绩 | 配置与评测条件 | 出处 |
|---|---|---|
| Accuracy90.3%原文 90.3% · 单位 % 公布 | GPT-5 thinking (system card)
|
|
| Accuracy85.7%原文 85.7% · 单位 % 公布 | GPT-5 main
|
|
| Accuracy89.2%原文 89.2% · 单位 % 公布 | GPT-5 thinking (system card)
|
|
| Accuracy85%原文 85.0% · 单位 % 公布 | GPT-5 main
|
|
| Accuracy90.2%原文 90.2% · 单位 % 公布 | GPT-5 thinking (system card)
|
|
| Accuracy86.7%原文 86.7% · 单位 % 公布 | GPT-5 main
|
|
| Accuracy90.1%原文 90.1% · 单位 % 公布 | GPT-5 thinking (system card)
|
|
| Accuracy87.5%原文 87.5% · 单位 % 公布 | GPT-5 main
|
|
| Accuracy89.6%原文 89.6% · 单位 % 公布 | GPT-5 thinking (system card)
|
|
| Accuracy86.6%原文 86.6% · 单位 % 公布 | GPT-5 main
|
|
| Accuracy89.9%原文 89.9% · 单位 % 公布 | GPT-5 thinking (system card)
|
|
| Accuracy86.1%原文 86.1% · 单位 % 公布 | GPT-5 main
|
|
| Accuracy90.9%原文 90.9% · 单位 % 公布 | GPT-5 thinking (system card)
|
|
| Accuracy87.2%原文 87.2% · 单位 % 公布 | GPT-5 main
|
|
| Accuracy90.8%原文 90.8% · 单位 % 公布 | GPT-5 thinking (system card)
|
|
| Accuracy87.6%原文 87.6% · 单位 % 公布 | GPT-5 main
|
|
| Accuracy89.8%原文 89.8% · 单位 % 公布 | GPT-5 thinking (system card)
|
|
| Accuracy86.5%原文 86.5% · 单位 % 公布 | GPT-5 main
|
|
| Accuracy89.6%原文 89.6% · 单位 % 公布 | GPT-5 thinking (system card)
|
|
| Accuracy85.4%原文 85.4% · 单位 % 公布 | GPT-5 main
|
|
| Accuracy91%原文 91.0% · 单位 % 公布 | GPT-5 thinking (system card)
|
|
| Accuracy87.9%原文 87.9% · 单位 % 公布 | GPT-5 main
|
|
| Accuracy91%原文 91.0% · 单位 % 公布 | GPT-5 thinking (system card)
|
|
| Accuracy88.1%原文 88.1% · 单位 % 公布 | GPT-5 main
|
|
| Accuracy88%原文 88.0% · 单位 % 公布 | GPT-5 thinking (system card)
|
|
| Accuracy81.5%原文 81.5% · 单位 % 公布 | GPT-5 main
|
|
| Accuracy80.6%原文 80.6% · 单位 % 公布 | GPT-5 thinking (system card)
|
|
| Accuracy66.4%原文 66.4% · 单位 % 公布 | GPT-5 main
|
|
出处与披露
- PDF p. 19, Table 10 / MMLU Language (0-shot) / Arabic 附件 · GPT-5 System Card | OpenAI
- PDF p. 19, Table 10 / MMLU Language (0-shot) / Arabic 附件 · GPT-5 System Card | OpenAI
- PDF p. 19, Table 10 / MMLU Language (0-shot) / Bengali 附件 · GPT-5 System Card | OpenAI
- PDF p. 19, Table 10 / MMLU Language (0-shot) / Bengali 附件 · GPT-5 System Card | OpenAI
- PDF p. 19, Table 10 / MMLU Language (0-shot) / Chinese (Simplified) 附件 · GPT-5 System Card | OpenAI
- PDF p. 19, Table 10 / MMLU Language (0-shot) / Chinese (Simplified) 附件 · GPT-5 System Card | OpenAI
- PDF p. 19, Table 10 / MMLU Language (0-shot) / French 附件 · GPT-5 System Card | OpenAI
- PDF p. 19, Table 10 / MMLU Language (0-shot) / French 附件 · GPT-5 System Card | OpenAI
- PDF p. 19, Table 10 / MMLU Language (0-shot) / German 附件 · GPT-5 System Card | OpenAI
- PDF p. 19, Table 10 / MMLU Language (0-shot) / German 附件 · GPT-5 System Card | OpenAI
- PDF p. 19, Table 10 / MMLU Language (0-shot) / Hindi 附件 · GPT-5 System Card | OpenAI
- PDF p. 19, Table 10 / MMLU Language (0-shot) / Hindi 附件 · GPT-5 System Card | OpenAI
- PDF p. 19, Table 10 / MMLU Language (0-shot) / Indonesian 附件 · GPT-5 System Card | OpenAI
- PDF p. 19, Table 10 / MMLU Language (0-shot) / Indonesian 附件 · GPT-5 System Card | OpenAI
- PDF p. 19, Table 10 / MMLU Language (0-shot) / Italian 附件 · GPT-5 System Card | OpenAI
- PDF p. 19, Table 10 / MMLU Language (0-shot) / Italian 附件 · GPT-5 System Card | OpenAI
- PDF p. 19, Table 10 / MMLU Language (0-shot) / Japanese 附件 · GPT-5 System Card | OpenAI
- PDF p. 19, Table 10 / MMLU Language (0-shot) / Japanese 附件 · GPT-5 System Card | OpenAI
- PDF p. 19, Table 10 / MMLU Language (0-shot) / Korean 附件 · GPT-5 System Card | OpenAI
- PDF p. 19, Table 10 / MMLU Language (0-shot) / Korean 附件 · GPT-5 System Card | OpenAI
- PDF p. 19, Table 10 / MMLU Language (0-shot) / Portuguese (Brazil) 附件 · GPT-5 System Card | OpenAI
- PDF p. 19, Table 10 / MMLU Language (0-shot) / Portuguese (Brazil) 附件 · GPT-5 System Card | OpenAI
- PDF p. 19, Table 10 / MMLU Language (0-shot) / Spanish 附件 · GPT-5 System Card | OpenAI
- PDF p. 19, Table 10 / MMLU Language (0-shot) / Spanish 附件 · GPT-5 System Card | OpenAI
- PDF p. 19, Table 10 / MMLU Language (0-shot) / Swahili 附件 · GPT-5 System Card | OpenAI
- PDF p. 19, Table 10 / MMLU Language (0-shot) / Swahili 附件 · GPT-5 System Card | OpenAI
- PDF p. 19, Table 10 / MMLU Language (0-shot) / Yoruba 附件 · GPT-5 System Card | OpenAI
- PDF p. 19, Table 10 / MMLU Language (0-shot) / Yoruba 附件 · GPT-5 System Card | OpenAI
- Current 60-page PDF p.20, Table 11, MMLU Language (0-shot); compare archived 59-page p.19, Table 10. Arabic 附件 · GPT-5 System Card (current 60-page revision)
- Current 60-page PDF p.20, Table 11, MMLU Language (0-shot); compare archived 59-page p.19, Table 10. Arabic 附件 · GPT-5 System Card (current 60-page revision)
- Current 60-page PDF p.20, Table 11, MMLU Language (0-shot); compare archived 59-page p.19, Table 10. Bengali 附件 · GPT-5 System Card (current 60-page revision)
- Current 60-page PDF p.20, Table 11, MMLU Language (0-shot); compare archived 59-page p.19, Table 10. Bengali 附件 · GPT-5 System Card (current 60-page revision)
- Current 60-page PDF p.20, Table 11, MMLU Language (0-shot); compare archived 59-page p.19, Table 10. Chinese (Simplified) 附件 · GPT-5 System Card (current 60-page revision)
- Current 60-page PDF p.20, Table 11, MMLU Language (0-shot); compare archived 59-page p.19, Table 10. Chinese (Simplified) 附件 · GPT-5 System Card (current 60-page revision)
- Current 60-page PDF p.20, Table 11, MMLU Language (0-shot); compare archived 59-page p.19, Table 10. French 附件 · GPT-5 System Card (current 60-page revision)
- Current 60-page PDF p.20, Table 11, MMLU Language (0-shot); compare archived 59-page p.19, Table 10. French 附件 · GPT-5 System Card (current 60-page revision)
- Current 60-page PDF p.20, Table 11, MMLU Language (0-shot); compare archived 59-page p.19, Table 10. German 附件 · GPT-5 System Card (current 60-page revision)
- Current 60-page PDF p.20, Table 11, MMLU Language (0-shot); compare archived 59-page p.19, Table 10. German 附件 · GPT-5 System Card (current 60-page revision)
- Current 60-page PDF p.20, Table 11, MMLU Language (0-shot); compare archived 59-page p.19, Table 10. Hindi 附件 · GPT-5 System Card (current 60-page revision)
- Current 60-page PDF p.20, Table 11, MMLU Language (0-shot); compare archived 59-page p.19, Table 10. Hindi 附件 · GPT-5 System Card (current 60-page revision)
- Current 60-page PDF p.20, Table 11, MMLU Language (0-shot); compare archived 59-page p.19, Table 10. Indonesian 附件 · GPT-5 System Card (current 60-page revision)
- Current 60-page PDF p.20, Table 11, MMLU Language (0-shot); compare archived 59-page p.19, Table 10. Indonesian 附件 · GPT-5 System Card (current 60-page revision)
- Current 60-page PDF p.20, Table 11, MMLU Language (0-shot); compare archived 59-page p.19, Table 10. Italian 附件 · GPT-5 System Card (current 60-page revision)
- Current 60-page PDF p.20, Table 11, MMLU Language (0-shot); compare archived 59-page p.19, Table 10. Italian 附件 · GPT-5 System Card (current 60-page revision)
- Current 60-page PDF p.20, Table 11, MMLU Language (0-shot); compare archived 59-page p.19, Table 10. Japanese 附件 · GPT-5 System Card (current 60-page revision)
- Current 60-page PDF p.20, Table 11, MMLU Language (0-shot); compare archived 59-page p.19, Table 10. Japanese 附件 · GPT-5 System Card (current 60-page revision)
- Current 60-page PDF p.20, Table 11, MMLU Language (0-shot); compare archived 59-page p.19, Table 10. Korean 附件 · GPT-5 System Card (current 60-page revision)
- Current 60-page PDF p.20, Table 11, MMLU Language (0-shot); compare archived 59-page p.19, Table 10. Korean 附件 · GPT-5 System Card (current 60-page revision)
- Current 60-page PDF p.20, Table 11, MMLU Language (0-shot); compare archived 59-page p.19, Table 10. Portuguese (Brazil) 附件 · GPT-5 System Card (current 60-page revision)
- Current 60-page PDF p.20, Table 11, MMLU Language (0-shot); compare archived 59-page p.19, Table 10. Portuguese (Brazil) 附件 · GPT-5 System Card (current 60-page revision)
- Current 60-page PDF p.20, Table 11, MMLU Language (0-shot); compare archived 59-page p.19, Table 10. Spanish 附件 · GPT-5 System Card (current 60-page revision)
- Current 60-page PDF p.20, Table 11, MMLU Language (0-shot); compare archived 59-page p.19, Table 10. Spanish 附件 · GPT-5 System Card (current 60-page revision)
- Current 60-page PDF p.20, Table 11, MMLU Language (0-shot); compare archived 59-page p.19, Table 10. Swahili 附件 · GPT-5 System Card (current 60-page revision)
- Current 60-page PDF p.20, Table 11, MMLU Language (0-shot); compare archived 59-page p.19, Table 10. Swahili 附件 · GPT-5 System Card (current 60-page revision)
- Current 60-page PDF p.20, Table 11, MMLU Language (0-shot); compare archived 59-page p.19, Table 10. Yoruba 附件 · GPT-5 System Card (current 60-page revision)
- Current 60-page PDF p.20, Table 11, MMLU Language (0-shot); compare archived 59-page p.19, Table 10. Yoruba 附件 · GPT-5 System Card (current 60-page revision)
测试版本与指标
别名 MMLU Language (0-shot; GPT-5 System Card)
- Accuracy · % · 越高越好