GPT-5.4 · GPQA Diamond (198-question Diamond subset) · Main text evidence (ev-gpt54-gpqa-928)
Official source for GPQA Diamond · 198-question Diamond subset in GPT-5.4. See “GPT-5.4 震撼登场 | OpenAI” at Evaluation / Academic / GPQA Diamond row. Evidence ev-gpt54-gpqa-928.
Source excerpt and location
GPT-5.4 · GPQA Diamond (198-question Diamond subset), configuration GPT-5.4 (xhigh), Accuracy 92.8% (exact score publication date unconfirmed). See “GPT-5.4 震撼登场 | OpenAI” at Evaluation / Academic / GPQA Diamond row. View score conditions
GPT-5.4 · GPQA Diamond (198-question Diamond subset), configuration GPT-5.4 Pro, Accuracy 94.4% (exact score publication date unconfirmed). See “GPT-5.4 震撼登场 | OpenAI” at Evaluation / Academic / GPQA Diamond row. View score conditions
GPQA Diamond: GPT-5.4 92.8%; GPT-5.4 Pro 94.4%.
- Official material
- GPT-5.4 震撼登场 | OpenAI
- Location
- Main text · Evaluation / Academic / GPQA Diamond row
- Material version
- Official article; page date label 2026-03-05; current page revision date unknown.
- Version published
- Unconfirmed
- Disclosure date
- Unconfirmed · Launch or later disclosure unconfirmed
- Collected
- Historical basis
- No reliable historical version evidence available
Citation text
GPT-5.4 · GPQA Diamond (198-question Diamond subset), configuration GPT-5.4 (xhigh), Accuracy 92.8% (exact score publication date unconfirmed); GPT-5.4 · GPQA Diamond (198-question Diamond subset), configuration GPT-5.4 Pro, Accuracy 94.4% (exact score publication date unconfirmed). Official source: GPT-5.4 震撼登场 | OpenAI (Main text, Official article; page date label 2026-03-05; current page revision date unknown.), Evaluation / Academic / GPQA Diamond row, https://openai.com/zh-Hans-CN/index/introducing-gpt-5-4/. Benchlog https://benchlog.lekshome.cc/evidence/gpt-5-4/ev-gpt54-gpqa-928/?lang=en
Related scores and conditions
GPT-5.4 · GPQA Diamond scores and configurations| Metric and score | Configuration and evaluation conditions | Evidence relation |
|---|
| Accuracy92.8%Reported 92.8% · Unit % Published Unconfirmed Conflicting results are pending review and are excluded from exact rankings. | GPT-5.4 (xhigh)- Settings
- The release article states evaluations use xhigh unless otherwise noted.
- Unknowns
- none recorded
- Tools
- Tool access not recorded
- Reasoning budget
- xhigh
- Framework
- not recorded
- Protocol
- GPQA Diamond; the table does not state tool access in this row.
- Conditions
- Official release table labels GPT-5.4 (xhigh); the article says evaluations use xhigh unless otherwise noted and were run in a research environment.
| Directly supports this score View this score in rankings |
|---|
| Accuracy94.4%Reported 94.4% · Unit % Published Unconfirmed | GPT-5.4 Pro- Settings
- Pro model variant; the article reports Pro separately from GPT-5.4.
- Unknowns
- The Pro column is not a reasoning-effort label; the exact effort for each Pro evaluation is not separately stated.
- Tools
- Tool access not recorded
- Reasoning budget
- not recorded
- Framework
- not recorded
- Protocol
- GPQA Diamond; the table does not state tool access in this row.
- Conditions
- Official release table labels GPT-5.4 Pro; research evaluation environment.
| Directly supports this score View this score in rankings |
|---|