GPQA DiamondVerified
87.3%
GPQA Diamond (AA run)
Models / OpenAI
GPT-5.1
GPT-5 · Released 2025-11-13
OpenAI's November 2025 GPT-5.1 family. $1.25/$10 per 1M tokens, 400K context. Retired from ChatGPT March 2026; API snapshots may still exist. MedScribe leader on Vals (88.1%).
Legacy GPT-5.1 endpoints only — migrate to GPT-5.4/5.5 for new work.
Composite61
Context400K
Input / 1M$1.3
Output / 1M$10
Knowledge cutoff2024-09-30
Output speed119 t/s
Statuslightweight
Family profile
Best published score in each covered benchmark family.
73/100 avg
- Reasoning
- 87
- Agentic
- 52
- Long context
- 80
3 tested benchmark families
Benchmark placements
Per-benchmark positions
Where GPT-5.1 places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.
| Benchmark | Family | Rank | Score | Source | Date |
|---|---|---|---|---|---|
| AA-LCR | Long context | #42/ 184 | 80 | Artificial Analysis | 2026-09-28 |
| AA output speed | Performance | #48/ 195 | Artificial Analysis | 2026-10-12 | |
| Terminal-Bench | Agentic | #69/ 167 | 52 | Artificial Analysis | 2026-09-28 |
| GPQA Diamond | Reasoning | #71/ 184 | 87 | Artificial Analysis | 2026-09-28 |
| Humanity's Last Exam | Reasoning | #91/ 186 | 29 | Artificial Analysis | 2026-09-28 |
Family context
Strongest rows in each family
The three highest-scoring models with pages in each capability family. Where GPT-5.1 shows up, it's highlighted.
ReasoningGPT-5.1 · 87
- 196
- 295
- 395
Math
- 152
- 252
- 350
AgenticGPT-5.1 · 52
- 191
- 289
- 389
Long contextGPT-5.1 · 80
- 189
- 286
- 385
Newest receipts
5 recentLast 120 days
Benchmark rows added to the public ledger for GPT-5.1 in the last 120 days. Older rows live in the full table below.
| Benchmark | Family | Score | Source | Days ago |
|---|---|---|---|---|
| AA output speed | Performance | 119 t/s | Artificial Analysis | 10 |
| AA-LCR | Long context | 80% | Artificial Analysis | 24 |
| GPQA Diamond | Reasoning | 87.3% | Artificial Analysis | 24 |
| Humanity's Last Exam | Reasoning | 28.5% | Artificial Analysis | 24 |
| Terminal-Bench | Agentic | 52.43% | Artificial Analysis | 24 |
Family coverage
Best score per family
A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.
Price vs. performance
Where GPT-5.1 sits on the scatter
Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.
AnthropicOpenAIGoogleAlibabaMetaZhipuxAIDeepSeekMiniMaxXiaomiMoonshotOtherMeituanMistralNVIDIACohere
Full benchmark ledger
Every catalog benchmark for GPT-5.1. Scores link to the original source; gaps mean no public row exists yet.
5 of 13 catalog benchmarks have a sourced row for GPT-5.1.
Reasoning
Humanity's Last ExamVerified
28.5%
HLE (AA run)
Agentic
Terminal-BenchVerified
52.43%
Terminal-Bench v2.1 (AA run)
Long context
AA-LCRVerified
80%
AA-LCR (AA run)
Performance
AA output speedVerified
119 t/s
Median output tokens/s (1k prompt, default provider)
Sources
Where the numbers come from
- OpenAI GPT-5.1 docs· checked 2026-06-09
Questions this model page answers
Every answer below is assembled from the dated fields on this page. Nothing is written separately for search.
What is GPT-5.1?
GPT-5.1 is a OpenAI model: OpenAI's November 2025 GPT-5.1 family. $1.25/$10 per 1M tokens, 400K context. Retired from ChatGPT March 2026; API snapshots may still exist. MedScribe leader on Vals (88.1%).
What is GPT-5.1 for?
Legacy GPT-5.1 endpoints only — migrate to GPT-5.4/5.5 for new work.
What does GPT-5.1 cost?
GPT-5.1 lists $1.3 input and $10 output per 1M tokens. Pricing last checked 2026-06-09.
How large is the GPT-5.1 context window?
GPT-5.1 publishes a 400K token context window.
What is the VerdictPal status of GPT-5.1?
GPT-5.1 carries Lightweight status on the model atlas.
The Pack · Editorial newsletter
Know when the rules move.
One short email when a university changes its AI rule for theses, or a research tool changes its pricing or privacy terms. No tracking, no third-party analytics. Unsubscribe in one click.