GPQA DiamondVerified
74.7%
GPQA Diamond (AA run)
Models / OpenAI
OpenAI o1
OpenAI o · Released 2024-09-12
OpenAI's September 2024 reasoning model. Predecessor to o3 and GPT-5 reasoning tiers.
Legacy reasoning tier — prefer o3 or GPT-5.5 for new math and code work.
Composite39
Context200K
Input / 1M—
Output / 1M—
Knowledge cutoff2023-10-01
Statuslightweight
Family profile
Best published score in each covered benchmark family.
51/100 avg
- Reasoning
- 75
- Agentic
- 13
- Long context
- 65
3 tested benchmark families
Benchmark placements
Per-benchmark positions
Where OpenAI o1 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 | #143/ 184 | 65 | Artificial Analysis | 2026-09-28 |
| Terminal-Bench | Agentic | #154/ 167 | 13 | Artificial Analysis | 2026-09-28 |
| GPQA Diamond | Reasoning | #156/ 184 | 75 | Artificial Analysis | 2026-09-28 |
| Humanity's Last Exam | Reasoning | #168/ 186 | 7 | Artificial Analysis | 2026-09-28 |
| AA output speed | Performance | #192/ 195 | Artificial Analysis | 2026-09-28 |
Family context
Strongest rows in each family
The three highest-scoring models with pages in each capability family. Where OpenAI o1 shows up, it's highlighted.
ReasoningOpenAI o1 · 75
- 196
- 295
- 395
Math
- 152
- 252
- 350
AgenticOpenAI o1 · 13
- 191
- 289
- 389
Long contextOpenAI o1 · 65
- 189
- 286
- 385
Newest receipts
5 recentLast 120 days
Benchmark rows added to the public ledger for OpenAI o1 in the last 120 days. Older rows live in the full table below.
| Benchmark | Family | Score | Source | Days ago |
|---|---|---|---|---|
| AA-LCR | Long context | 65% | Artificial Analysis | 24 |
| AA output speed | Performance | 0 t/s | Artificial Analysis | 24 |
| GPQA Diamond | Reasoning | 74.7% | Artificial Analysis | 24 |
| Humanity's Last Exam | Reasoning | 7% | Artificial Analysis | 24 |
| Terminal-Bench | Agentic | 12.88% | 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 OpenAI o1 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 OpenAI o1. Scores link to the original source; gaps mean no public row exists yet.
5 of 13 catalog benchmarks have a sourced row for OpenAI o1.
Reasoning
Humanity's Last ExamVerified
7%
HLE (AA run)
Agentic
Terminal-BenchVerified
12.88%
Terminal-Bench Hard (AA run)
Long context
AA-LCRVerified
65%
AA-LCR (AA run)
Performance
AA output speedVerified
0 t/s
Median output tokens/s (1k prompt, default provider)
Sources
Where the numbers come from
- Learning to reason with LLMs· 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 OpenAI o1?
OpenAI o1 is a OpenAI model: OpenAI's September 2024 reasoning model. Predecessor to o3 and GPT-5 reasoning tiers.
What is OpenAI o1 for?
Legacy reasoning tier — prefer o3 or GPT-5.5 for new math and code work.
What does OpenAI o1 cost?
OpenAI o1 lists — input and — output per 1M tokens. Pricing last checked 2026-06-09.
How large is the OpenAI o1 context window?
OpenAI o1 publishes a 200K token context window.
What is the VerdictPal status of OpenAI o1?
OpenAI o1 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.