GPQA DiamondVerified
90.3%
GPQA Diamond (AA run)
Models / OpenAI
GPT-5.2
GPT-5 · Released 2025-12-11
OpenAI's December 2025 frontier. 410K context, 128K output, configurable reasoning effort. $1.75/$14 per 1M tokens.
Previous-gen GPT-5 for complex professional work. Superseded by GPT-5.4/5.5 but still available at lower cost.
Composite60
Context410K
Input / 1M$1.8
Output / 1M$14
Knowledge cutoff2025-08-01
Output speed81 t/s
Statussolid
Family profile
Best published score in each covered benchmark family.
65/100 avg
- Reasoning
- 90
- Math
- 41
- Agentic
- 47
- Long context
- 83
4 tested benchmark families
Benchmark placements
Per-benchmark positions
Where GPT-5.2 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 |
|---|---|---|---|---|---|
| FrontierMath | Math | #8/ 15 | 41 | Epoch AI FrontierMath Tiers 1-3 (v2) CSV | 2026-08-15 |
| AA-LCR | Long context | #17/ 184 | 83 | Artificial Analysis | 2026-09-28 |
| GPQA Diamond | Reasoning | #43/ 184 | 90 | Artificial Analysis | 2026-09-28 |
| Humanity's Last Exam | Reasoning | #53/ 186 | 38 | Artificial Analysis | 2026-09-28 |
| Terminal-Bench | Agentic | #78/ 167 | 47 | Artificial Analysis | 2026-09-28 |
| AA output speed | Performance | #80/ 195 | Artificial Analysis | 2026-10-12 |
Family context
Strongest rows in each family
The three highest-scoring models with pages in each capability family. Where GPT-5.2 shows up, it's highlighted.
ReasoningGPT-5.2 · 90
- 196
- 295
- 395
MathGPT-5.2 · 41
- 152
- 252
- 350
AgenticGPT-5.2 · 47
- 191
- 289
- 389
Long contextGPT-5.2 · 83
- 189
- 286
- 385
Newest receipts
6 recentLast 120 days
Benchmark rows added to the public ledger for GPT-5.2 in the last 120 days. Older rows live in the full table below.
| Benchmark | Family | Score | Source | Days ago |
|---|---|---|---|---|
| AA output speed | Performance | 81 t/s | Artificial Analysis | 10 |
| AA-LCR | Long context | 82.67% | Artificial Analysis | 24 |
| GPQA Diamond | Reasoning | 90.3% | Artificial Analysis | 24 |
| Humanity's Last Exam | Reasoning | 37.7% | Artificial Analysis | 24 |
| Terminal-Bench | Agentic | 46.97% | Artificial Analysis | 24 |
| FrontierMath | Math | 40.7% | Epoch AI FrontierMath Tiers 1-3 (v2) CSV | 68 |
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-5.2 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-5.2. Scores link to the original source; gaps mean no public row exists yet.
6 of 13 catalog benchmarks have a sourced row for GPT-5.2.
Reasoning
Humanity's Last ExamVerified
37.7%
HLE (AA run)
Math
FrontierMathVerified
40.7%
FrontierMath Tiers 1-3 (v2) best Epoch run
Agentic
Terminal-BenchVerified
46.97%
Terminal-Bench Hard (AA run)
Long context
AA-LCRVerified
82.67%
AA-LCR (AA run)
Performance
AA output speedVerified
81 t/s
Median output tokens/s (1k prompt, default provider)
Changelog
Version history
- Released GPT-5.2 — 410K context, configurable reasoning, $1.75/$14.
Sources
Where the numbers come from
- OpenAI announcement· checked 2026-06-02
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-5.2?
GPT-5.2 is a OpenAI model: OpenAI's December 2025 frontier. 410K context, 128K output, configurable reasoning effort. $1.75/$14 per 1M tokens.
What is GPT-5.2 for?
Previous-gen GPT-5 for complex professional work. Superseded by GPT-5.4/5.5 but still available at lower cost.
What does GPT-5.2 cost?
GPT-5.2 lists $1.8 input and $14 output per 1M tokens. Pricing last checked 2026-06-02.
How large is the GPT-5.2 context window?
GPT-5.2 publishes a 410K token context window.
What is the VerdictPal status of GPT-5.2?
GPT-5.2 carries Solid 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.