GPQA DiamondVerified
80.8%
GPQA Diamond (AA run)
Models / OpenAI
GPT-5 (low)
GPT-5 (low) · Released 2025-08-07
Listed on Artificial Analysis with API pricing $1.25/$10 per 1M tokens. Benchmark rows sync from the AA snapshot — see the ledger on this page.
Frontier model tracked on Artificial Analysis. Use the benchmark ledger below for sourced scores; we do not infer numbers beyond published rows.
Composite43
ContextUnlisted
Input / 1M$1.3
Output / 1M$10
Knowledge cutoffunpublished
Output speed104 t/s
Statuslightweight
Not enough families covered yet.Add more benchmark rows for GPT-5 (low) to see the family profile.
Benchmark placements
Per-benchmark positions
Where GPT-5 (low) 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 output speed | Performance | #56/ 195 | Artificial Analysis | 2026-10-12 | |
| Humanity's Last Exam | Reasoning | #131/ 186 | 20 | Artificial Analysis | 2026-09-28 |
| GPQA Diamond | Reasoning | #138/ 184 | 81 | Artificial Analysis | 2026-09-28 |
| Terminal-Bench | Agentic | #143/ 167 | 27 | 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 (low) shows up, it's highlighted.
ReasoningGPT-5 (low) · 81
- 196
- 295
- 395
Math
- 152
- 252
- 350
AgenticGPT-5 (low) · 27
- 191
- 289
- 389
Long context
- 189
- 286
- 385
Newest receipts
4 recentLast 120 days
Benchmark rows added to the public ledger for GPT-5 (low) in the last 120 days. Older rows live in the full table below.
| Benchmark | Family | Score | Source | Days ago |
|---|---|---|---|---|
| AA output speed | Performance | 104 t/s | Artificial Analysis | 10 |
| GPQA Diamond | Reasoning | 80.8% | Artificial Analysis | 24 |
| Humanity's Last Exam | Reasoning | 19.6% | Artificial Analysis | 24 |
| Terminal-Bench | Agentic | 26.52% | 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 (low) 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 (low). Scores link to the original source; gaps mean no public row exists yet.
4 of 13 catalog benchmarks have a sourced row for GPT-5 (low).
Reasoning
Humanity's Last ExamVerified
19.6%
HLE (AA run)
Agentic
Terminal-BenchVerified
26.52%
Terminal-Bench Hard (AA run)
Performance
AA output speedVerified
104 t/s
Median output tokens/s (1k prompt, default provider)
Sources
Where the numbers come from
- Artificial Analysis models index· checked 2026-08-09
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 (low)?
GPT-5 (low) is a OpenAI model: Listed on Artificial Analysis with API pricing $1.25/$10 per 1M tokens. Benchmark rows sync from the AA snapshot — see the ledger on this page.
What is GPT-5 (low) for?
Frontier model tracked on Artificial Analysis. Use the benchmark ledger below for sourced scores; we do not infer numbers beyond published rows.
What does GPT-5 (low) cost?
GPT-5 (low) lists $1.3 input and $10 output per 1M tokens. Pricing last checked 2026-08-09.
How large is the GPT-5 (low) context window?
GPT-5 (low) does not publish a context window on the sources checked for this page.
What is the VerdictPal status of GPT-5 (low)?
GPT-5 (low) 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.