GPT
Overview
OpenAI's flagship large language model family behind ChatGPT and the OpenAI API. The current generation is the GPT-6 series, split into Astra, Sol, Terra and Luna tiers, alongside the o-series reasoning line.
Field checks and source notes
When sources disagree on a field, every reading is listed here with its own citation. We do not take a midpoint, invent a missing figure, or decide which side is right — follow the citation and judge for your case.
These field-level notes are recorded verbatim in Chinese in the source data. Open the Chinese version
Plain-language benchmarks
Practical facts
| Context length | Not disclosed |
|---|---|
| Max output | Not disclosed |
| Parameters | Not disclosed |
| Input | $10.00 USD / 1M tokens |
| Output price | $50.00 USD / 1M tokens |
| CNY | Not disclosed |
| Free tier | Not disclosed |
| Output speed | Not disclosed |
| Release date | |
| License | Not disclosed |
Show technical data
Technical benchmark table
This model is evaluated per reasoning tier; available tiers: low / medium / high / xhigh / max. Each row below shows the highest tier measured for that benchmark. Tier switching happens on the compare page.
| Benchmark | Score | Max / unit | Source type | Source | Test date | Conditions |
|---|---|---|---|---|---|---|
| AA Intelligence Index aa-intelligence-index · v5 | 56.9 | score_0_100 / 100 | Independent test | Tiermax | ||
| AA Finance & Accounting aa-finance-index · v5 | 57.4 | score_0_100 / 100 | Independent test | Tiermax | ||
| AA Strategy & Ops aa-strategy-index · v5 | 58 | score_0_100 / 100 | Independent test | Tiermax | ||
| AA Legal aa-legal-index · v5 | 55.6 | score_0_100 / 100 | Independent test | Tiermax | ||
| AA Economics aa-economics-index · v5 | 57.2 | score_0_100 / 100 | Independent test | Tiermax | ||
| AA Engineering aa-engineering-index · v5 | 61.8 | score_0_100 / 100 | Independent test | Tiermax | ||
| AA Healthcare & Medical aa-healthcare-index · v5 | 53.7 | score_0_100 / 100 | Independent test | Tiermax | ||
| GPQA Diamond gpqa-diamond | 96% | percent / 100 | Vendor-reported | OpenAI 自报 | ||
| Terminal-Bench terminal-bench · 4.0 | 57.9% | percent / 100 | Vendor-reported | Tierhigh |
| Version | Release date | Status | Openness | Parameters | What changed | Detail | |
|---|---|---|---|---|---|---|---|
| GPT-6.1 Terra | Active | Closed source | Not disclosed | TBD | Detail | ||
| GPT-6.1 Sol | Active | Closed source | Not disclosed | TBD | Detail | ||
| GPT-6 AstraShowing version | Active | Closed source | Not disclosed | TBD | Detail | ||
| GPT-6 Sol | Superseded | Closed source | Not disclosed | TBD | Detail | ||
| GPT-5.6 Sol | Superseded | Closed source | Not disclosed | TBD | Detail | ||
| GPT-5 | Superseded | Closed source | Not disclosed | TBD | Detail | ||
| GPT-4.1 | Superseded | Closed source | Not disclosed | TBD | Detail | ||
| GPT-4o | Superseded | Closed source | Not disclosed | TBD | Detail | ||
| GPT-4 | Discontinued | Closed source | Not disclosed | TBD | Detail |
Last updated: · Sources on detail page