Updated daily at 05:00 UTC
- Released
- 22 Sep 2026
- Status
- Current
- Context
- 1.1M
- Max output
- 128K
- Input per 1M tokens
- $2.00
- Output per 1M tokens
- $10.00
- Open weights
- No
- License
- proprietary
- Parameters
- —
- Knowledge cutoff
- 20 Apr 2026
- Reasoning
- Yes
- Modalities
- text, image → text
Category scores
Out of 100, from independent and third-party results only, by method category-2026-09-29.1.
| Category | Score | Rank | Coverage |
|---|---|---|---|
| Knowledge & reasoning | 61.4 | 6 | 2 of 4 |
| Coding & software engineering | 49.3 | Not ranked | 1 of 5 |
| Vision & multimodal understanding | 40.5 | Not ranked | 1 of 3 |
| Human preference | 70.8 | Not ranked | 2 of 5 |
Benchmark results
Every result we hold for this model, with who ran it and where it was published.
Knowledge & reasoning
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| DTBench (Decision Theory Benchmark) | Accuracy (capability questions) | 97.3% | Third party | max | — | https://conceptualreasoning.ai/dtbench via Epoch AI |
| Earthborne Rangers (EBR-bench) | Objectives reached | 53.3% | Independent | max | 22 Sep 2026 | Epoch AI |
| LMCA (Language Model Conceptual Argumentation) | Correlation with expert ratings (Pearson r) | 0.5908 | Third party | max | — | https://conceptualreasoning.ai/lmca via Epoch AI |
Coding & software engineering
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| FrontierCode | Main score (Mean@5) | 49.3% | Third party | max | — | https://cognition.com/frontiercode via Epoch AI |
Professional knowledge work
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| APEX-Agents | Pass@1 (all rubric criteria met) | 54.3% | Source not stated | max | — | Epoch AI via Epoch AI |
Vision & multimodal understanding
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Furniture Assembly | Score | 58.3% | Independent | max | 23 Sep 2026 | Epoch AI |
Human preference
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Code Arena: WebDev (arena.ai) | Arena score (Elo scale) | 1681 | Independent | max | 25 Sep 2026 | Arena |
| Code Arena: WebDev (arena.ai) | Votes | 2019 | Independent | max | 25 Sep 2026 | Arena |
| Text Arena (arena.ai) | Arena score (Elo scale) | 1457 | Independent | max | 25 Sep 2026 | Arena |
| Text Arena (arena.ai) | Votes | 4773 | Independent | max | 25 Sep 2026 | Arena |
Other GPT-6 versions
- GPT-6 Luna22 Sep 2026
- GPT-6 Astra3 Sep 2026