Updated daily at 05:00 UTC
- Released
- —
- Status
- Legacy
- Context
- —
- Max output
- —
- Input per 1M tokens
- —
- Output per 1M tokens
- —
- Open weights
- Yes
- License
- —
- Parameters
- 12B
- Knowledge cutoff
- —
- Reasoning
- No
- Modalities
- text → text
Category scores
Out of 100, from independent and third-party results only, by method category-2026-09-29.1.
| Category | Score | Rank | Coverage |
|---|---|---|---|
| Human preference | 8.3 | Not ranked | 1 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 |
|---|---|---|---|---|---|---|
| AI2 Reasoning Challenge (ARC) | Challenge set accuracy | 39.6% | Self-reported | — | — | XGen-7B Technical Report via Epoch AI |
| HellaSwag | Accuracy | 70.8% | Self-reported | — | — | XGen-7B Technical Report via Epoch AI |
| MMLU | Accuracy | 26.2% | Self-reported | — | — | XGen-7B Technical Report via Epoch AI |
| MMLU | Accuracy | 25.4% | Self-reported | — | — | XGen-7B Technical Report via Epoch AI |
| OpenBookQA | Accuracy | 39.2% | Self-reported | — | — | XGen-7B Technical Report via Epoch AI |
| PIQA | Accuracy | 75.4% | Self-reported | — | — | XGen-7B Technical Report via Epoch AI |
| WinoGrande | Accuracy | 61.8% | Self-reported | — | — | XGen-7B Technical Report via Epoch AI |
Human preference
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Text Arena (arena.ai) | Arena score (Elo scale) | 982 | Independent | — | 25 Sep 2026 | Arena |
| Text Arena (arena.ai) | Votes | 3412 | Independent | — | 25 Sep 2026 | Arena |
Other Dolly versions
- Dolly (v1, 6B)Mar 2023