Updated daily at 05:00 UTC
- Released
- 19 Apr 2023
- Status
- Legacy
- Context
- 4.1K
- Max output
- —
- Input per 1M tokens
- —
- Output per 1M tokens
- —
- Open weights
- Yes
- License
- cc-by-nc-sa-4.0
- Parameters
- 7B
- 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 | 7.1 | 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 | 27.0% | Self-reported | — | — | XGen-7B Technical Report via Epoch AI |
| HellaSwag | Accuracy | 40.7% | Self-reported | — | — | XGen-7B Technical Report via Epoch AI |
| OpenBookQA | Accuracy | 32.4% | Self-reported | — | — | XGen-7B Technical Report via Epoch AI |
| PIQA | Accuracy | 65.8% | Self-reported | — | — | XGen-7B Technical Report via Epoch AI |
| WinoGrande | Accuracy | 51.5% | 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) | 953 | Independent | — | 25 Sep 2026 | Arena |
| Text Arena (arena.ai) | Votes | 3287 | Independent | — | 25 Sep 2026 | Arena |
Other StableLM versions
- StableLM 2 12B8 Apr 2024
- StableLM 2 1.6B19 Jan 2024
- StableLM Zephyr 3B21 Nov 2023
- StableLM-3B-4E1T29 Sep 2023
- Stable Beluga 2 (Llama 2 70B fine-tune)20 Jul 2023
- StableLM-Alpha 3B19 Apr 2023