Updated daily at 05:00 UTC
Language
MPT-7B (Instruct, Chat, StoryWriter)
By Databricks, in the MPT (MosaicML Pretrained Transformer) family.
- Released
- —
- Status
- Legacy
- Context
- —
- Max output
- —
- Input per 1M tokens
- —
- Output per 1M tokens
- —
- Open weights
- Yes
- License
- —
- Parameters
- 6.7B
- 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.
Not enough independent results yet
Only independent and third-party results rank a model; self-reported and unattributed numbers never do.
Benchmark results
Every result we hold for this model, with who ran it and where it was published.
Knowledge & reasoning
Mathematics
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| GSM8K | Exact match | 8.6% | Third party | — | — | Baichuan 2: Open Large-scale Language Models via Epoch AI |
| GSM8K | Exact match | 6.8% | Third party | — | — | Llama 2: Open Foundation and Fine-Tuned Chat Models via Epoch AI |
| GSM8K | Exact match | 9.1% | Self-reported | — | — | Qwen Technical Report via Epoch AI |
| GSM8K | Exact match | 6.8% | Self-reported | — | — | Textbooks Are All You Need II: phi-1.5 technical report via Epoch AI |
Factuality & hallucination
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| TriviaQA | Exact match | 61.6% | Third party | — | — | Llama 2: Open Foundation and Fine-Tuned Chat Models via Epoch AI |
| TriviaQA | Exact match | 61.2% | Third party | — | — | Llama 2: Open Foundation and Fine-Tuned Chat Models via Epoch AI |
| TriviaQA | Exact match | 59.6% | Third party | — | — | Llama 2: Open Foundation and Fine-Tuned Chat Models via Epoch AI |
| TriviaQA | Exact match | 55.7% | Third party | — | — | Llama 2: Open Foundation and Fine-Tuned Chat Models via Epoch AI |