MPT-7B
MPT-7B.
12
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
MosaicML May 2023 MPT-7B
Open weights
73.7
#244 of 256
Epoch Capabilities Index
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| PIQA | 80.6% | #32 of 58 | Claim in Qwen Technical Report, via Epoch AI | |
| HellaSwag | 76.4% | #37 of 63 | Claim in Qwen Technical Report, via Epoch AI | |
| OpenBookQA | 51.4% | #27 of 41 | Claim in Llama 2: Open Foundation and Fine-Tuned Chat Models, via Epoch AI | |
| WinoGrande | 68.6% | #52 of 76 | Claim in XGen-7B Technical Report, via Epoch AI | |
| BoolQ | 75% | #44 of 61 | Claim in Qwen Technical Report, via Epoch AI | |
| ARC-Challenge | 42.6% | #55 of 75 | Claim in Qwen Technical Report, via Epoch AI | |
| BIG-Bench Hard | 35.6% | #38 of 45 | Claim in Qwen Technical Report, via Epoch AI | |
| LAMBADA | 70% | #22 of 26 | Claim in Qwen Technical Report, via Epoch AI | |
| TriviaQA | 61.6% | #34 of 38 | Claim in Llama 2: Open Foundation and Fine-Tuned Chat Models, via Epoch AI | |
| MMLU | 30.8% | #77 of 85 | Claim in Qwen Technical Report, via Epoch AI | |
| LMArena (Elo) | 1,064 | #328 of 335 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GSM8K | 9.10% | #68 of 70 | Claim in Qwen Technical Report, via Epoch AI |
MosaicML's models over time
MosaicML's models in color, against every other model on the Epoch Capabilities Index, by release date.
Source: Epoch Capabilities Index, Epoch AI (CC BY 4.0)