whatmodel.sh / MPT-30B-Chat
MPT-30B-Chat
↗ share
+ contribute
MPT-30B-Chat is an open-weights language model from MosaicML, released June 2023. Its published size is 30B parameters. Licence: cc-by-nc-sa-4.0.
Catalogue identity notes
Comparison-only. Arena entry 'mpt-30b-chat' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'mpt-30b-chat' as 'MPT-30B-chat' (MosaicML, CC-BY-NC-SA-4.0), linking https://huggingface.co/mosaicml/mpt-30b-chat. Parameters: nominal size from the model name. Released 2023-06: Databricks/MosaicML blog databricks.com/blog/mpt-30b (linked from FastChat's registry as mosaicml.com/blog/mpt-30b), datePublished 2023-06-22. LMArena's table links huggingface.co/mosaicml/mpt-30b-chat (CC-BY-NC-SA-4.0), which no longer resolves; no current download verified.
$ how it compares
The LLMs ranked either side of MPT-30B-Chat, out of 828 with a score, then more from MosaicML.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 691 |  Mistral 7B v0.1 (base) | 36±0 | local | ||
| 692 |  Qwen2.5 1.5B Instruct | 36±1 | local | ||
| 693 | MPT-30B-Chat | 35±2 | comparison only | ||
| 694 |  Gemma 7B (base) | 35±1 | local | ||
| 695 |  Tulu 2 DPO 7B | 35±1 | local | ||
| more from MosaicML | |||||
| 744 | MPT-7B (base) | 30±1 | comparison only | ||
| 765 | MPT-7B-Chat | 27±2 | comparison only | ||
$ what it's good at
chat & writing▁▁▁▃▅▄▆█▇▇▇▃ #416 of 463 · 98% of its score · 3 tests
Beats Gemma 4 E2B, Code Llama 70B Instruct, Phi-3-mini-4k-instruct (June 2024 update) here, though they rank higher overall. Trails Gemma 3 270M IT, SmolLM2 360M Instruct, Qwen2.5 0.5B Instruct here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Polyrating rating (bias-aware re-fit of Chatbot Arena votes, mid-2024) | 1041.0 ✎ | ▂▁▂▁▃▇█▆▇▄▂▂ beats 23/95 | 34% |
| LMArena (text) | 1150.7 ✎ | ▁▁▁▂▃▃▃▆▆▇█▃ beats 40/379 | 34% |
| MT-Bench (GPT-4 single-answer grading, LMSYS runs) | 6.3900 MT-Bench score (1-10) ✎ | ▆▂▂▆▆▄██▂▄▄▆ beats 15/28 | 30% |
$ where to run it
No verified API or download recorded yet · add one
$ how the score was worked out · Polyrating: A Cost-Effective… 34%, LMArena leaderboard dataset 34%, LMSYS Chatbot Arena leaderboa… 30%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3) | 1 | 34% |
 LMArena leaderboard dataset | 1 | 34% |
 LMSYS Chatbot Arena leaderboard Space: MT-Bench column of the published leaderboard table | 1 | 30% |
| prior · pull toward the middle | 2% | |
| weighted average | = 35.4 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json