MPT-7B-Chat

+ contribute

MPT-7B-Chat is an open-weights language model from MosaicML, released May 2023. Its published size is 7B parameters. Licence: cc-by-nc-sa-4.0.

Catalogue identity notes

Comparison-only. Arena entry 'mpt-7b-chat' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'mpt-7b-chat' as 'MPT-7B-Chat' (MosaicML, CC-BY-NC-SA-4.0), linking https://huggingface.co/mosaicml/mpt-7b-chat. Parameters: nominal size from the model name. Released 2023-05: Databricks/MosaicML blog databricks.com/blog/mpt-7b, datePublished 2023-05-05. LMArena's table links huggingface.co/mosaicml/mpt-7b-chat (CC-BY-NC-SA-4.0), which no longer resolves; no current download verified.

26.6±1.9comparison only: no current run option verifiedfrom 4 benchmark results across 4 sources

$ how it compares

The LLMs ranked either side of MPT-7B-Chat, out of 828 with a score, then more from MosaicML.

#	model	score	where	RAM	released
763	Granite 4.0 H 350M IBM	27±1	local	~1.7GB	2025-10
764	Flan-T5 Large Google	27±2	local	~4.8GB	2022-10
765	MPT-7B-Chat MosaicML	27±2	comparison only		2023-05
766	Gemma 2B IT Google	27±1	local	~3.1GB	2024-02
767	EuroLLM 1.7B Instruct UTTER (EuroLLM)	27±3	local	~2.4GB	2024-08
	more from MosaicML
693	MPT-30B-Chat MosaicML	35±2	comparison only		2023-06
744	MPT-7B (base) MosaicML	30±1	comparison only		2023-05

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▁▁▃▃▅▄▆█▇▇▇▃ #449 of 463 · 91% of its score · 3 tests

Beats Phi-2 (2.7B), Falcon 40B Instruct, ChatGLM3-6B here, though they rank higher overall. Trails Gemma 3 270M IT, SmolLM2 360M Instruct, Granite 4.0 350M here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Polyrating rating (bias-aware re-fit of Chatbot Arena votes, mid-2024)	944.0 ✎	▂▁▃▁▃▇█▆▇▄▂▂ beats 8/95	avg 1201	▇▇▇▇▇▇▇▇▇▇▇▇▇ 32%	blunt
LMArena (text)	1063.4 ✎	▁▁▃▂▃▃▃▆▆▇█▃ beats 9/379	avg 1268	▇▇▇▇▇▇▇▇▇▇▇▇▇ 31%	blunt
MT-Bench (GPT-4 single-answer grading, LMSYS runs)	5.4200 MT-Bench score (1-10) ✎	▆▂▂▆▆▄██▂▄▄▆ beats 12/28	avg 8.819 MT-Bench score (1-10)	▇▇▇▇▇▇▇▇▇▇▇ 28%	sharp · noisy

other tests1 not in a task · 7.6% of its score

test	result	vs the others in its run	difficulty	counts	why
MMLU	33.8% ✎	▁▁▁▁▃▂▃▅█▃▆▃ beats 7/183	medium · avg 73%	▇▇▇ 7.6%	noisy · small run

$ where to run it

No verified API or download recorded yet · add one

$ how the score was worked out · Polyrating: A Cost-Effective… 32%, LMArena leaderboard dataset 31%, LMSYS Chatbot Arena leaderboa… 28% and 1 more

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	licence
Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)	1	▇▇▇▇▇▇▇▇▇▇ 32%	CC-BY-4.0
LMArena leaderboard dataset	1	▇▇▇▇▇▇▇▇▇ 31%	CC BY 4.0
LMSYS Chatbot Arena leaderboard Space: MT-Bench column of the published leaderboard table	1	▇▇▇▇▇▇▇▇ 28%	Apache-2.0
OLMo: Accelerating the Science of Language Models — authors' own runs	1	▇▇ 8%	CC BY 4.0
prior · pull toward the middle		▇ 2%
weighted average		= 26.6

$ improve this page

Update model information Add a place to run it Add a test result Propose a benchmark Correct a benchmark score Edit data on GitHub

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 2026-10-11 02:20 UTC · sources and licences · json