MPT 30B Chat
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsMPT 30B Chat
Model evaluation
Capability & preference
Human preference · Arena
Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.
Recorded results
Only the same benchmark, version, workload, scenario and unit share a row. Missing results are not zero. System results include the full submitted hardware and software configuration.
Arena text preference / codinghuman preference · 2026-10-28 · rating
MPT 30B Chat
1,039.01 rating
Confidence interval: 1,004.51 – 1,073.51
258 votes
- Category
- coding
- Evaluated configuration
- MPT 30B Chat
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
MPT 30B Chat
1,073.75 rating
Confidence interval: 1,045.16 – 1,102.33
452 votes
- Category
- creative_writing
- Evaluated configuration
- MPT 30B Chat
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
MPT 30B Chat
1,102.20 rating
Confidence interval: 1,088.54 – 1,115.86
2056 votes
- Category
- english
- Evaluated configuration
- MPT 30B Chat
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
MPT 30B Chat
895.09 rating
Confidence interval: 877.43 – 912.75
1777 votes
- Category
- exclude_ties
- Evaluated configuration
- MPT 30B Chat
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
MPT 30B Chat
1,051.43 rating
Confidence interval: 1,024.90 – 1,077.97
434 votes
- Category
- hard_prompts
- Evaluated configuration
- MPT 30B Chat
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
MPT 30B Chat
1,082.38 rating
Confidence interval: 1,052.78 – 1,111.98
359 votes
- Category
- hard_prompts_english
- Evaluated configuration
- MPT 30B Chat
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
MPT 30B Chat
1,008.35 rating
Confidence interval: 970.57 – 1,046.14
207 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- MPT 30B Chat
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
MPT 30B Chat
1,055.11 rating
Confidence interval: 1,026.44 – 1,083.78
435 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- MPT 30B Chat
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
MPT 30B Chat
1,038.20 rating
Confidence interval: 1,011.94 – 1,064.47
509 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- MPT 30B Chat
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
MPT 30B Chat
1,053.17 rating
Confidence interval: 1,016.47 – 1,089.86
218 votes
- Category
- industry_mathematical
- Evaluated configuration
- MPT 30B Chat
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
MPT 30B Chat
1,057.51 rating
Confidence interval: 1,033.12 – 1,081.90
575 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- MPT 30B Chat
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
MPT 30B Chat
1,079.24 rating
Confidence interval: 1,056.71 – 1,101.77
647 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- MPT 30B Chat
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
MPT 30B Chat
1,053.79 rating
Confidence interval: 1,032.52 – 1,075.06
718 votes
- Category
- instruction_following
- Evaluated configuration
- MPT 30B Chat
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
MPT 30B Chat
1,046.59 rating
Confidence interval: 1,012.74 – 1,080.44
242 votes
- Category
- math
- Evaluated configuration
- MPT 30B Chat
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
MPT 30B Chat
1,054.52 rating
Confidence interval: 1,022.57 – 1,086.47
341 votes
- Category
- multi_turn
- Evaluated configuration
- MPT 30B Chat
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
MPT 30B Chat
990.44 rating
Confidence interval: 966.83 – 1,014.05
516 votes
- Category
- non_english
- Evaluated configuration
- MPT 30B Chat
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
MPT 30B Chat
1,068.58 rating
Confidence interval: 1,056.49 – 1,080.68
2572 votes
- Category
- overall
- Evaluated configuration
- MPT 30B Chat
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- CC-BY-NC-SA-4.0
0 selected Compare 0