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 · 2026-10-15 · rating
mpt-30b-chat
1,039.11 rating
Confidence interval: 1,004.59 – 1,073.63
258 votes
- Category
- coding
- Evaluated configuration
- mpt-30b-chat
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
mpt-30b-chat
1,073.90 rating
Confidence interval: 1,045.31 – 1,102.50
452 votes
- Category
- creative_writing
- Evaluated configuration
- mpt-30b-chat
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
mpt-30b-chat
1,102.15 rating
Confidence interval: 1,088.49 – 1,115.81
2056 votes
- Category
- english
- Evaluated configuration
- mpt-30b-chat
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
mpt-30b-chat
895.10 rating
Confidence interval: 877.44 – 912.77
1777 votes
- Category
- exclude_ties
- Evaluated configuration
- mpt-30b-chat
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
mpt-30b-chat
1,051.42 rating
Confidence interval: 1,024.88 – 1,077.97
434 votes
- Category
- hard_prompts
- Evaluated configuration
- mpt-30b-chat
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
mpt-30b-chat
1,082.27 rating
Confidence interval: 1,052.66 – 1,111.88
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 · 2026-10-15 · rating
mpt-30b-chat
1,008.39 rating
Confidence interval: 970.58 – 1,046.21
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 · 2026-10-15 · rating
mpt-30b-chat
1,055.17 rating
Confidence interval: 1,026.49 – 1,083.85
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 · 2026-10-15 · rating
mpt-30b-chat
1,038.18 rating
Confidence interval: 1,011.91 – 1,064.46
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 · 2026-10-15 · rating
mpt-30b-chat
1,053.16 rating
Confidence interval: 1,016.45 – 1,089.87
218 votes
- Category
- industry_mathematical
- Evaluated configuration
- mpt-30b-chat
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
mpt-30b-chat
1,057.59 rating
Confidence interval: 1,033.19 – 1,081.99
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 · 2026-10-15 · rating
mpt-30b-chat
1,079.30 rating
Confidence interval: 1,056.76 – 1,101.84
647 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- mpt-30b-chat
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
mpt-30b-chat
1,053.80 rating
Confidence interval: 1,032.52 – 1,075.08
718 votes
- Category
- instruction_following
- Evaluated configuration
- mpt-30b-chat
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
mpt-30b-chat
1,046.55 rating
Confidence interval: 1,012.69 – 1,080.41
242 votes
- Category
- math
- Evaluated configuration
- mpt-30b-chat
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
mpt-30b-chat
1,054.52 rating
Confidence interval: 1,022.56 – 1,086.48
341 votes
- Category
- multi_turn
- Evaluated configuration
- mpt-30b-chat
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
mpt-30b-chat
990.53 rating
Confidence interval: 966.91 – 1,014.15
516 votes
- Category
- non_english
- Evaluated configuration
- mpt-30b-chat
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
mpt-30b-chat
1,068.57 rating
Confidence interval: 1,056.47 – 1,080.66
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