MPT 7B Chat
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsMPT 7B 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 / chinesehuman preference · 2026-10-28 · rating
MPT 7B Chat
954.66 rating
Confidence interval: 913.50 – 995.81
178 votes
- Category
- chinese
- Evaluated configuration
- MPT 7B Chat
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
MPT 7B Chat
912.85 rating
Confidence interval: 881.89 – 943.80
397 votes
- Category
- coding
- Evaluated configuration
- MPT 7B Chat
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
MPT 7B Chat
957.37 rating
Confidence interval: 933.70 – 981.04
683 votes
- Category
- creative_writing
- Evaluated configuration
- MPT 7B Chat
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
MPT 7B Chat
980.67 rating
Confidence interval: 967.82 – 993.52
3278 votes
- Category
- english
- Evaluated configuration
- MPT 7B Chat
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
MPT 7B Chat
726.86 rating
Confidence interval: 709.18 – 744.54
2652 votes
- Category
- exclude_ties
- Evaluated configuration
- MPT 7B Chat
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
MPT 7B Chat
895.42 rating
Confidence interval: 873.75 – 917.08
714 votes
- Category
- hard_prompts
- Evaluated configuration
- MPT 7B Chat
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
MPT 7B Chat
908.34 rating
Confidence interval: 884.57 – 932.11
626 votes
- Category
- hard_prompts_english
- Evaluated configuration
- MPT 7B Chat
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
MPT 7B Chat
864.44 rating
Confidence interval: 828.31 – 900.58
306 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- MPT 7B Chat
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
MPT 7B Chat
928.13 rating
Confidence interval: 904.44 – 951.83
717 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- MPT 7B Chat
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
MPT 7B Chat
913.16 rating
Confidence interval: 888.96 – 937.36
677 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- MPT 7B Chat
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
MPT 7B Chat
906.85 rating
Confidence interval: 878.46 – 935.24
397 votes
- Category
- industry_mathematical
- Evaluated configuration
- MPT 7B Chat
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
MPT 7B Chat
912.22 rating
Confidence interval: 890.58 – 933.86
882 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- MPT 7B Chat
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
MPT 7B Chat
972.73 rating
Confidence interval: 952.35 – 993.10
892 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- MPT 7B Chat
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
MPT 7B Chat
906.60 rating
Confidence interval: 888.48 – 924.71
1115 votes
- Category
- instruction_following
- Evaluated configuration
- MPT 7B Chat
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
MPT 7B Chat
919.20 rating
Confidence interval: 894.01 – 944.40
471 votes
- Category
- math
- Evaluated configuration
- MPT 7B Chat
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
MPT 7B Chat
901.52 rating
Confidence interval: 872.75 – 930.29
466 votes
- Category
- multi_turn
- Evaluated configuration
- MPT 7B Chat
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
MPT 7B Chat
912.21 rating
Confidence interval: 890.24 – 934.17
646 votes
- Category
- non_english
- Evaluated configuration
- MPT 7B Chat
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
MPT 7B Chat
955.19 rating
Confidence interval: 943.48 – 966.90
3924 votes
- Category
- overall
- Evaluated configuration
- MPT 7B Chat
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- CC-BY-NC-SA-4.0
0 selected Compare 0