dolly-v2-12b
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsdolly-v2-12b
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 · 2026-10-15 · rating
dolly-v2-12b
836.39 rating
Confidence interval: 792.09 – 880.68
177 votes
- Category
- chinese
- Evaluated configuration
- dolly-v2-12b
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
dolly-v2-12b
776.09 rating
Confidence interval: 743.61 – 808.58
396 votes
- Category
- coding
- Evaluated configuration
- dolly-v2-12b
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
dolly-v2-12b
863.57 rating
Confidence interval: 836.63 – 890.52
565 votes
- Category
- creative_writing
- Evaluated configuration
- dolly-v2-12b
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
dolly-v2-12b
866.65 rating
Confidence interval: 851.99 – 881.31
2765 votes
- Category
- english
- Evaluated configuration
- dolly-v2-12b
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
dolly-v2-12b
567.72 rating
Confidence interval: 546.55 – 588.90
2379 votes
- Category
- exclude_ties
- Evaluated configuration
- dolly-v2-12b
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
dolly-v2-12b
803.60 rating
Confidence interval: 780.01 – 827.19
615 votes
- Category
- hard_prompts
- Evaluated configuration
- dolly-v2-12b
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
dolly-v2-12b
809.23 rating
Confidence interval: 783.10 – 835.37
523 votes
- Category
- hard_prompts_english
- Evaluated configuration
- dolly-v2-12b
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
dolly-v2-12b
734.18 rating
Confidence interval: 690.33 – 778.03
233 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- dolly-v2-12b
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
dolly-v2-12b
809.00 rating
Confidence interval: 782.41 – 835.60
558 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- dolly-v2-12b
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
dolly-v2-12b
800.80 rating
Confidence interval: 772.61 – 828.98
589 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- dolly-v2-12b
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
dolly-v2-12b
839.91 rating
Confidence interval: 809.57 – 870.25
343 votes
- Category
- industry_mathematical
- Evaluated configuration
- dolly-v2-12b
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
dolly-v2-12b
789.03 rating
Confidence interval: 765.78 – 812.29
824 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- dolly-v2-12b
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
dolly-v2-12b
872.25 rating
Confidence interval: 849.37 – 895.13
732 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- dolly-v2-12b
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
dolly-v2-12b
813.59 rating
Confidence interval: 792.87 – 834.30
899 votes
- Category
- instruction_following
- Evaluated configuration
- dolly-v2-12b
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
dolly-v2-12b
870.90 rating
Confidence interval: 842.43 – 899.36
370 votes
- Category
- math
- Evaluated configuration
- dolly-v2-12b
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
dolly-v2-12b
740.35 rating
Confidence interval: 705.05 – 775.65
356 votes
- Category
- multi_turn
- Evaluated configuration
- dolly-v2-12b
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
dolly-v2-12b
835.58 rating
Confidence interval: 812.21 – 858.96
647 votes
- Category
- non_english
- Evaluated configuration
- dolly-v2-12b
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
dolly-v2-12b
851.08 rating
Confidence interval: 837.85 – 864.32
3412 votes
- Category
- overall
- Evaluated configuration
- dolly-v2-12b
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- MIT
0 selected Compare 0