tulu-2-dpo-70b
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelstulu-2-dpo-70b
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
tulu-2-dpo-70b
1,013.47 rating
Confidence interval: 977.98 – 1,048.96
274 votes
- Category
- chinese
- Evaluated configuration
- tulu-2-dpo-70b
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
tulu-2-dpo-70b
1,115.99 rating
Confidence interval: 1,095.06 – 1,136.92
805 votes
- Category
- coding
- Evaluated configuration
- tulu-2-dpo-70b
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
tulu-2-dpo-70b
1,104.83 rating
Confidence interval: 1,085.64 – 1,124.02
1126 votes
- Category
- creative_writing
- Evaluated configuration
- tulu-2-dpo-70b
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
tulu-2-dpo-70b
1,149.89 rating
Confidence interval: 1,139.16 – 1,160.62
5039 votes
- Category
- english
- Evaluated configuration
- tulu-2-dpo-70b
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
tulu-2-dpo-70b
962.71 rating
Confidence interval: 948.91 – 976.51
4397 votes
- Category
- exclude_ties
- Evaluated configuration
- tulu-2-dpo-70b
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
tulu-2-dpo-70b
1,104.26 rating
Confidence interval: 1,088.18 – 1,120.35
1419 votes
- Category
- hard_prompts
- Evaluated configuration
- tulu-2-dpo-70b
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
tulu-2-dpo-70b
1,124.07 rating
Confidence interval: 1,106.73 – 1,141.42
1200 votes
- Category
- hard_prompts_english
- Evaluated configuration
- tulu-2-dpo-70b
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
tulu-2-dpo-70b
1,077.37 rating
Confidence interval: 1,052.16 – 1,102.58
540 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- tulu-2-dpo-70b
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
tulu-2-dpo-70b
1,115.57 rating
Confidence interval: 1,095.65 – 1,135.49
989 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- tulu-2-dpo-70b
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
tulu-2-dpo-70b
1,135.31 rating
Confidence interval: 1,105.24 – 1,165.37
377 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- tulu-2-dpo-70b
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
tulu-2-dpo-70b
1,104.86 rating
Confidence interval: 1,086.24 – 1,123.48
1112 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- tulu-2-dpo-70b
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
tulu-2-dpo-70b
1,098.88 rating
Confidence interval: 1,078.46 – 1,119.29
751 votes
- Category
- industry_mathematical
- Evaluated configuration
- tulu-2-dpo-70b
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
tulu-2-dpo-70b
1,059.85 rating
Confidence interval: 1,028.37 – 1,091.33
348 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- tulu-2-dpo-70b
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
tulu-2-dpo-70b
1,110.08 rating
Confidence interval: 1,093.61 – 1,126.54
1495 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- tulu-2-dpo-70b
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
tulu-2-dpo-70b
1,123.34 rating
Confidence interval: 1,106.67 – 1,140.00
1547 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- tulu-2-dpo-70b
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
tulu-2-dpo-70b
1,110.21 rating
Confidence interval: 1,095.67 – 1,124.74
2008 votes
- Category
- instruction_following
- Evaluated configuration
- tulu-2-dpo-70b
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
tulu-2-dpo-70b
1,105.66 rating
Confidence interval: 1,073.08 – 1,138.25
280 votes
- Category
- longer_query
- Evaluated configuration
- tulu-2-dpo-70b
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
tulu-2-dpo-70b
1,107.20 rating
Confidence interval: 1,088.31 – 1,126.09
888 votes
- Category
- math
- Evaluated configuration
- tulu-2-dpo-70b
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
tulu-2-dpo-70b
1,085.43 rating
Confidence interval: 1,064.32 – 1,106.55
827 votes
- Category
- multi_turn
- Evaluated configuration
- tulu-2-dpo-70b
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
tulu-2-dpo-70b
1,067.91 rating
Confidence interval: 1,051.74 – 1,084.08
1496 votes
- Category
- non_english
- Evaluated configuration
- tulu-2-dpo-70b
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
tulu-2-dpo-70b
1,121.00 rating
Confidence interval: 1,111.31 – 1,130.68
6535 votes
- Category
- overall
- Evaluated configuration
- tulu-2-dpo-70b
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- AI2 ImpACT Low-risk
0 selected Compare 0