step-3
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsstep-3
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
step-3
1,397.26 rating
Confidence interval: 1,364.89 – 1,429.63
312 votes
- Category
- chinese
- Evaluated configuration
- step-3
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
step-3
1,367.01 rating
Confidence interval: 1,350.47 – 1,383.54
1212 votes
- Category
- coding
- Evaluated configuration
- step-3
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
step-3
1,320.89 rating
Confidence interval: 1,300.05 – 1,341.72
770 votes
- Category
- creative_writing
- Evaluated configuration
- step-3
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
step-3
1,373.12 rating
Confidence interval: 1,362.17 – 1,384.06
2775 votes
- Category
- english
- Evaluated configuration
- step-3
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
step-3
1,311.17 rating
Confidence interval: 1,300.61 – 1,321.73
4456 votes
- Category
- exclude_ties
- Evaluated configuration
- step-3
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
step-3
1,332.75 rating
Confidence interval: 1,298.08 – 1,367.41
265 votes
- Category
- expert
- Evaluated configuration
- step-3
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
step-3
1,370.67 rating
Confidence interval: 1,324.77 – 1,416.58
153 votes
- Category
- german
- Evaluated configuration
- step-3
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
step-3
1,354.75 rating
Confidence interval: 1,344.10 – 1,365.40
2960 votes
- Category
- hard_prompts
- Evaluated configuration
- step-3
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
step-3
1,378.22 rating
Confidence interval: 1,362.33 – 1,394.11
1327 votes
- Category
- hard_prompts_english
- Evaluated configuration
- step-3
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
step-3
1,343.00 rating
Confidence interval: 1,326.20 – 1,359.79
1141 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- step-3
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
step-3
1,331.51 rating
Confidence interval: 1,314.30 – 1,348.71
1086 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- step-3
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
step-3
1,336.84 rating
Confidence interval: 1,308.34 – 1,365.34
408 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- step-3
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
step-3
1,353.73 rating
Confidence interval: 1,335.54 – 1,371.91
1069 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- step-3
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
step-3
1,375.46 rating
Confidence interval: 1,342.24 – 1,408.68
300 votes
- Category
- industry_mathematical
- Evaluated configuration
- step-3
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
step-3
1,361.64 rating
Confidence interval: 1,331.21 – 1,392.07
349 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- step-3
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
step-3
1,365.05 rating
Confidence interval: 1,352.41 – 1,377.70
2089 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- step-3
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
step-3
1,326.47 rating
Confidence interval: 1,311.25 – 1,341.70
1386 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- step-3
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
step-3
1,332.04 rating
Confidence interval: 1,317.66 – 1,346.42
1637 votes
- Category
- instruction_following
- Evaluated configuration
- step-3
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
step-3
1,268.88 rating
Confidence interval: 1,223.95 – 1,313.80
181 votes
- Category
- korean
- Evaluated configuration
- step-3
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
step-3
1,325.52 rating
Confidence interval: 1,309.31 – 1,341.73
1272 votes
- Category
- longer_query
- Evaluated configuration
- step-3
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
step-3
1,365.91 rating
Confidence interval: 1,334.78 – 1,397.03
350 votes
- Category
- math
- Evaluated configuration
- step-3
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
step-3
1,340.51 rating
Confidence interval: 1,322.29 – 1,358.73
1037 votes
- Category
- multi_turn
- Evaluated configuration
- step-3
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
step-3
1,327.07 rating
Confidence interval: 1,317.26 – 1,336.88
3515 votes
- Category
- non_english
- Evaluated configuration
- step-3
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
step-3
1,350.27 rating
Confidence interval: 1,342.83 – 1,357.71
6293 votes
- Category
- overall
- Evaluated configuration
- step-3
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
step-3
1,300.62 rating
Confidence interval: 1,272.99 – 1,328.24
449 votes
- Category
- polish
- Evaluated configuration
- step-3
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
step-3
1,330.23 rating
Confidence interval: 1,304.73 – 1,355.73
492 votes
- Category
- russian
- Evaluated configuration
- step-3
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
step-3
1,370.71 rating
Confidence interval: 1,329.15 – 1,412.27
210 votes
- Category
- spanish
- Evaluated configuration
- step-3
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- Apache 2.0
0 selected Compare 0