koala-13b
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelskoala-13b
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
koala-13b
880.90 rating
Confidence interval: 849.99 – 911.82
374 votes
- Category
- chinese
- Evaluated configuration
- koala-13b
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
koala-13b
944.72 rating
Confidence interval: 921.26 – 968.17
747 votes
- Category
- coding
- Evaluated configuration
- koala-13b
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
koala-13b
972.83 rating
Confidence interval: 952.58 – 993.08
1200 votes
- Category
- creative_writing
- Evaluated configuration
- koala-13b
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
koala-13b
1,021.73 rating
Confidence interval: 1,010.72 – 1,032.73
5711 votes
- Category
- english
- Evaluated configuration
- koala-13b
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
koala-13b
781.98 rating
Confidence interval: 767.18 – 796.78
4743 votes
- Category
- exclude_ties
- Evaluated configuration
- koala-13b
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
koala-13b
930.29 rating
Confidence interval: 912.61 – 947.97
1250 votes
- Category
- hard_prompts
- Evaluated configuration
- koala-13b
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
koala-13b
942.96 rating
Confidence interval: 923.73 – 962.18
1100 votes
- Category
- hard_prompts_english
- Evaluated configuration
- koala-13b
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
koala-13b
936.42 rating
Confidence interval: 907.22 – 965.62
503 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- koala-13b
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
koala-13b
944.73 rating
Confidence interval: 924.71 – 964.75
1134 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- koala-13b
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
koala-13b
963.61 rating
Confidence interval: 923.66 – 1,003.55
248 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- koala-13b
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
koala-13b
986.22 rating
Confidence interval: 965.98 – 1,006.47
1211 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- koala-13b
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
koala-13b
928.57 rating
Confidence interval: 905.92 – 951.23
692 votes
- Category
- industry_mathematical
- Evaluated configuration
- koala-13b
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
koala-13b
956.01 rating
Confidence interval: 916.16 – 995.86
253 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- koala-13b
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
koala-13b
960.84 rating
Confidence interval: 943.22 – 978.46
1572 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- koala-13b
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
koala-13b
979.41 rating
Confidence interval: 961.81 – 997.00
1515 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- koala-13b
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
koala-13b
943.53 rating
Confidence interval: 928.58 – 958.47
1913 votes
- Category
- instruction_following
- Evaluated configuration
- koala-13b
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
koala-13b
932.31 rating
Confidence interval: 911.31 – 953.31
751 votes
- Category
- math
- Evaluated configuration
- koala-13b
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
koala-13b
923.43 rating
Confidence interval: 899.56 – 947.30
792 votes
- Category
- multi_turn
- Evaluated configuration
- koala-13b
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
koala-13b
916.24 rating
Confidence interval: 898.59 – 933.89
1254 votes
- Category
- non_english
- Evaluated configuration
- koala-13b
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
koala-13b
989.57 rating
Confidence interval: 979.88 – 999.25
6965 votes
- Category
- overall
- Evaluated configuration
- koala-13b
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- Non-commercial
0 selected Compare 0