LLaMA-13B
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsLLaMA-13B
AI model Released
Capability & preference
General capability · ECI
A cross-benchmark capability estimate. Index points, not a percentage; intervals show uncertainty.
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 / codinghuman preference · 2026-10-28 · rating
LLaMA-13B
682.64 rating
Confidence interval: 644.96 – 720.33
304 votes
- Category
- coding
- Evaluated configuration
- LLaMA 13B
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
LLaMA-13B
793.68 rating
Confidence interval: 761.81 – 825.55
431 votes
- Category
- creative_writing
- Evaluated configuration
- LLaMA 13B
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
LLaMA-13B
845.82 rating
Confidence interval: 828.94 – 862.70
1953 votes
- Category
- english
- Evaluated configuration
- LLaMA 13B
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
LLaMA-13B
533.64 rating
Confidence interval: 508.86 – 558.43
1647 votes
- Category
- exclude_ties
- Evaluated configuration
- LLaMA 13B
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
LLaMA-13B
727.90 rating
Confidence interval: 698.83 – 756.97
430 votes
- Category
- hard_prompts
- Evaluated configuration
- LLaMA 13B
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
LLaMA-13B
734.64 rating
Confidence interval: 702.14 – 767.15
371 votes
- Category
- hard_prompts_english
- Evaluated configuration
- LLaMA 13B
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
LLaMA-13B
784.74 rating
Confidence interval: 754.26 – 815.22
402 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- LLaMA 13B
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
LLaMA-13B
806.15 rating
Confidence interval: 774.26 – 838.05
414 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- LLaMA 13B
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
LLaMA-13B
833.42 rating
Confidence interval: 797.01 – 869.83
228 votes
- Category
- industry_mathematical
- Evaluated configuration
- LLaMA 13B
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
LLaMA-13B
719.21 rating
Confidence interval: 691.10 – 747.32
566 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- LLaMA 13B
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
LLaMA-13B
809.00 rating
Confidence interval: 781.29 – 836.71
513 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- LLaMA 13B
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
LLaMA-13B
780.70 rating
Confidence interval: 756.61 – 804.78
584 votes
- Category
- instruction_following
- Evaluated configuration
- LLaMA 13B
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
LLaMA-13B
837.77 rating
Confidence interval: 805.31 – 870.23
252 votes
- Category
- math
- Evaluated configuration
- LLaMA 13B
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
LLaMA-13B
753.14 rating
Confidence interval: 710.49 – 795.80
247 votes
- Category
- multi_turn
- Evaluated configuration
- LLaMA 13B
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
LLaMA-13B
818.44 rating
Confidence interval: 792.19 – 844.68
438 votes
- Category
- non_english
- Evaluated configuration
- LLaMA 13B
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
LLaMA-13B
833.48 rating
Confidence interval: 817.95 – 849.02
2391 votes
- Category
- overall
- Evaluated configuration
- LLaMA 13B
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
LLaMA-13B
682.74 rating
Confidence interval: 645.02 – 720.47
304 votes
- Category
- coding
- Evaluated configuration
- llama-13b
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
LLaMA-13B
793.83 rating
Confidence interval: 761.95 – 825.72
431 votes
- Category
- creative_writing
- Evaluated configuration
- llama-13b
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
LLaMA-13B
845.77 rating
Confidence interval: 828.88 – 862.65
1953 votes
- Category
- english
- Evaluated configuration
- llama-13b
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
LLaMA-13B
533.66 rating
Confidence interval: 508.85 – 558.46
1647 votes
- Category
- exclude_ties
- Evaluated configuration
- llama-13b
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
LLaMA-13B
727.89 rating
Confidence interval: 698.80 – 756.98
430 votes
- Category
- hard_prompts
- Evaluated configuration
- llama-13b
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
LLaMA-13B
734.53 rating
Confidence interval: 702.00 – 767.06
371 votes
- Category
- hard_prompts_english
- Evaluated configuration
- llama-13b
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
LLaMA-13B
784.80 rating
Confidence interval: 754.30 – 815.30
402 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- llama-13b
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
LLaMA-13B
806.13 rating
Confidence interval: 774.22 – 838.04
414 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- llama-13b
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
LLaMA-13B
833.42 rating
Confidence interval: 796.99 – 869.85
228 votes
- Category
- industry_mathematical
- Evaluated configuration
- llama-13b
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
LLaMA-13B
719.29 rating
Confidence interval: 691.16 – 747.42
566 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- llama-13b
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
LLaMA-13B
809.07 rating
Confidence interval: 781.34 – 836.79
513 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- llama-13b
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
LLaMA-13B
780.71 rating
Confidence interval: 756.60 – 804.81
584 votes
- Category
- instruction_following
- Evaluated configuration
- llama-13b
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
LLaMA-13B
837.73 rating
Confidence interval: 805.26 – 870.20
252 votes
- Category
- math
- Evaluated configuration
- llama-13b
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
LLaMA-13B
753.14 rating
Confidence interval: 710.45 – 795.83
247 votes
- Category
- multi_turn
- Evaluated configuration
- llama-13b
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
LLaMA-13B
818.53 rating
Confidence interval: 792.27 – 844.80
438 votes
- Category
- non_english
- Evaluated configuration
- llama-13b
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
LLaMA-13B
833.47 rating
Confidence interval: 817.92 – 849.01
2391 votes
- Category
- overall
- Evaluated configuration
- llama-13b
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- Non-commercial
0 selected Compare 0
* Provisional data