Llama-2-7b-chat
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsLlama-2-7b-chat
AI model
- Open weights
- Yes
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 · 2026-10-28 · rating
Llama-2-7b-chat
972.90 rating
Confidence interval: 953.18 – 992.63
956 votes
- Category
- chinese
- Evaluated configuration
- Llama 2 7B Chat
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Llama-2-7b-chat
1,001.64 rating
Confidence interval: 987.66 – 1,015.61
1956 votes
- Category
- coding
- Evaluated configuration
- Llama 2 7B Chat
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Llama-2-7b-chat
1,032.94 rating
Confidence interval: 1,019.38 – 1,046.50
2341 votes
- Category
- creative_writing
- Evaluated configuration
- Llama 2 7B Chat
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Llama-2-7b-chat
1,095.85 rating
Confidence interval: 1,087.95 – 1,103.76
10259 votes
- Category
- english
- Evaluated configuration
- Llama 2 7B Chat
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Llama-2-7b-chat
861.11 rating
Confidence interval: 850.78 – 871.44
9245 votes
- Category
- exclude_ties
- Evaluated configuration
- Llama 2 7B Chat
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Llama-2-7b-chat
1,035.88 rating
Confidence interval: 1,008.16 – 1,063.61
411 votes
- Category
- expert
- Evaluated configuration
- Llama 2 7B Chat
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
Llama-2-7b-chat
970.05 rating
Confidence interval: 926.90 – 1,013.21
257 votes
- Category
- french
- Evaluated configuration
- Llama 2 7B Chat
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Llama-2-7b-chat
977.49 rating
Confidence interval: 942.61 – 1,012.38
327 votes
- Category
- german
- Evaluated configuration
- Llama 2 7B Chat
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Llama-2-7b-chat
1,009.07 rating
Confidence interval: 998.28 – 1,019.87
3289 votes
- Category
- hard_prompts
- Evaluated configuration
- Llama 2 7B Chat
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Llama-2-7b-chat
1,031.62 rating
Confidence interval: 1,019.26 – 1,043.97
2560 votes
- Category
- hard_prompts_english
- Evaluated configuration
- Llama 2 7B Chat
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
Llama-2-7b-chat
1,027.82 rating
Confidence interval: 1,009.92 – 1,045.72
1255 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- Llama 2 7B Chat
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
Llama-2-7b-chat
1,019.67 rating
Confidence interval: 1,006.17 – 1,033.17
2220 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- Llama 2 7B Chat
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
Llama-2-7b-chat
1,064.90 rating
Confidence interval: 1,042.27 – 1,087.54
760 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- Llama 2 7B Chat
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
Llama-2-7b-chat
1,046.89 rating
Confidence interval: 1,033.54 – 1,060.25
2474 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- Llama 2 7B Chat
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
Llama-2-7b-chat
1,038.65 rating
Confidence interval: 1,023.31 – 1,053.99
1401 votes
- Category
- industry_mathematical
- Evaluated configuration
- Llama 2 7B Chat
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
Llama-2-7b-chat
1,035.93 rating
Confidence interval: 1,013.02 – 1,058.84
764 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- Llama 2 7B Chat
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
Llama-2-7b-chat
1,028.87 rating
Confidence interval: 1,017.90 – 1,039.84
3721 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- Llama 2 7B Chat
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
Llama-2-7b-chat
1,037.03 rating
Confidence interval: 1,025.56 – 1,048.49
3454 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- Llama 2 7B Chat
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
Llama-2-7b-chat
1,005.69 rating
Confidence interval: 995.92 – 1,015.46
4541 votes
- Category
- instruction_following
- Evaluated configuration
- Llama 2 7B Chat
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
Llama-2-7b-chat
998.76 rating
Confidence interval: 978.96 – 1,018.56
835 votes
- Category
- longer_query
- Evaluated configuration
- Llama 2 7B Chat
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
Llama-2-7b-chat
1,041.90 rating
Confidence interval: 1,028.02 – 1,055.79
1656 votes
- Category
- math
- Evaluated configuration
- Llama 2 7B Chat
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
Llama-2-7b-chat
1,029.07 rating
Confidence interval: 1,014.04 – 1,044.10
1851 votes
- Category
- multi_turn
- Evaluated configuration
- Llama 2 7B Chat
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
Llama-2-7b-chat
972.67 rating
Confidence interval: 962.14 – 983.21
3889 votes
- Category
- non_english
- Evaluated configuration
- Llama 2 7B Chat
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
Llama-2-7b-chat
1,053.37 rating
Confidence interval: 1,046.41 – 1,060.33
14148 votes
- Category
- overall
- Evaluated configuration
- Llama 2 7B Chat
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
Llama-2-7b-chat
994.84 rating
Confidence interval: 971.70 – 1,017.98
580 votes
- Category
- russian
- Evaluated configuration
- Llama 2 7B Chat
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating
Llama-2-7b-chat
1,007.31 rating
Confidence interval: 956.88 – 1,057.75
143 votes
- Category
- spanish
- Evaluated configuration
- Llama 2 7B Chat
- Evaluation type
- human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating
Llama-2-7b-chat
972.95 rating
Confidence interval: 953.22 – 992.68
956 votes
- Category
- chinese
- Evaluated configuration
- llama-2-7b-chat
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
Llama-2-7b-chat
1,001.74 rating
Confidence interval: 987.76 – 1,015.71
1956 votes
- Category
- coding
- Evaluated configuration
- llama-2-7b-chat
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
Llama-2-7b-chat
1,033.09 rating
Confidence interval: 1,019.53 – 1,046.66
2341 votes
- Category
- creative_writing
- Evaluated configuration
- llama-2-7b-chat
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
Llama-2-7b-chat
1,095.80 rating
Confidence interval: 1,087.89 – 1,103.71
10259 votes
- Category
- english
- Evaluated configuration
- llama-2-7b-chat
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
Llama-2-7b-chat
861.12 rating
Confidence interval: 850.79 – 871.45
9245 votes
- Category
- exclude_ties
- Evaluated configuration
- llama-2-7b-chat
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
Llama-2-7b-chat
1,035.93 rating
Confidence interval: 1,008.19 – 1,063.66
411 votes
- Category
- expert
- Evaluated configuration
- llama-2-7b-chat
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
Llama-2-7b-chat
969.74 rating
Confidence interval: 926.55 – 1,012.92
257 votes
- Category
- french
- Evaluated configuration
- llama-2-7b-chat
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
Llama-2-7b-chat
977.49 rating
Confidence interval: 942.63 – 1,012.35
327 votes
- Category
- german
- Evaluated configuration
- llama-2-7b-chat
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
Llama-2-7b-chat
1,009.06 rating
Confidence interval: 998.27 – 1,019.86
3289 votes
- Category
- hard_prompts
- Evaluated configuration
- llama-2-7b-chat
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
Llama-2-7b-chat
1,031.50 rating
Confidence interval: 1,019.15 – 1,043.86
2560 votes
- Category
- hard_prompts_english
- Evaluated configuration
- llama-2-7b-chat
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
Llama-2-7b-chat
1,027.86 rating
Confidence interval: 1,009.95 – 1,045.77
1255 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- llama-2-7b-chat
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
Llama-2-7b-chat
1,019.73 rating
Confidence interval: 1,006.23 – 1,033.23
2220 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- llama-2-7b-chat
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
Llama-2-7b-chat
1,064.65 rating
Confidence interval: 1,042.01 – 1,087.29
760 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- llama-2-7b-chat
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
Llama-2-7b-chat
1,046.87 rating
Confidence interval: 1,033.51 – 1,060.23
2474 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- llama-2-7b-chat
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
Llama-2-7b-chat
1,038.64 rating
Confidence interval: 1,023.30 – 1,053.99
1401 votes
- Category
- industry_mathematical
- Evaluated configuration
- llama-2-7b-chat
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
Llama-2-7b-chat
1,035.98 rating
Confidence interval: 1,013.07 – 1,058.90
764 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- llama-2-7b-chat
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
Llama-2-7b-chat
1,028.95 rating
Confidence interval: 1,017.98 – 1,039.92
3721 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- llama-2-7b-chat
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
Llama-2-7b-chat
1,037.09 rating
Confidence interval: 1,025.62 – 1,048.55
3454 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- llama-2-7b-chat
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
Llama-2-7b-chat
1,005.70 rating
Confidence interval: 995.93 – 1,015.48
4541 votes
- Category
- instruction_following
- Evaluated configuration
- llama-2-7b-chat
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
Llama-2-7b-chat
998.80 rating
Confidence interval: 978.99 – 1,018.61
835 votes
- Category
- longer_query
- Evaluated configuration
- llama-2-7b-chat
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
Llama-2-7b-chat
1,041.86 rating
Confidence interval: 1,027.98 – 1,055.75
1656 votes
- Category
- math
- Evaluated configuration
- llama-2-7b-chat
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
Llama-2-7b-chat
1,029.07 rating
Confidence interval: 1,014.04 – 1,044.11
1851 votes
- Category
- multi_turn
- Evaluated configuration
- llama-2-7b-chat
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
Llama-2-7b-chat
972.77 rating
Confidence interval: 962.23 – 983.30
3889 votes
- Category
- non_english
- Evaluated configuration
- llama-2-7b-chat
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
Llama-2-7b-chat
1,053.36 rating
Confidence interval: 1,046.39 – 1,060.32
14148 votes
- Category
- overall
- Evaluated configuration
- llama-2-7b-chat
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
Llama-2-7b-chat
995.00 rating
Confidence interval: 971.85 – 1,018.14
580 votes
- Category
- russian
- Evaluated configuration
- llama-2-7b-chat
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
Llama-2-7b-chat
1,007.24 rating
Confidence interval: 956.76 – 1,057.72
143 votes
- Category
- spanish
- Evaluated configuration
- llama-2-7b-chat
- Evaluation type
- human preference
Run it locally
Capabilities
- Open weights
- Yes
- Model license
- llama2
Input modalities
- text
Output modalities
- text
0 selected Compare 0