Llama 2 70B SteerLM Chat
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsLlama 2 70B SteerLM Chat
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 / codinghuman preference · 2026-10-28 · rating
Llama 2 70B SteerLM Chat
1,024.48 rating
Confidence interval: 996.47 – 1,052.49
467 votes
- Category
- coding
- Evaluated configuration
- Llama 2 70B SteerLM Chat
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Llama 2 70B SteerLM Chat
1,090.21 rating
Confidence interval: 1,065.80 – 1,114.63
604 votes
- Category
- creative_writing
- Evaluated configuration
- Llama 2 70B SteerLM Chat
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Llama 2 70B SteerLM Chat
1,119.79 rating
Confidence interval: 1,106.08 – 1,133.49
2751 votes
- Category
- english
- Evaluated configuration
- Llama 2 70B SteerLM Chat
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Llama 2 70B SteerLM Chat
930.32 rating
Confidence interval: 913.08 – 947.56
2540 votes
- Category
- exclude_ties
- Evaluated configuration
- Llama 2 70B SteerLM Chat
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Llama 2 70B SteerLM Chat
1,046.56 rating
Confidence interval: 1,026.15 – 1,066.97
787 votes
- Category
- hard_prompts
- Evaluated configuration
- Llama 2 70B SteerLM Chat
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Llama 2 70B SteerLM Chat
1,056.72 rating
Confidence interval: 1,033.96 – 1,079.48
645 votes
- Category
- hard_prompts_english
- Evaluated configuration
- Llama 2 70B SteerLM Chat
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
Llama 2 70B SteerLM Chat
1,078.16 rating
Confidence interval: 1,043.02 – 1,113.29
282 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- Llama 2 70B SteerLM Chat
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
Llama 2 70B SteerLM Chat
1,069.08 rating
Confidence interval: 1,044.64 – 1,093.51
591 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- Llama 2 70B SteerLM Chat
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
Llama 2 70B SteerLM Chat
1,094.25 rating
Confidence interval: 1,070.59 – 1,117.92
642 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- Llama 2 70B SteerLM Chat
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
Llama 2 70B SteerLM Chat
1,065.00 rating
Confidence interval: 1,035.26 – 1,094.74
353 votes
- Category
- industry_mathematical
- Evaluated configuration
- Llama 2 70B SteerLM Chat
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
Llama 2 70B SteerLM Chat
1,055.64 rating
Confidence interval: 1,035.08 – 1,076.19
877 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- Llama 2 70B SteerLM Chat
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
Llama 2 70B SteerLM Chat
1,094.32 rating
Confidence interval: 1,073.00 – 1,115.63
836 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- Llama 2 70B SteerLM Chat
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
Llama 2 70B SteerLM Chat
1,060.29 rating
Confidence interval: 1,042.36 – 1,078.21
1076 votes
- Category
- instruction_following
- Evaluated configuration
- Llama 2 70B SteerLM Chat
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
Llama 2 70B SteerLM Chat
997.48 rating
Confidence interval: 956.92 – 1,038.05
208 votes
- Category
- longer_query
- Evaluated configuration
- Llama 2 70B SteerLM Chat
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
Llama 2 70B SteerLM Chat
1,071.81 rating
Confidence interval: 1,045.29 – 1,098.34
440 votes
- Category
- math
- Evaluated configuration
- Llama 2 70B SteerLM Chat
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
Llama 2 70B SteerLM Chat
1,057.92 rating
Confidence interval: 1,029.82 – 1,086.03
451 votes
- Category
- multi_turn
- Evaluated configuration
- Llama 2 70B SteerLM Chat
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
Llama 2 70B SteerLM Chat
1,063.36 rating
Confidence interval: 1,043.23 – 1,083.49
834 votes
- Category
- non_english
- Evaluated configuration
- Llama 2 70B SteerLM Chat
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
Llama 2 70B SteerLM Chat
1,098.07 rating
Confidence interval: 1,085.62 – 1,110.51
3585 votes
- Category
- overall
- Evaluated configuration
- Llama 2 70B SteerLM Chat
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- Llama 2 Community
0 selected Compare 0