PaLM 2
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsPaLM 2
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 · 2026-10-28 · rating
PaLM 2
887.20 rating
Confidence interval: 850.29 – 924.11
355 votes
- Category
- chinese
- Evaluated configuration
- PaLM 2
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
PaLM 2
994.16 rating
Confidence interval: 973.51 – 1,014.82
917 votes
- Category
- coding
- Evaluated configuration
- PaLM 2
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
PaLM 2
991.11 rating
Confidence interval: 973.83 – 1,008.40
1576 votes
- Category
- creative_writing
- Evaluated configuration
- PaLM 2
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
PaLM 2
1,063.43 rating
Confidence interval: 1,053.48 – 1,073.37
6912 votes
- Category
- english
- Evaluated configuration
- PaLM 2
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
PaLM 2
830.04 rating
Confidence interval: 817.36 – 842.72
6230 votes
- Category
- exclude_ties
- Evaluated configuration
- PaLM 2
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
PaLM 2
1,004.83 rating
Confidence interval: 989.45 – 1,020.20
1605 votes
- Category
- hard_prompts
- Evaluated configuration
- PaLM 2
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
PaLM 2
1,035.23 rating
Confidence interval: 1,018.81 – 1,051.64
1366 votes
- Category
- hard_prompts_english
- Evaluated configuration
- PaLM 2
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
PaLM 2
958.63 rating
Confidence interval: 934.57 – 982.68
755 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- PaLM 2
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
PaLM 2
992.15 rating
Confidence interval: 974.91 – 1,009.40
1480 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- PaLM 2
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
PaLM 2
1,005.61 rating
Confidence interval: 973.89 – 1,037.34
428 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- PaLM 2
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
PaLM 2
1,011.08 rating
Confidence interval: 992.98 – 1,029.17
1368 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- PaLM 2
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
PaLM 2
1,043.06 rating
Confidence interval: 1,022.12 – 1,064.01
801 votes
- Category
- industry_mathematical
- Evaluated configuration
- PaLM 2
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
PaLM 2
961.60 rating
Confidence interval: 924.62 – 998.59
303 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- PaLM 2
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
PaLM 2
999.58 rating
Confidence interval: 984.55 – 1,014.61
2077 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- PaLM 2
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
PaLM 2
1,006.75 rating
Confidence interval: 991.74 – 1,021.76
2155 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- PaLM 2
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
PaLM 2
1,009.91 rating
Confidence interval: 996.59 – 1,023.24
2536 votes
- Category
- instruction_following
- Evaluated configuration
- PaLM 2
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
PaLM 2
1,009.45 rating
Confidence interval: 973.03 – 1,045.87
251 votes
- Category
- longer_query
- Evaluated configuration
- PaLM 2
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
PaLM 2
1,048.85 rating
Confidence interval: 1,029.49 – 1,068.21
901 votes
- Category
- math
- Evaluated configuration
- PaLM 2
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
PaLM 2
994.33 rating
Confidence interval: 974.81 – 1,013.85
1163 votes
- Category
- multi_turn
- Evaluated configuration
- PaLM 2
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
PaLM 2
915.94 rating
Confidence interval: 898.71 – 933.17
1642 votes
- Category
- non_english
- Evaluated configuration
- PaLM 2
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
PaLM 2
1,027.21 rating
Confidence interval: 1,018.01 – 1,036.41
8554 votes
- Category
- overall
- Evaluated configuration
- PaLM 2
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- Proprietary
0 selected Compare 0