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
Olmo-3-32B-Think
1,299.33 rating
Confidence interval: 1,271.49 – 1,327.17
488 votes
Category
chinese
Evaluated configuration
Olmo 3 32B Think
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Olmo-3-32B-Think
1,318.24 rating
Confidence interval: 1,299.90 – 1,336.58
1045 votes
Category
coding
Evaluated configuration
Olmo 3 32B Think
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Olmo-3-32B-Think
1,255.39 rating
Confidence interval: 1,234.77 – 1,276.01
862 votes
Category
creative_writing
Evaluated configuration
Olmo 3 32B Think
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Olmo-3-32B-Think
1,347.73 rating
Confidence interval: 1,335.86 – 1,359.61
2464 votes
Category
english
Evaluated configuration
Olmo 3 32B Think
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Olmo-3-32B-Think
1,237.89 rating
Confidence interval: 1,225.83 – 1,249.95
4251 votes
Category
exclude_ties
Evaluated configuration
Olmo 3 32B Think
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Olmo-3-32B-Think
1,272.26 rating
Confidence interval: 1,236.77 – 1,307.76
314 votes
Category
expert
Evaluated configuration
Olmo 3 32B Think
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
Olmo-3-32B-Think
1,291.39 rating
Confidence interval: 1,234.82 – 1,347.95
124 votes
Category
french
Evaluated configuration
Olmo 3 32B Think
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Olmo-3-32B-Think
1,290.25 rating
Confidence interval: 1,236.74 – 1,343.77
136 votes
Category
german
Evaluated configuration
Olmo 3 32B Think
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Olmo-3-32B-Think
1,301.54 rating
Confidence interval: 1,290.47 – 1,312.60
3017 votes
Category
hard_prompts
Evaluated configuration
Olmo 3 32B Think
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Olmo-3-32B-Think
1,335.62 rating
Confidence interval: 1,319.19 – 1,352.06
1292 votes
Category
hard_prompts_english
Evaluated configuration
Olmo 3 32B Think
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
Olmo-3-32B-Think
1,263.34 rating
Confidence interval: 1,245.26 – 1,281.42
1054 votes
Category
industry_entertainment_and_sports_and_media
Evaluated configuration
olmo-3-32b-think
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
Olmo-3-32B-Think
1,289.14 rating
Confidence interval: 1,259.71 – 1,318.58
417 votes
Category
industry_legal_and_government
Evaluated configuration
olmo-3-32b-think
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
Olmo-3-32B-Think
1,310.69 rating
Confidence interval: 1,291.22 – 1,330.15
1010 votes
Category
industry_life_and_physical_and_social_science
Evaluated configuration
olmo-3-32b-think
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
Olmo-3-32B-Think
1,329.89 rating
Confidence interval: 1,291.53 – 1,368.24
212 votes
Category
industry_mathematical
Evaluated configuration
olmo-3-32b-think
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
Olmo-3-32B-Think
1,315.10 rating
Confidence interval: 1,280.18 – 1,350.02
323 votes
Category
industry_medicine_and_healthcare
Evaluated configuration
olmo-3-32b-think
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
Olmo-3-32B-Think
1,331.40 rating
Confidence interval: 1,317.66 – 1,345.14
1878 votes
Category
industry_software_and_it_services
Evaluated configuration
olmo-3-32b-think
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
Olmo-3-32B-Think
1,268.07 rating
Confidence interval: 1,251.54 – 1,284.59
1337 votes
Category
industry_writing_and_literature_and_language
Evaluated configuration
olmo-3-32b-think
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
Olmo-3-32B-Think
1,274.22 rating
Confidence interval: 1,258.55 – 1,289.89
1521 votes
Category
instruction_following
Evaluated configuration
olmo-3-32b-think
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
Olmo-3-32B-Think
1,295.20 rating
Confidence interval: 1,279.15 – 1,311.24
1384 votes
Category
longer_query
Evaluated configuration
olmo-3-32b-think
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
Olmo-3-32B-Think
1,316.54 rating
Confidence interval: 1,285.37 – 1,347.71
329 votes
Category
math
Evaluated configuration
olmo-3-32b-think
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
Olmo-3-32B-Think
1,289.51 rating
Confidence interval: 1,267.67 – 1,311.35
771 votes
Category
multi_turn
Evaluated configuration
olmo-3-32b-think
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
Olmo-3-32B-Think
1,254.17 rating
Confidence interval: 1,243.38 – 1,264.95
3362 votes
Category
non_english
Evaluated configuration
olmo-3-32b-think
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
Olmo-3-32B-Think
1,299.42 rating
Confidence interval: 1,291.18 – 1,307.66
5831 votes
Category
overall
Evaluated configuration
olmo-3-32b-think
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
Olmo-3-32B-Think
1,251.52 rating
Confidence interval: 1,205.84 – 1,297.20
195 votes
Category
polish
Evaluated configuration
olmo-3-32b-think
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
Olmo-3-32B-Think
1,253.50 rating
Confidence interval: 1,228.82 – 1,278.18
610 votes
Category
russian
Evaluated configuration
olmo-3-32b-think
Evaluation type
human preference
Run it locally
Inference · memory estimate
Olmo-3-32B-Think
60.0 GiB checkpoint tensor payload · 32.23 B stored tensor elements · BF16
Stored tensors can include buffers and repeated shared weights. A verified unique parameter count is unavailable. Checkpoint size is not the memory required to run the model.