GeekRadar / The comparison desk
COMPARE.
AI models
allenai

Olmo-3.1-32B-Think

AI model

Context window
65,536 tokens
Open weights
Yes

Capability & preference

Human preference · Arena

Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.

Olmo-3.1-32B-Think 1271.4 Olmo 3.1 32B Think · 95% interval 1264.1–1278.6 · 8,299 votes · 2026-10-28

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

Olmo-3.1-32B-Think

1,240.64 rating

Confidence interval: 1,217.01 – 1,264.27

729 votes

Category
chinese
Evaluated configuration
Olmo 3.1 32B Think
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

Olmo-3.1-32B-Think

1,290.86 rating

Confidence interval: 1,275.52 – 1,306.19

1553 votes

Category
coding
Evaluated configuration
Olmo 3.1 32B Think
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

Olmo-3.1-32B-Think

1,226.67 rating

Confidence interval: 1,209.70 – 1,243.64

1367 votes

Category
creative_writing
Evaluated configuration
Olmo 3.1 32B Think
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

Olmo-3.1-32B-Think

1,344.59 rating

Confidence interval: 1,334.37 – 1,354.82

3313 votes

Category
english
Evaluated configuration
Olmo 3.1 32B Think
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

Olmo-3.1-32B-Think

1,190.45 rating

Confidence interval: 1,179.28 – 1,201.63

5987 votes

Category
exclude_ties
Evaluated configuration
Olmo 3.1 32B Think
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

Olmo-3.1-32B-Think

1,294.57 rating

Confidence interval: 1,269.31 – 1,319.82

554 votes

Category
expert
Evaluated configuration
Olmo 3.1 32B Think
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating

Olmo-3.1-32B-Think

1,260.84 rating

Confidence interval: 1,216.88 – 1,304.79

211 votes

Category
french
Evaluated configuration
Olmo 3.1 32B Think
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating

Olmo-3.1-32B-Think

1,261.81 rating

Confidence interval: 1,213.42 – 1,310.20

165 votes

Category
german
Evaluated configuration
Olmo 3.1 32B Think
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

Olmo-3.1-32B-Think

1,272.18 rating

Confidence interval: 1,262.70 – 1,281.66

4365 votes

Category
hard_prompts
Evaluated configuration
Olmo 3.1 32B Think
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

Olmo-3.1-32B-Think

1,328.81 rating

Confidence interval: 1,314.59 – 1,343.03

1725 votes

Category
hard_prompts_english
Evaluated configuration
Olmo 3.1 32B Think
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

Olmo-3.1-32B-Think

1,253.00 rating

Confidence interval: 1,236.83 – 1,269.17

1477 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Olmo 3.1 32B Think
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

Olmo-3.1-32B-Think

1,236.76 rating

Confidence interval: 1,222.00 – 1,251.51

1656 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Olmo 3.1 32B Think
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

Olmo-3.1-32B-Think

1,286.82 rating

Confidence interval: 1,262.76 – 1,310.88

620 votes

Category
industry_legal_and_government
Evaluated configuration
Olmo 3.1 32B Think
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

Olmo-3.1-32B-Think

1,289.81 rating

Confidence interval: 1,273.55 – 1,306.07

1404 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Olmo 3.1 32B Think
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

Olmo-3.1-32B-Think

1,311.08 rating

Confidence interval: 1,281.99 – 1,340.18

379 votes

Category
industry_mathematical
Evaluated configuration
Olmo 3.1 32B Think
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

Olmo-3.1-32B-Think

1,260.28 rating

Confidence interval: 1,233.85 – 1,286.72

589 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Olmo 3.1 32B Think
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

Olmo-3.1-32B-Think

1,300.82 rating

Confidence interval: 1,289.09 – 1,312.55

2671 votes

Category
industry_software_and_it_services
Evaluated configuration
Olmo 3.1 32B Think
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

Olmo-3.1-32B-Think

1,250.22 rating

Confidence interval: 1,236.42 – 1,264.03

1944 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Olmo 3.1 32B Think
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

Olmo-3.1-32B-Think

1,246.20 rating

Confidence interval: 1,233.10 – 1,259.29

2184 votes

Category
instruction_following
Evaluated configuration
Olmo 3.1 32B Think
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

Olmo-3.1-32B-Think

1,271.02 rating

Confidence interval: 1,257.62 – 1,284.42

2041 votes

Category
longer_query
Evaluated configuration
Olmo 3.1 32B Think
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

Olmo-3.1-32B-Think

1,304.66 rating

Confidence interval: 1,278.85 – 1,330.48

477 votes

Category
math
Evaluated configuration
Olmo 3.1 32B Think
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

Olmo-3.1-32B-Think

1,251.01 rating

Confidence interval: 1,233.09 – 1,268.94

1183 votes

Category
multi_turn
Evaluated configuration
Olmo 3.1 32B Think
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

Olmo-3.1-32B-Think

1,209.14 rating

Confidence interval: 1,199.91 – 1,218.37

4986 votes

Category
non_english
Evaluated configuration
Olmo 3.1 32B Think
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

Olmo-3.1-32B-Think

1,271.38 rating

Confidence interval: 1,264.14 – 1,278.63

8299 votes

Category
overall
Evaluated configuration
Olmo 3.1 32B Think
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating

Olmo-3.1-32B-Think

1,190.73 rating

Confidence interval: 1,155.49 – 1,225.97

336 votes

Category
polish
Evaluated configuration
Olmo 3.1 32B Think
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

Olmo-3.1-32B-Think

1,192.02 rating

Confidence interval: 1,172.95 – 1,211.08

1064 votes

Category
russian
Evaluated configuration
Olmo 3.1 32B Think
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating

Olmo-3.1-32B-Think

1,288.78 rating

Confidence interval: 1,245.72 – 1,331.85

199 votes

Category
spanish
Evaluated configuration
Olmo 3.1 32B Think
Evaluation type
human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating

Olmo-3.1-32B-Think

1,241.86 rating

Confidence interval: 1,218.26 – 1,265.45

728 votes

Category
chinese
Evaluated configuration
olmo-3.1-32b-think
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

Olmo-3.1-32B-Think

1,291.71 rating

Confidence interval: 1,276.40 – 1,307.03

1556 votes

Category
coding
Evaluated configuration
olmo-3.1-32b-think
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

Olmo-3.1-32B-Think

1,226.77 rating

Confidence interval: 1,209.78 – 1,243.77

1365 votes

Category
creative_writing
Evaluated configuration
olmo-3.1-32b-think
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

Olmo-3.1-32B-Think

1,344.56 rating

Confidence interval: 1,334.34 – 1,354.78

3315 votes

Category
english
Evaluated configuration
olmo-3.1-32b-think
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

Olmo-3.1-32B-Think

1,190.80 rating

Confidence interval: 1,179.63 – 1,201.98

5986 votes

Category
exclude_ties
Evaluated configuration
olmo-3.1-32b-think
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

Olmo-3.1-32B-Think

1,295.26 rating

Confidence interval: 1,270.04 – 1,320.48

554 votes

Category
expert
Evaluated configuration
olmo-3.1-32b-think
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating

Olmo-3.1-32B-Think

1,260.47 rating

Confidence interval: 1,216.48 – 1,304.45

211 votes

Category
french
Evaluated configuration
olmo-3.1-32b-think
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating

Olmo-3.1-32B-Think

1,261.59 rating

Confidence interval: 1,213.19 – 1,310.00

165 votes

Category
german
Evaluated configuration
olmo-3.1-32b-think
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

Olmo-3.1-32B-Think

1,272.59 rating

Confidence interval: 1,263.11 – 1,282.06

4365 votes

Category
hard_prompts
Evaluated configuration
olmo-3.1-32b-think
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

Olmo-3.1-32B-Think

1,328.56 rating

Confidence interval: 1,314.33 – 1,342.78

1726 votes

Category
hard_prompts_english
Evaluated configuration
olmo-3.1-32b-think
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

Olmo-3.1-32B-Think

1,253.41 rating

Confidence interval: 1,237.24 – 1,269.59

1475 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
olmo-3.1-32b-think
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

Olmo-3.1-32B-Think

1,236.94 rating

Confidence interval: 1,222.19 – 1,251.69

1656 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
olmo-3.1-32b-think
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

Olmo-3.1-32B-Think

1,287.11 rating

Confidence interval: 1,263.03 – 1,311.18

619 votes

Category
industry_legal_and_government
Evaluated configuration
olmo-3.1-32b-think
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

Olmo-3.1-32B-Think

1,289.77 rating

Confidence interval: 1,273.49 – 1,306.04

1403 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
olmo-3.1-32b-think
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

Olmo-3.1-32B-Think

1,311.50 rating

Confidence interval: 1,282.48 – 1,340.52

380 votes

Category
industry_mathematical
Evaluated configuration
olmo-3.1-32b-think
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

Olmo-3.1-32B-Think

1,260.69 rating

Confidence interval: 1,234.30 – 1,287.07

590 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
olmo-3.1-32b-think
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

Olmo-3.1-32B-Think

1,301.26 rating

Confidence interval: 1,289.54 – 1,312.98

2674 votes

Category
industry_software_and_it_services
Evaluated configuration
olmo-3.1-32b-think
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

Olmo-3.1-32B-Think

1,250.32 rating

Confidence interval: 1,236.51 – 1,264.13

1943 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
olmo-3.1-32b-think
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

Olmo-3.1-32B-Think

1,246.73 rating

Confidence interval: 1,233.62 – 1,259.83

2182 votes

Category
instruction_following
Evaluated configuration
olmo-3.1-32b-think
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

Olmo-3.1-32B-Think

1,272.10 rating

Confidence interval: 1,258.69 – 1,285.50

2039 votes

Category
longer_query
Evaluated configuration
olmo-3.1-32b-think
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

Olmo-3.1-32B-Think

1,304.89 rating

Confidence interval: 1,279.12 – 1,330.65

478 votes

Category
math
Evaluated configuration
olmo-3.1-32b-think
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

Olmo-3.1-32B-Think

1,252.13 rating

Confidence interval: 1,234.24 – 1,270.03

1186 votes

Category
multi_turn
Evaluated configuration
olmo-3.1-32b-think
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

Olmo-3.1-32B-Think

1,209.68 rating

Confidence interval: 1,200.46 – 1,218.90

4986 votes

Category
non_english
Evaluated configuration
olmo-3.1-32b-think
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

Olmo-3.1-32B-Think

1,271.62 rating

Confidence interval: 1,264.38 – 1,278.87

8301 votes

Category
overall
Evaluated configuration
olmo-3.1-32b-think
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating

Olmo-3.1-32B-Think

1,190.69 rating

Confidence interval: 1,155.45 – 1,225.93

336 votes

Category
polish
Evaluated configuration
olmo-3.1-32b-think
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

Olmo-3.1-32B-Think

1,193.24 rating

Confidence interval: 1,174.22 – 1,212.27

1066 votes

Category
russian
Evaluated configuration
olmo-3.1-32b-think
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating

Olmo-3.1-32B-Think

1,288.69 rating

Confidence interval: 1,245.60 – 1,331.77

199 votes

Category
spanish
Evaluated configuration
olmo-3.1-32b-think
Evaluation type
human preference

Run it locally

Inference · memory estimate

Olmo-3.1-32B-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.

Capabilities

Context window
65,536 tokens
Open weights
Yes
Model license
apache-2.0
Checkpoint tensor payload
60.04 GiB

Input modalities

  • text

Output modalities

  • text

Processing & platform

Architecture
olmo3