GeekRadar / The comparison desk
COMPARE.
AI models
allenai

Olmo-3.1-32B-Instruct

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-Instruct 1311.2 Olmo 3.1 32B Instruct · 95% interval 1305.1–1317.3 · 11,805 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-Instruct

1,303.99 rating

Confidence interval: 1,283.34 – 1,324.63

875 votes

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

Olmo-3.1-32B-Instruct

1,346.92 rating

Confidence interval: 1,335.09 – 1,358.75

2459 votes

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

Olmo-3.1-32B-Instruct

1,264.64 rating

Confidence interval: 1,249.94 – 1,279.34

1725 votes

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

Olmo-3.1-32B-Instruct

1,353.48 rating

Confidence interval: 1,344.63 – 1,362.32

4596 votes

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

Olmo-3.1-32B-Instruct

1,250.22 rating

Confidence interval: 1,241.20 – 1,259.24

8455 votes

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

Olmo-3.1-32B-Instruct

1,308.37 rating

Confidence interval: 1,286.63 – 1,330.12

760 votes

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

Olmo-3.1-32B-Instruct

1,329.22 rating

Confidence interval: 1,294.05 – 1,364.38

324 votes

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

Olmo-3.1-32B-Instruct

1,281.81 rating

Confidence interval: 1,244.20 – 1,319.41

245 votes

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

Olmo-3.1-32B-Instruct

1,322.02 rating

Confidence interval: 1,314.20 – 1,329.84

6341 votes

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

Olmo-3.1-32B-Instruct

1,352.51 rating

Confidence interval: 1,340.56 – 1,364.45

2426 votes

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

Olmo-3.1-32B-Instruct

1,317.39 rating

Confidence interval: 1,304.76 – 1,330.02

2135 votes

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

Olmo-3.1-32B-Instruct

1,270.32 rating

Confidence interval: 1,257.25 – 1,283.39

2080 votes

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

Olmo-3.1-32B-Instruct

1,331.23 rating

Confidence interval: 1,311.48 – 1,350.97

885 votes

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

Olmo-3.1-32B-Instruct

1,316.48 rating

Confidence interval: 1,302.39 – 1,330.57

1867 votes

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

Olmo-3.1-32B-Instruct

1,346.37 rating

Confidence interval: 1,318.91 – 1,373.84

439 votes

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

Olmo-3.1-32B-Instruct

1,286.32 rating

Confidence interval: 1,263.83 – 1,308.81

784 votes

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

Olmo-3.1-32B-Instruct

1,349.27 rating

Confidence interval: 1,339.85 – 1,358.70

3959 votes

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

Olmo-3.1-32B-Instruct

1,275.48 rating

Confidence interval: 1,263.76 – 1,287.20

2662 votes

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

Olmo-3.1-32B-Instruct

1,298.95 rating

Confidence interval: 1,288.36 – 1,309.55

3211 votes

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

Olmo-3.1-32B-Instruct

1,205.66 rating

Confidence interval: 1,159.13 – 1,252.19

183 votes

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

Olmo-3.1-32B-Instruct

1,312.66 rating

Confidence interval: 1,301.86 – 1,323.45

2954 votes

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

Olmo-3.1-32B-Instruct

1,304.46 rating

Confidence interval: 1,281.75 – 1,327.17

693 votes

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

Olmo-3.1-32B-Instruct

1,309.76 rating

Confidence interval: 1,296.53 – 1,322.99

2138 votes

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

Olmo-3.1-32B-Instruct

1,275.13 rating

Confidence interval: 1,267.59 – 1,282.68

7209 votes

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

Olmo-3.1-32B-Instruct

1,311.24 rating

Confidence interval: 1,305.15 – 1,317.33

11805 votes

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

Olmo-3.1-32B-Instruct

1,220.18 rating

Confidence interval: 1,186.92 – 1,253.43

384 votes

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

Olmo-3.1-32B-Instruct

1,267.57 rating

Confidence interval: 1,252.91 – 1,282.22

1689 votes

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

Olmo-3.1-32B-Instruct

1,336.21 rating

Confidence interval: 1,305.58 – 1,366.84

375 votes

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

Olmo-3.1-32B-Instruct

1,304.15 rating

Confidence interval: 1,283.50 – 1,324.80

875 votes

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

Olmo-3.1-32B-Instruct

1,346.68 rating

Confidence interval: 1,334.87 – 1,358.50

2469 votes

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

Olmo-3.1-32B-Instruct

1,264.54 rating

Confidence interval: 1,249.83 – 1,279.25

1724 votes

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

Olmo-3.1-32B-Instruct

1,353.36 rating

Confidence interval: 1,344.52 – 1,362.21

4596 votes

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

Olmo-3.1-32B-Instruct

1,250.22 rating

Confidence interval: 1,241.20 – 1,259.24

8465 votes

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

Olmo-3.1-32B-Instruct

1,307.62 rating

Confidence interval: 1,285.88 – 1,329.37

762 votes

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

Olmo-3.1-32B-Instruct

1,328.83 rating

Confidence interval: 1,293.65 – 1,364.02

324 votes

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

Olmo-3.1-32B-Instruct

1,281.60 rating

Confidence interval: 1,243.98 – 1,319.23

245 votes

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

Olmo-3.1-32B-Instruct

1,321.88 rating

Confidence interval: 1,314.06 – 1,329.70

6354 votes

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

Olmo-3.1-32B-Instruct

1,352.17 rating

Confidence interval: 1,340.22 – 1,364.11

2426 votes

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

Olmo-3.1-32B-Instruct

1,317.43 rating

Confidence interval: 1,304.79 – 1,330.07

2134 votes

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

Olmo-3.1-32B-Instruct

1,269.46 rating

Confidence interval: 1,256.39 – 1,282.53

2084 votes

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

Olmo-3.1-32B-Instruct

1,331.17 rating

Confidence interval: 1,311.42 – 1,350.92

885 votes

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

Olmo-3.1-32B-Instruct

1,316.70 rating

Confidence interval: 1,302.60 – 1,330.79

1866 votes

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

Olmo-3.1-32B-Instruct

1,346.47 rating

Confidence interval: 1,319.00 – 1,373.95

439 votes

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

Olmo-3.1-32B-Instruct

1,286.39 rating

Confidence interval: 1,263.89 – 1,308.88

784 votes

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

Olmo-3.1-32B-Instruct

1,349.42 rating

Confidence interval: 1,340.01 – 1,358.83

3972 votes

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

Olmo-3.1-32B-Instruct

1,275.69 rating

Confidence interval: 1,263.97 – 1,287.42

2661 votes

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

Olmo-3.1-32B-Instruct

1,299.03 rating

Confidence interval: 1,288.46 – 1,309.61

3220 votes

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

Olmo-3.1-32B-Instruct

1,205.71 rating

Confidence interval: 1,159.15 – 1,252.26

183 votes

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

Olmo-3.1-32B-Instruct

1,312.48 rating

Confidence interval: 1,301.68 – 1,323.27

2963 votes

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

Olmo-3.1-32B-Instruct

1,304.44 rating

Confidence interval: 1,281.72 – 1,327.16

693 votes

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

Olmo-3.1-32B-Instruct

1,309.61 rating

Confidence interval: 1,296.39 – 1,322.82

2142 votes

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

Olmo-3.1-32B-Instruct

1,275.24 rating

Confidence interval: 1,267.69 – 1,282.78

7221 votes

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

Olmo-3.1-32B-Instruct

1,311.14 rating

Confidence interval: 1,305.05 – 1,317.23

11817 votes

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

Olmo-3.1-32B-Instruct

1,220.14 rating

Confidence interval: 1,186.88 – 1,253.41

384 votes

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

Olmo-3.1-32B-Instruct

1,268.35 rating

Confidence interval: 1,253.72 – 1,282.98

1693 votes

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

Olmo-3.1-32B-Instruct

1,335.60 rating

Confidence interval: 1,305.06 – 1,366.14

377 votes

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

Run it locally

Inference · memory estimate

Olmo-3.1-32B-Instruct

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