GeekRadar / The comparison desk
COMPARE.
AI models
allenai

OLMo 2 32B Instruct (0325)

Model evaluation

Capability & preference

Human preference · Arena

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

OLMo 2 32B Instruct (0325) 1217.9 OLMo 2 32B Instruct (0325) · 95% interval 1207.1–1228.7 · 3,334 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 2 32B Instruct (0325)

1,191.41 rating

Confidence interval: 1,155.59 – 1,227.23

229 votes

Category
chinese
Evaluated configuration
OLMo 2 32B Instruct (0325)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

OLMo 2 32B Instruct (0325)

1,209.81 rating

Confidence interval: 1,182.58 – 1,237.04

427 votes

Category
coding
Evaluated configuration
OLMo 2 32B Instruct (0325)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

OLMo 2 32B Instruct (0325)

1,198.22 rating

Confidence interval: 1,173.55 – 1,222.88

567 votes

Category
creative_writing
Evaluated configuration
OLMo 2 32B Instruct (0325)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

OLMo 2 32B Instruct (0325)

1,255.41 rating

Confidence interval: 1,242.43 – 1,268.39

2025 votes

Category
english
Evaluated configuration
OLMo 2 32B Instruct (0325)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

OLMo 2 32B Instruct (0325)

1,106.73 rating

Confidence interval: 1,089.61 – 1,123.84

2276 votes

Category
exclude_ties
Evaluated configuration
OLMo 2 32B Instruct (0325)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

OLMo 2 32B Instruct (0325)

1,207.59 rating

Confidence interval: 1,187.91 – 1,227.26

789 votes

Category
hard_prompts
Evaluated configuration
OLMo 2 32B Instruct (0325)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

OLMo 2 32B Instruct (0325)

1,243.63 rating

Confidence interval: 1,220.03 – 1,267.22

538 votes

Category
hard_prompts_english
Evaluated configuration
OLMo 2 32B Instruct (0325)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

OLMo 2 32B Instruct (0325)

1,180.97 rating

Confidence interval: 1,148.93 – 1,213.00

336 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
OLMo 2 32B Instruct (0325)
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

OLMo 2 32B Instruct (0325)

1,224.40 rating

Confidence interval: 1,201.31 – 1,247.49

606 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
OLMo 2 32B Instruct (0325)
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

OLMo 2 32B Instruct (0325)

1,228.34 rating

Confidence interval: 1,188.08 – 1,268.61

202 votes

Category
industry_legal_and_government
Evaluated configuration
OLMo 2 32B Instruct (0325)
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

OLMo 2 32B Instruct (0325)

1,239.47 rating

Confidence interval: 1,215.85 – 1,263.08

580 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
OLMo 2 32B Instruct (0325)
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

OLMo 2 32B Instruct (0325)

1,195.36 rating

Confidence interval: 1,165.53 – 1,225.18

336 votes

Category
industry_mathematical
Evaluated configuration
OLMo 2 32B Instruct (0325)
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

OLMo 2 32B Instruct (0325)

1,181.60 rating

Confidence interval: 1,137.47 – 1,225.73

204 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
OLMo 2 32B Instruct (0325)
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

OLMo 2 32B Instruct (0325)

1,213.77 rating

Confidence interval: 1,192.35 – 1,235.18

740 votes

Category
industry_software_and_it_services
Evaluated configuration
OLMo 2 32B Instruct (0325)
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

OLMo 2 32B Instruct (0325)

1,203.60 rating

Confidence interval: 1,184.24 – 1,222.95

872 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
OLMo 2 32B Instruct (0325)
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

OLMo 2 32B Instruct (0325)

1,185.82 rating

Confidence interval: 1,168.60 – 1,203.04

1063 votes

Category
instruction_following
Evaluated configuration
OLMo 2 32B Instruct (0325)
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

OLMo 2 32B Instruct (0325)

1,193.83 rating

Confidence interval: 1,160.00 – 1,227.66

261 votes

Category
longer_query
Evaluated configuration
OLMo 2 32B Instruct (0325)
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

OLMo 2 32B Instruct (0325)

1,207.56 rating

Confidence interval: 1,179.37 – 1,235.74

375 votes

Category
math
Evaluated configuration
OLMo 2 32B Instruct (0325)
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

OLMo 2 32B Instruct (0325)

1,221.20 rating

Confidence interval: 1,192.09 – 1,250.31

363 votes

Category
multi_turn
Evaluated configuration
OLMo 2 32B Instruct (0325)
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

OLMo 2 32B Instruct (0325)

1,160.14 rating

Confidence interval: 1,144.05 – 1,176.22

1309 votes

Category
non_english
Evaluated configuration
OLMo 2 32B Instruct (0325)
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

OLMo 2 32B Instruct (0325)

1,217.91 rating

Confidence interval: 1,207.14 – 1,228.69

3334 votes

Category
overall
Evaluated configuration
OLMo 2 32B Instruct (0325)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

OLMo 2 32B Instruct (0325)

1,186.71 rating

Confidence interval: 1,154.04 – 1,219.39

304 votes

Category
russian
Evaluated configuration
OLMo 2 32B Instruct (0325)
Evaluation type
human preference

Run it locally

Inference · memory estimate

OLMo 2 32B Instruct (0325)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Apache-2.0