GeekRadar / The comparison desk
COMPARE.
AI models
Not reported

OpenHermes 2.5 Mistral 7B

Model evaluation

Capability & preference

Human preference · Arena

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

OpenHermes 2.5 Mistral 7B 1092.5 OpenHermes 2.5 Mistral 7B · 95% interval 1082.2–1102.8 · 5,006 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

OpenHermes 2.5 Mistral 7B

1,014.26 rating

Confidence interval: 972.47 – 1,056.05

205 votes

Category
chinese
Evaluated configuration
OpenHermes 2.5 Mistral 7B
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

OpenHermes 2.5 Mistral 7B

1,064.07 rating

Confidence interval: 1,040.93 – 1,087.21

589 votes

Category
coding
Evaluated configuration
OpenHermes 2.5 Mistral 7B
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

OpenHermes 2.5 Mistral 7B

1,096.88 rating

Confidence interval: 1,075.30 – 1,118.46

811 votes

Category
creative_writing
Evaluated configuration
OpenHermes 2.5 Mistral 7B
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

OpenHermes 2.5 Mistral 7B

1,125.58 rating

Confidence interval: 1,114.13 – 1,137.02

3857 votes

Category
english
Evaluated configuration
OpenHermes 2.5 Mistral 7B
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

OpenHermes 2.5 Mistral 7B

923.29 rating

Confidence interval: 908.28 – 938.31

3283 votes

Category
exclude_ties
Evaluated configuration
OpenHermes 2.5 Mistral 7B
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

OpenHermes 2.5 Mistral 7B

1,071.45 rating

Confidence interval: 1,054.72 – 1,088.19

1139 votes

Category
hard_prompts
Evaluated configuration
OpenHermes 2.5 Mistral 7B
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

OpenHermes 2.5 Mistral 7B

1,086.60 rating

Confidence interval: 1,068.13 – 1,105.08

917 votes

Category
hard_prompts_english
Evaluated configuration
OpenHermes 2.5 Mistral 7B
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

OpenHermes 2.5 Mistral 7B

1,024.31 rating

Confidence interval: 994.98 – 1,053.63

381 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
OpenHermes 2.5 Mistral 7B
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

OpenHermes 2.5 Mistral 7B

1,073.90 rating

Confidence interval: 1,052.99 – 1,094.81

799 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
OpenHermes 2.5 Mistral 7B
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

OpenHermes 2.5 Mistral 7B

1,099.66 rating

Confidence interval: 1,064.16 – 1,135.17

275 votes

Category
industry_legal_and_government
Evaluated configuration
OpenHermes 2.5 Mistral 7B
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

OpenHermes 2.5 Mistral 7B

1,065.24 rating

Confidence interval: 1,044.94 – 1,085.54

884 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
OpenHermes 2.5 Mistral 7B
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

OpenHermes 2.5 Mistral 7B

1,096.96 rating

Confidence interval: 1,074.89 – 1,119.03

568 votes

Category
industry_mathematical
Evaluated configuration
OpenHermes 2.5 Mistral 7B
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

OpenHermes 2.5 Mistral 7B

1,051.77 rating

Confidence interval: 1,016.41 – 1,087.14

285 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
OpenHermes 2.5 Mistral 7B
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

OpenHermes 2.5 Mistral 7B

1,076.69 rating

Confidence interval: 1,059.30 – 1,094.07

1192 votes

Category
industry_software_and_it_services
Evaluated configuration
OpenHermes 2.5 Mistral 7B
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

OpenHermes 2.5 Mistral 7B

1,095.90 rating

Confidence interval: 1,077.58 – 1,114.22

1136 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
OpenHermes 2.5 Mistral 7B
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

OpenHermes 2.5 Mistral 7B

1,070.09 rating

Confidence interval: 1,054.89 – 1,085.29

1577 votes

Category
instruction_following
Evaluated configuration
OpenHermes 2.5 Mistral 7B
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

OpenHermes 2.5 Mistral 7B

1,053.92 rating

Confidence interval: 1,021.02 – 1,086.82

270 votes

Category
longer_query
Evaluated configuration
OpenHermes 2.5 Mistral 7B
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

OpenHermes 2.5 Mistral 7B

1,097.59 rating

Confidence interval: 1,077.65 – 1,117.53

697 votes

Category
math
Evaluated configuration
OpenHermes 2.5 Mistral 7B
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

OpenHermes 2.5 Mistral 7B

1,064.42 rating

Confidence interval: 1,041.94 – 1,086.90

722 votes

Category
multi_turn
Evaluated configuration
OpenHermes 2.5 Mistral 7B
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

OpenHermes 2.5 Mistral 7B

1,024.22 rating

Confidence interval: 1,006.38 – 1,042.05

1149 votes

Category
non_english
Evaluated configuration
OpenHermes 2.5 Mistral 7B
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

OpenHermes 2.5 Mistral 7B

1,092.47 rating

Confidence interval: 1,082.16 – 1,102.78

5006 votes

Category
overall
Evaluated configuration
OpenHermes 2.5 Mistral 7B
Evaluation type
human preference

Run it locally

Inference · memory estimate

OpenHermes 2.5 Mistral 7B

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Apache-2.0