GeekRadar / The comparison desk
COMPARE.
AI models
Not reported

nous-hermes-2-mixtral-8x7b-dpo

Model evaluation

Capability & preference

Human preference · Arena

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

nous-hermes-2-mixtral-8x7b-dpo 1112.0 nous-hermes-2-mixtral-8x7b-dpo · 95% interval 1100.2–1123.8 · 3,777 votes · 2026-10-15

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 / codinghuman preference · 2026-10-15 · rating

nous-hermes-2-mixtral-8x7b-dpo

1,079.52 rating

Confidence interval: 1,056.43 – 1,102.60

575 votes

Category
coding
Evaluated configuration
nous-hermes-2-mixtral-8x7b-dpo
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

nous-hermes-2-mixtral-8x7b-dpo

1,101.52 rating

Confidence interval: 1,078.30 – 1,124.74

616 votes

Category
creative_writing
Evaluated configuration
nous-hermes-2-mixtral-8x7b-dpo
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

nous-hermes-2-mixtral-8x7b-dpo

1,139.49 rating

Confidence interval: 1,126.71 – 1,152.28

3033 votes

Category
english
Evaluated configuration
nous-hermes-2-mixtral-8x7b-dpo
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

nous-hermes-2-mixtral-8x7b-dpo

950.98 rating

Confidence interval: 934.13 – 967.84

2559 votes

Category
exclude_ties
Evaluated configuration
nous-hermes-2-mixtral-8x7b-dpo
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

nous-hermes-2-mixtral-8x7b-dpo

1,053.29 rating

Confidence interval: 1,036.03 – 1,070.54

1066 votes

Category
hard_prompts
Evaluated configuration
nous-hermes-2-mixtral-8x7b-dpo
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

nous-hermes-2-mixtral-8x7b-dpo

1,066.25 rating

Confidence interval: 1,047.86 – 1,084.63

929 votes

Category
hard_prompts_english
Evaluated configuration
nous-hermes-2-mixtral-8x7b-dpo
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

nous-hermes-2-mixtral-8x7b-dpo

1,071.18 rating

Confidence interval: 1,036.73 – 1,105.63

282 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
nous-hermes-2-mixtral-8x7b-dpo
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

nous-hermes-2-mixtral-8x7b-dpo

1,066.71 rating

Confidence interval: 1,043.16 – 1,090.27

593 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
nous-hermes-2-mixtral-8x7b-dpo
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

nous-hermes-2-mixtral-8x7b-dpo

1,103.73 rating

Confidence interval: 1,080.98 – 1,126.49

651 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
nous-hermes-2-mixtral-8x7b-dpo
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

nous-hermes-2-mixtral-8x7b-dpo

1,049.89 rating

Confidence interval: 1,024.19 – 1,075.59

464 votes

Category
industry_mathematical
Evaluated configuration
nous-hermes-2-mixtral-8x7b-dpo
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

nous-hermes-2-mixtral-8x7b-dpo

1,056.18 rating

Confidence interval: 1,024.16 – 1,088.20

266 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
nous-hermes-2-mixtral-8x7b-dpo
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

nous-hermes-2-mixtral-8x7b-dpo

1,094.70 rating

Confidence interval: 1,076.19 – 1,113.20

993 votes

Category
industry_software_and_it_services
Evaluated configuration
nous-hermes-2-mixtral-8x7b-dpo
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

nous-hermes-2-mixtral-8x7b-dpo

1,105.05 rating

Confidence interval: 1,085.23 – 1,124.86

858 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
nous-hermes-2-mixtral-8x7b-dpo
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

nous-hermes-2-mixtral-8x7b-dpo

1,055.83 rating

Confidence interval: 1,039.75 – 1,071.91

1421 votes

Category
instruction_following
Evaluated configuration
nous-hermes-2-mixtral-8x7b-dpo
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

nous-hermes-2-mixtral-8x7b-dpo

1,045.52 rating

Confidence interval: 1,010.85 – 1,080.19

230 votes

Category
longer_query
Evaluated configuration
nous-hermes-2-mixtral-8x7b-dpo
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

nous-hermes-2-mixtral-8x7b-dpo

1,060.52 rating

Confidence interval: 1,039.16 – 1,081.87

628 votes

Category
math
Evaluated configuration
nous-hermes-2-mixtral-8x7b-dpo
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

nous-hermes-2-mixtral-8x7b-dpo

1,081.09 rating

Confidence interval: 1,055.30 – 1,106.88

467 votes

Category
multi_turn
Evaluated configuration
nous-hermes-2-mixtral-8x7b-dpo
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

nous-hermes-2-mixtral-8x7b-dpo

1,048.93 rating

Confidence interval: 1,028.33 – 1,069.53

744 votes

Category
non_english
Evaluated configuration
nous-hermes-2-mixtral-8x7b-dpo
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

nous-hermes-2-mixtral-8x7b-dpo

1,112.00 rating

Confidence interval: 1,100.22 – 1,123.78

3777 votes

Category
overall
Evaluated configuration
nous-hermes-2-mixtral-8x7b-dpo
Evaluation type
human preference

Run it locally

Inference · memory estimate

nous-hermes-2-mixtral-8x7b-dpo

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Apache-2.0