openchat-3.5
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsopenchat-3.5
Model evaluation
Capability & preference
Human preference · Arena
Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.
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 · 2026-10-15 · rating
openchat-3.5
1,069.99 rating
Confidence interval: 1,038.20 – 1,101.78
322 votes
- Category
- chinese
- Evaluated configuration
- openchat-3.5
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
openchat-3.5
1,074.02 rating
Confidence interval: 1,054.65 – 1,093.40
971 votes
- Category
- coding
- Evaluated configuration
- openchat-3.5
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
openchat-3.5
1,125.42 rating
Confidence interval: 1,107.47 – 1,143.37
1454 votes
- Category
- creative_writing
- Evaluated configuration
- openchat-3.5
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
openchat-3.5
1,117.59 rating
Confidence interval: 1,106.96 – 1,128.21
6196 votes
- Category
- english
- Evaluated configuration
- openchat-3.5
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
openchat-3.5
929.24 rating
Confidence interval: 915.35 – 943.14
5304 votes
- Category
- exclude_ties
- Evaluated configuration
- openchat-3.5
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
openchat-3.5
1,041.79 rating
Confidence interval: 1,001.17 – 1,082.41
194 votes
- Category
- expert
- Evaluated configuration
- openchat-3.5
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
openchat-3.5
1,065.34 rating
Confidence interval: 1,049.95 – 1,080.73
1663 votes
- Category
- hard_prompts
- Evaluated configuration
- openchat-3.5
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
openchat-3.5
1,070.97 rating
Confidence interval: 1,054.33 – 1,087.61
1389 votes
- Category
- hard_prompts_english
- Evaluated configuration
- openchat-3.5
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
openchat-3.5
1,036.08 rating
Confidence interval: 1,012.13 – 1,060.03
615 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- openchat-3.5
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
openchat-3.5
1,096.39 rating
Confidence interval: 1,079.10 – 1,113.68
1340 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- openchat-3.5
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
openchat-3.5
1,112.80 rating
Confidence interval: 1,084.32 – 1,141.28
467 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- openchat-3.5
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
openchat-3.5
1,067.26 rating
Confidence interval: 1,049.57 – 1,084.95
1439 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- openchat-3.5
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
openchat-3.5
1,069.18 rating
Confidence interval: 1,049.21 – 1,089.16
826 votes
- Category
- industry_mathematical
- Evaluated configuration
- openchat-3.5
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
openchat-3.5
1,065.80 rating
Confidence interval: 1,036.01 – 1,095.59
426 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- openchat-3.5
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
openchat-3.5
1,083.36 rating
Confidence interval: 1,067.99 – 1,098.72
1879 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- openchat-3.5
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
openchat-3.5
1,116.82 rating
Confidence interval: 1,101.25 – 1,132.38
1995 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- openchat-3.5
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
openchat-3.5
1,070.03 rating
Confidence interval: 1,056.08 – 1,083.98
2391 votes
- Category
- instruction_following
- Evaluated configuration
- openchat-3.5
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
openchat-3.5
1,092.67 rating
Confidence interval: 1,064.55 – 1,120.79
414 votes
- Category
- longer_query
- Evaluated configuration
- openchat-3.5
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
openchat-3.5
1,070.65 rating
Confidence interval: 1,052.44 – 1,088.86
945 votes
- Category
- math
- Evaluated configuration
- openchat-3.5
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
openchat-3.5
1,085.29 rating
Confidence interval: 1,066.74 – 1,103.84
1167 votes
- Category
- multi_turn
- Evaluated configuration
- openchat-3.5
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
openchat-3.5
1,066.80 rating
Confidence interval: 1,051.29 – 1,082.32
1772 votes
- Category
- non_english
- Evaluated configuration
- openchat-3.5
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
openchat-3.5
1,096.99 rating
Confidence interval: 1,087.37 – 1,106.61
7968 votes
- Category
- overall
- Evaluated configuration
- openchat-3.5
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
openchat-3.5
1,106.64 rating
Confidence interval: 1,066.66 – 1,146.63
187 votes
- Category
- russian
- Evaluated configuration
- openchat-3.5
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- Apache-2.0
0 selected Compare 0