Qwen3.5 122B-A10B
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.
GeekRadar / The comparison desk
COMPARE.
AI modelsQwen3.5 122B-A10B
AI model Released
- Context window
- 262,144 tokens
- Maximum output
- 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.
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
Qwen3.5 122B-A10B
1,462.82 rating
Confidence interval: 1,449.83 – 1,475.81
2123 votes
- Category
- chinese
- Evaluated configuration
- Qwen3.5-122B-A10B
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Qwen3.5 122B-A10B
1,435.56 rating
Confidence interval: 1,428.50 – 1,442.62
8170 votes
- Category
- coding
- Evaluated configuration
- Qwen3.5-122B-A10B
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Qwen3.5 122B-A10B
1,368.72 rating
Confidence interval: 1,359.51 – 1,377.93
4522 votes
- Category
- creative_writing
- Evaluated configuration
- Qwen3.5-122B-A10B
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Qwen3.5 122B-A10B
1,428.35 rating
Confidence interval: 1,422.55 – 1,434.14
13147 votes
- Category
- english
- Evaluated configuration
- Qwen3.5-122B-A10B
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Qwen3.5 122B-A10B
1,403.20 rating
Confidence interval: 1,397.45 – 1,408.96
21743 votes
- Category
- exclude_ties
- Evaluated configuration
- Qwen3.5-122B-A10B
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Qwen3.5 122B-A10B
1,431.15 rating
Confidence interval: 1,419.72 – 1,442.58
2724 votes
- Category
- expert
- Evaluated configuration
- Qwen3.5-122B-A10B
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
Qwen3.5 122B-A10B
1,443.34 rating
Confidence interval: 1,422.84 – 1,463.85
918 votes
- Category
- french
- Evaluated configuration
- Qwen3.5-122B-A10B
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Qwen3.5 122B-A10B
1,425.68 rating
Confidence interval: 1,398.12 – 1,453.25
425 votes
- Category
- german
- Evaluated configuration
- Qwen3.5-122B-A10B
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Qwen3.5 122B-A10B
1,421.31 rating
Confidence interval: 1,416.13 – 1,426.50
18788 votes
- Category
- hard_prompts
- Evaluated configuration
- Qwen3.5-122B-A10B
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Qwen3.5 122B-A10B
1,430.91 rating
Confidence interval: 1,423.98 – 1,437.84
8659 votes
- Category
- hard_prompts_english
- Evaluated configuration
- Qwen3.5-122B-A10B
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
Qwen3.5 122B-A10B
1,414.55 rating
Confidence interval: 1,406.44 – 1,422.66
5728 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- Qwen3.5-122B-A10B
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
Qwen3.5 122B-A10B
1,366.17 rating
Confidence interval: 1,357.97 – 1,374.38
5746 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- Qwen3.5-122B-A10B
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
Qwen3.5 122B-A10B
1,422.65 rating
Confidence interval: 1,410.27 – 1,435.03
2345 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- Qwen3.5-122B-A10B
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
Qwen3.5 122B-A10B
1,432.21 rating
Confidence interval: 1,423.65 – 1,440.78
4914 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- Qwen3.5-122B-A10B
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
Qwen3.5 122B-A10B
1,431.55 rating
Confidence interval: 1,417.11 – 1,445.98
1719 votes
- Category
- industry_mathematical
- Evaluated configuration
- Qwen3.5-122B-A10B
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
Qwen3.5 122B-A10B
1,423.38 rating
Confidence interval: 1,410.58 – 1,436.18
2186 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- Qwen3.5-122B-A10B
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
Qwen3.5 122B-A10B
1,436.17 rating
Confidence interval: 1,430.11 – 1,442.23
11690 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- Qwen3.5-122B-A10B
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
Qwen3.5 122B-A10B
1,387.68 rating
Confidence interval: 1,380.14 – 1,395.22
6800 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- Qwen3.5-122B-A10B
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
Qwen3.5 122B-A10B
1,399.55 rating
Confidence interval: 1,392.99 – 1,406.10
9566 votes
- Category
- instruction_following
- Evaluated configuration
- Qwen3.5-122B-A10B
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating
Qwen3.5 122B-A10B
1,367.11 rating
Confidence interval: 1,330.84 – 1,403.38
258 votes
- Category
- japanese
- Evaluated configuration
- Qwen3.5-122B-A10B
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating
Qwen3.5 122B-A10B
1,353.82 rating
Confidence interval: 1,326.42 – 1,381.22
476 votes
- Category
- korean
- Evaluated configuration
- Qwen3.5-122B-A10B
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
Qwen3.5 122B-A10B
1,410.45 rating
Confidence interval: 1,404.17 – 1,416.73
11722 votes
- Category
- longer_query
- Evaluated configuration
- Qwen3.5-122B-A10B
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
Qwen3.5 122B-A10B
1,431.57 rating
Confidence interval: 1,417.93 – 1,445.21
1842 votes
- Category
- math
- Evaluated configuration
- Qwen3.5-122B-A10B
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
Qwen3.5 122B-A10B
1,416.67 rating
Confidence interval: 1,408.06 – 1,425.28
5208 votes
- Category
- multi_turn
- Evaluated configuration
- Qwen3.5-122B-A10B
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
Qwen3.5 122B-A10B
1,400.63 rating
Confidence interval: 1,395.38 – 1,405.88
16565 votes
- Category
- non_english
- Evaluated configuration
- Qwen3.5-122B-A10B
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
Qwen3.5 122B-A10B
1,417.51 rating
Confidence interval: 1,413.25 – 1,421.77
29712 votes
- Category
- overall
- Evaluated configuration
- Qwen3.5-122B-A10B
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating
Qwen3.5 122B-A10B
1,400.11 rating
Confidence interval: 1,376.72 – 1,423.51
600 votes
- Category
- polish
- Evaluated configuration
- Qwen3.5-122B-A10B
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
Qwen3.5 122B-A10B
1,400.15 rating
Confidence interval: 1,390.01 – 1,410.29
3479 votes
- Category
- russian
- Evaluated configuration
- Qwen3.5-122B-A10B
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating
Qwen3.5 122B-A10B
1,425.08 rating
Confidence interval: 1,406.14 – 1,444.01
967 votes
- Category
- spanish
- Evaluated configuration
- Qwen3.5-122B-A10B
- Evaluation type
- human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating
Qwen3.5 122B-A10B
1,461.72 rating
Confidence interval: 1,448.74 – 1,474.70
2122 votes
- Category
- chinese
- Evaluated configuration
- qwen3.5-122b-a10b
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
Qwen3.5 122B-A10B
1,435.87 rating
Confidence interval: 1,428.81 – 1,442.92
8187 votes
- Category
- coding
- Evaluated configuration
- qwen3.5-122b-a10b
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
Qwen3.5 122B-A10B
1,367.81 rating
Confidence interval: 1,358.59 – 1,377.03
4521 votes
- Category
- creative_writing
- Evaluated configuration
- qwen3.5-122b-a10b
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
Qwen3.5 122B-A10B
1,428.52 rating
Confidence interval: 1,422.73 – 1,434.32
13158 votes
- Category
- english
- Evaluated configuration
- qwen3.5-122b-a10b
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
Qwen3.5 122B-A10B
1,403.06 rating
Confidence interval: 1,397.30 – 1,408.81
21755 votes
- Category
- exclude_ties
- Evaluated configuration
- qwen3.5-122b-a10b
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
Qwen3.5 122B-A10B
1,431.15 rating
Confidence interval: 1,419.73 – 1,442.57
2731 votes
- Category
- expert
- Evaluated configuration
- qwen3.5-122b-a10b
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
Qwen3.5 122B-A10B
1,442.30 rating
Confidence interval: 1,421.80 – 1,462.80
921 votes
- Category
- french
- Evaluated configuration
- qwen3.5-122b-a10b
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
Qwen3.5 122B-A10B
1,425.24 rating
Confidence interval: 1,397.76 – 1,452.72
427 votes
- Category
- german
- Evaluated configuration
- qwen3.5-122b-a10b
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
Qwen3.5 122B-A10B
1,421.24 rating
Confidence interval: 1,416.05 – 1,426.43
18806 votes
- Category
- hard_prompts
- Evaluated configuration
- qwen3.5-122b-a10b
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
Qwen3.5 122B-A10B
1,430.94 rating
Confidence interval: 1,424.01 – 1,437.87
8668 votes
- Category
- hard_prompts_english
- Evaluated configuration
- qwen3.5-122b-a10b
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
Qwen3.5 122B-A10B
1,414.15 rating
Confidence interval: 1,406.04 – 1,422.25
5731 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- qwen3.5-122b-a10b
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
Qwen3.5 122B-A10B
1,365.53 rating
Confidence interval: 1,357.32 – 1,373.73
5750 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- qwen3.5-122b-a10b
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
Qwen3.5 122B-A10B
1,422.23 rating
Confidence interval: 1,409.84 – 1,434.62
2344 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- qwen3.5-122b-a10b
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
Qwen3.5 122B-A10B
1,432.00 rating
Confidence interval: 1,423.43 – 1,440.57
4913 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- qwen3.5-122b-a10b
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
Qwen3.5 122B-A10B
1,429.94 rating
Confidence interval: 1,415.49 – 1,444.39
1716 votes
- Category
- industry_mathematical
- Evaluated configuration
- qwen3.5-122b-a10b
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
Qwen3.5 122B-A10B
1,423.53 rating
Confidence interval: 1,410.73 – 1,436.33
2190 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- qwen3.5-122b-a10b
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
Qwen3.5 122B-A10B
1,436.67 rating
Confidence interval: 1,430.61 – 1,442.73
11701 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- qwen3.5-122b-a10b
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
Qwen3.5 122B-A10B
1,386.81 rating
Confidence interval: 1,379.26 – 1,394.35
6795 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- qwen3.5-122b-a10b
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
Qwen3.5 122B-A10B
1,399.29 rating
Confidence interval: 1,392.73 – 1,405.84
9582 votes
- Category
- instruction_following
- Evaluated configuration
- qwen3.5-122b-a10b
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
Qwen3.5 122B-A10B
1,367.00 rating
Confidence interval: 1,330.53 – 1,403.47
257 votes
- Category
- japanese
- Evaluated configuration
- qwen3.5-122b-a10b
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
Qwen3.5 122B-A10B
1,353.11 rating
Confidence interval: 1,325.70 – 1,380.52
477 votes
- Category
- korean
- Evaluated configuration
- qwen3.5-122b-a10b
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
Qwen3.5 122B-A10B
1,410.19 rating
Confidence interval: 1,403.91 – 1,416.48
11732 votes
- Category
- longer_query
- Evaluated configuration
- qwen3.5-122b-a10b
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
Qwen3.5 122B-A10B
1,431.31 rating
Confidence interval: 1,417.68 – 1,444.94
1845 votes
- Category
- math
- Evaluated configuration
- qwen3.5-122b-a10b
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
Qwen3.5 122B-A10B
1,416.51 rating
Confidence interval: 1,407.91 – 1,425.12
5201 votes
- Category
- multi_turn
- Evaluated configuration
- qwen3.5-122b-a10b
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
Qwen3.5 122B-A10B
1,400.32 rating
Confidence interval: 1,395.07 – 1,405.57
16574 votes
- Category
- non_english
- Evaluated configuration
- qwen3.5-122b-a10b
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
Qwen3.5 122B-A10B
1,417.40 rating
Confidence interval: 1,413.14 – 1,421.66
29732 votes
- Category
- overall
- Evaluated configuration
- qwen3.5-122b-a10b
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
Qwen3.5 122B-A10B
1,399.14 rating
Confidence interval: 1,375.80 – 1,422.48
604 votes
- Category
- polish
- Evaluated configuration
- qwen3.5-122b-a10b
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
Qwen3.5 122B-A10B
1,399.79 rating
Confidence interval: 1,389.64 – 1,409.94
3473 votes
- Category
- russian
- Evaluated configuration
- qwen3.5-122b-a10b
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
Qwen3.5 122B-A10B
1,423.97 rating
Confidence interval: 1,404.99 – 1,442.95
965 votes
- Category
- spanish
- Evaluated configuration
- qwen3.5-122b-a10b
- Evaluation type
- human preference
Run it locally
API cost
Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.
Qwen3.5 122B-A10B
Qwen3.5 122B-A10B / Pricing tiers
| Provider / scope | Rate | Currency | Amount / unit |
|---|---|---|---|
| SiliconFlowQwen/Qwen3.5-122B-A10BStandard 1314 | Input | CNY | 2 / 1M tokens |
| Output | CNY | 16 / 1M tokens | |
| SiliconFlowQwen/Qwen3.5-122B-A10BStandard 输入 [0, 128k) Token tier: 0 – 128,000 | Input | CNY | 0.8 / 1M tokens |
| Output | CNY | 6.4 / 1M tokens | |
| SiliconFlowQwen/Qwen3.5-122B-A10BStandard 输入 [0,128k) Token tier: 0 – 128,000 | Input | CNY | 0.8 / 1M tokens |
| Output | CNY | 6.4 / 1M tokens | |
| SiliconFlowQwen/Qwen3.5-122B-A10BStandard 输入 [128k,256k) Token tier: 128,000 – 256,000 | Input | CNY | 2 / 1M tokens |
| Output | CNY | 16 / 1M tokens | |
| SiliconFlowQwen/Qwen3.5-122B-A10BStandard 输入 [128k, +∞) Token tier: 128,000 – No stated upper limit | Input | CNY | 2 / 1M tokens |
| Output | CNY | 16 / 1M tokens |
Capabilities
- Context window
- 262,144 tokens
- Maximum output
- 65,536 tokens
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- Yes
- Checkpoint tensor payload
- 232.99 GiB
Input modalities
- text
- image
- video
Output modalities
- text
Processing & platform
- Architecture
- qwen3_5_moe
0 selected Compare 0