geekradar
Int
Explore GeekRadar

More to explore

Good gear All topics About us Say hello
GeekRadar / The comparison desk
COMPARE.
AI models
alibaba

Qwen3.7 Plus

AI model Released

Context window
1,000,000 tokens
Maximum output
64,000 tokens
Open weights
No

Capability & preference

General capability · ECI

A cross-benchmark capability estimate. Index points, not a percentage; intervals show uncertainty.

Qwen3.7 Plus 147.1* Qwen3.7-Plus · 95% interval 145.1–148.7

Human preference · Arena

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

Qwen3.7 Plus 1454.6 Qwen3.7-Plus · 95% interval 1450.2–1458.9 · 42,011 votes · 2026-10-28

Model performance

Radar task score: four tests, equal weight. An experimental summary of these tasks, not a universal intelligence rating.

Qwen3.7 Plus

Radar task score

Unrated

3/4 core tests · not enough evidence

4 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

Expert-written science questions; strict multiple-choice scoring. Chance accuracy is 25%.

Qwen3.7 Plus 81.8*% Approx. 95% interval: 76.4–87.2%

Novel problem solving

Mystery Game Puzzles · 25%

Best-next-move puzzles in an undisclosed game variant. A narrow reasoning test, not general intelligence.

Qwen3.7 Plus 17.0*% Approx. 95% interval: 9.6–24.4%

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

Private v2 mathematics problems with Python tools. Earlier versions and Tier 4 are excluded.

Qwen3.7 Plus 34.4*% Approx. 95% interval: 28.9–39.9%

Factual answers

SimpleQA Verified · 25%

Correct factual answers under a guessing prompt, graded by a model. Not a hallucination or abstention score.

Qwen3.7 Plus Not available

Competition mathematics

OTIS Mock AIME 2024-2025 · Separate result

Competition problems with model-extracted answers checked against an exact key. Earlier grading procedures are excluded.

Qwen3.7 Plus 80.0*% Approx. 95% interval: 68.2–91.8%

Bars show reported task scores. Whiskers are approximate 95% intervals where standard errors are available. Different reasoning budgets are not equal-cost tests. Missing results are never zero.

Benchmark results

  • Agentic coding DeepSWE 1.1 · 1.1 · reported score · Claude Code14.20*Platform unreported Compare results
    Test conditions
    Metric
    reported score*
    Checkpoint version
    Not specified*
    Harness
    Claude Code*
    Temperature
    1.0*
    Top p
    0.95*
    Context length
    256K tokens*
  • Agentic coding SWE-bench Pro · version unreported · reported score · Claude Code · Refined task set with corrected problematic tasks57.60*Platform unreported Compare results
    Test conditions
    Metric
    reported score*
    Checkpoint version
    Not specified*
    Harness
    Claude Code*
    Task set
    Refined task set with corrected problematic tasks*
    Temperature
    1.0*
    Top p
    0.95*
    Context length
    256K tokens*
  • Agentic terminal coding Terminal Bench 2.1 (Terminus) · 2.1 · reported score · Terminus64*Platform unreported Compare results
    Test conditions
    Metric
    reported score*
    Checkpoint version
    Not specified*
    Harness
    Terminus*
  • Application recreation RecreationBench · version unreported · reported score · Internal30.20*Platform unreported Compare results
    Test conditions
    Metric
    reported score*
    Checkpoint version
    Not specified*
    Task set
    Internal*
    Variant
    Application recreation across Ubuntu, macOS, Windows, Android and web*
  • Browser use WebArena-Verified · version unreported · reported score · OSWorld scaffold; official WebArena-Verified grader55.30*Platform unreported Compare results
    Test conditions
    Metric
    reported score*
    Checkpoint version
    Not specified*
    Harness
    OSWorld scaffold; official WebArena-Verified grader*
  • Competitive coding LiveCodeBench v6 · 6 · reported score89.60*Platform unreported Compare results
    Test conditions
    Metric
    reported score*
    Checkpoint version
    Not specified*
  • Computer use OSWorld-Verified · version unreported · reported score73.30*Platform unreported Compare results
    Test conditions
    Metric
    reported score*
    Checkpoint version
    Not specified*
  • Document intelligence OmniDocBench 1.5 · 1.5 · reported score91.40*Platform unreported Compare results
    Test conditions
    Metric
    reported score*
    Checkpoint version
    Not specified*
  • Embodied intelligence ERQA · version unreported · reported score69.80*Platform unreported Compare results
    Test conditions
    Metric
    reported score*
    Checkpoint version
    Not specified*
  • Frontier agentic tasks Agents' Last Exam · version unreported · pass@113.20*Platform unreported Compare results
    Test conditions
    Metric
    pass@1*
    Checkpoint version
    Not specified*
  • Frontier agentic tasks Agents' Last Exam · version unreported · score33.60*Platform unreported Compare results
    Test conditions
    Metric
    score*
    Checkpoint version
    Not specified*
  • General visual reasoning BabyVision · version unreported · reported score · Code interpreter disabled64.70*Platform unreported Compare results
    Test conditions
    Metric
    reported score*
    Checkpoint version
    Not specified*
    Tool access
    Code interpreter disabled*
  • General visual reasoning BabyVision · version unreported · reported score · Code interpreter enabled70.40*Platform unreported Compare results
    Test conditions
    Metric
    reported score*
    Checkpoint version
    Not specified*
    Tool access
    Code interpreter enabled*
  • Instruction following IFBench · version unreported · reported score79.10*Platform unreported Compare results
    Test conditions
    Metric
    reported score*
    Checkpoint version
    Not specified*
  • Long-horizon office work CoWorkBench · version unreported · reported score · Internal65.10*Platform unreported Compare results
    Test conditions
    Metric
    reported score*
    Checkpoint version
    Not specified*
    Task set
    Internal*
  • Mobile use AndroidWorld · version unreported · reported score81*Platform unreported Compare results
    Test conditions
    Metric
    reported score*
    Checkpoint version
    Not specified*
  • Multidisciplinary reasoning HLE · version unreported · reported score34.70*Platform unreported Compare results
    Test conditions
    Metric
    reported score*
    Checkpoint version
    Not specified*
    Judge
    GPT-4o*
  • Multimodal software engineering SWE-MM · version unreported · reported score · Claude Code · Public SWE-bench Multimodal dev split with Opus 4.7 system-card appendix 8.3 modifications30*Platform unreported Compare results
    Test conditions
    Metric
    reported score*
    Checkpoint version
    Not specified*
    Harness
    Claude Code*
    Task set
    Public SWE-bench Multimodal dev split with Opus 4.7 system-card appendix 8.3 modifications*
  • Multimodal tool use ClawEval-MM · version unreported · average score · Mean benchmark score over three trials60.10*Platform unreported Compare results
    Test conditions
    Metric
    average score*
    Checkpoint version
    Not specified*
    Statistic
    Mean benchmark score over three trials*
  • Multimodal tool use ClawEval-MM · version unreported · pass@3 · At least one success in three trials57.40* %Platform unreported Compare results
    Test conditions
    Metric
    pass@3*
    Checkpoint version
    Not specified*
    Statistic
    At least one success in three trials*
  • Professional job tasks JobBench · version unreported · reported score27.60*Platform unreported Compare results
    Test conditions
    Metric
    reported score*
    Checkpoint version
    Not specified*
  • Real-world perception RealWorldQA · version unreported · reported score86.90*Platform unreported Compare results
    Test conditions
    Metric
    reported score*
    Checkpoint version
    Not specified*
  • Repo-level code generation NL2Repo-Bench · version unreported · reported score · Claude Code · Repository acquisition commands disabled41.10*Platform unreported Compare results
    Test conditions
    Metric
    reported score*
    Checkpoint version
    Not specified*
    Harness
    Claude Code*
    Tool access
    Repository acquisition commands disabled*
  • Scientific chart analysis CharXiv (RQ) · version unreported · reported score · Code interpreter disabled85.80*Platform unreported Compare results
    Test conditions
    Metric
    reported score*
    Checkpoint version
    Not specified*
    Tool access
    Code interpreter disabled*
    Annotation set
    Corrected ground-truth annotations*
  • Scientific chart analysis CharXiv (RQ) · version unreported · reported score · Code interpreter enabled85.90*Platform unreported Compare results
    Test conditions
    Metric
    reported score*
    Checkpoint version
    Not specified*
    Tool access
    Code interpreter enabled*
    Annotation set
    Corrected ground-truth annotations*
  • Scientific reasoning GPQA Diamond · version unreported · reported score90.30*Platform unreported Compare results
    Test conditions
    Metric
    reported score*
    Checkpoint version
    Not specified*
  • Software engineering QwenSWEBench · version unreported · reported score · Claude Code · Internal · avg@359.20*Platform unreported Compare results
    Test conditions
    Metric
    reported score*
    Checkpoint version
    Not specified*
    Harness
    Claude Code*
    Statistic
    avg@3*
    Timeout
    8 hours*
    Task set
    Internal*
    Maximum output
    32,768*
    Temperature
    1.0*
    Context length
    256K tokens*
  • Visual math problem solving MathVision · version unreported · reported score · Code interpreter disabled90.30*Platform unreported Compare results
    Test conditions
    Metric
    reported score*
    Checkpoint version
    Not specified*
    Tool access
    Code interpreter disabled*
    Annotation set
    Corrected ground-truth annotations*
    Prompt
    Best of two prompts, with and without boxed final-answer formatting*
  • Visual web development Vision2Web · version unreported · reported score · Claude Code · Category average42.10*Platform unreported Compare results
    Test conditions
    Metric
    reported score*
    Checkpoint version
    Not specified*
    Harness
    Claude Code*
    Judge
    gpt-5.4-2026-03-05*
    Categories
    Frontend, webpage and website*
    Statistic
    Category average*

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

Qwen3.7 Plus

1,509.55 rating

Confidence interval: 1,497.65 – 1,521.45

2646 votes

Category
chinese
Evaluated configuration
Qwen3.7-Plus
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

Qwen3.7 Plus

1,472.52 rating

Confidence interval: 1,466.17 – 1,478.86

12194 votes

Category
coding
Evaluated configuration
Qwen3.7-Plus
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

Qwen3.7 Plus

1,437.82 rating

Confidence interval: 1,430.21 – 1,445.42

7794 votes

Category
creative_writing
Evaluated configuration
Qwen3.7-Plus
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

Qwen3.7 Plus

1,458.74 rating

Confidence interval: 1,453.17 – 1,464.32

17706 votes

Category
english
Evaluated configuration
Qwen3.7-Plus
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

Qwen3.7 Plus

1,454.20 rating

Confidence interval: 1,448.60 – 1,459.80

30935 votes

Category
exclude_ties
Evaluated configuration
Qwen3.7-Plus
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

Qwen3.7 Plus

1,466.32 rating

Confidence interval: 1,457.30 – 1,475.33

4723 votes

Category
expert
Evaluated configuration
Qwen3.7-Plus
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating

Qwen3.7 Plus

1,471.42 rating

Confidence interval: 1,455.39 – 1,487.46

1606 votes

Category
french
Evaluated configuration
Qwen3.7-Plus
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating

Qwen3.7 Plus

1,470.20 rating

Confidence interval: 1,448.49 – 1,491.90

758 votes

Category
german
Evaluated configuration
Qwen3.7-Plus
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

Qwen3.7 Plus

1,459.52 rating

Confidence interval: 1,454.57 – 1,464.48

28284 votes

Category
hard_prompts
Evaluated configuration
Qwen3.7-Plus
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

Qwen3.7 Plus

1,460.23 rating

Confidence interval: 1,453.84 – 1,466.63

12148 votes

Category
hard_prompts_english
Evaluated configuration
Qwen3.7-Plus
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

Qwen3.7 Plus

1,434.66 rating

Confidence interval: 1,427.41 – 1,441.92

8377 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Qwen3.7-Plus
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

Qwen3.7 Plus

1,421.43 rating

Confidence interval: 1,414.55 – 1,428.31

9992 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Qwen3.7-Plus
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

Qwen3.7 Plus

1,451.72 rating

Confidence interval: 1,441.47 – 1,461.98

3558 votes

Category
industry_legal_and_government
Evaluated configuration
Qwen3.7-Plus
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

Qwen3.7 Plus

1,464.13 rating

Confidence interval: 1,456.42 – 1,471.84

6748 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Qwen3.7-Plus
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

Qwen3.7 Plus

1,469.67 rating

Confidence interval: 1,456.84 – 1,482.50

2255 votes

Category
industry_mathematical
Evaluated configuration
Qwen3.7-Plus
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

Qwen3.7 Plus

1,465.03 rating

Confidence interval: 1,453.65 – 1,476.40

2972 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Qwen3.7-Plus
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

Qwen3.7 Plus

1,472.95 rating

Confidence interval: 1,467.28 – 1,478.62

17157 votes

Category
industry_software_and_it_services
Evaluated configuration
Qwen3.7-Plus
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

Qwen3.7 Plus

1,437.41 rating

Confidence interval: 1,430.77 – 1,444.06

10795 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Qwen3.7-Plus
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

Qwen3.7 Plus

1,439.57 rating

Confidence interval: 1,433.66 – 1,445.48

15013 votes

Category
instruction_following
Evaluated configuration
Qwen3.7-Plus
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating

Qwen3.7 Plus

1,411.55 rating

Confidence interval: 1,387.58 – 1,435.52

680 votes

Category
japanese
Evaluated configuration
Qwen3.7-Plus
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating

Qwen3.7 Plus

1,412.78 rating

Confidence interval: 1,391.57 – 1,433.99

829 votes

Category
korean
Evaluated configuration
Qwen3.7-Plus
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

Qwen3.7 Plus

1,454.05 rating

Confidence interval: 1,448.41 – 1,459.68

19524 votes

Category
longer_query
Evaluated configuration
Qwen3.7-Plus
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

Qwen3.7 Plus

1,467.36 rating

Confidence interval: 1,453.69 – 1,481.04

1909 votes

Category
math
Evaluated configuration
Qwen3.7-Plus
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

Qwen3.7 Plus

1,459.34 rating

Confidence interval: 1,451.57 – 1,467.11

7006 votes

Category
multi_turn
Evaluated configuration
Qwen3.7-Plus
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

Qwen3.7 Plus

1,444.69 rating

Confidence interval: 1,439.63 – 1,449.76

24303 votes

Category
non_english
Evaluated configuration
Qwen3.7-Plus
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

Qwen3.7 Plus

1,454.56 rating

Confidence interval: 1,450.24 – 1,458.88

42011 votes

Category
overall
Evaluated configuration
Qwen3.7-Plus
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating

Qwen3.7 Plus

1,449.06 rating

Confidence interval: 1,428.68 – 1,469.43

807 votes

Category
polish
Evaluated configuration
Qwen3.7-Plus
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

Qwen3.7 Plus

1,457.58 rating

Confidence interval: 1,448.58 – 1,466.59

4651 votes

Category
russian
Evaluated configuration
Qwen3.7-Plus
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating

Qwen3.7 Plus

1,456.10 rating

Confidence interval: 1,438.51 – 1,473.69

1238 votes

Category
spanish
Evaluated configuration
Qwen3.7-Plus
Evaluation type
human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating

Qwen3.7 Plus

1,509.93 rating

Confidence interval: 1,498.07 – 1,521.79

2662 votes

Category
chinese
Evaluated configuration
qwen3.7-plus
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

Qwen3.7 Plus

1,472.64 rating

Confidence interval: 1,466.29 – 1,479.00

12183 votes

Category
coding
Evaluated configuration
qwen3.7-plus
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

Qwen3.7 Plus

1,438.56 rating

Confidence interval: 1,430.96 – 1,446.15

7841 votes

Category
creative_writing
Evaluated configuration
qwen3.7-plus
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

Qwen3.7 Plus

1,458.73 rating

Confidence interval: 1,453.16 – 1,464.31

17716 votes

Category
english
Evaluated configuration
qwen3.7-plus
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

Qwen3.7 Plus

1,454.23 rating

Confidence interval: 1,448.63 – 1,459.83

30986 votes

Category
exclude_ties
Evaluated configuration
qwen3.7-plus
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

Qwen3.7 Plus

1,466.58 rating

Confidence interval: 1,457.56 – 1,475.60

4725 votes

Category
expert
Evaluated configuration
qwen3.7-plus
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating

Qwen3.7 Plus

1,471.98 rating

Confidence interval: 1,455.93 – 1,488.03

1613 votes

Category
french
Evaluated configuration
qwen3.7-plus
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating

Qwen3.7 Plus

1,470.76 rating

Confidence interval: 1,449.06 – 1,492.45

763 votes

Category
german
Evaluated configuration
qwen3.7-plus
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

Qwen3.7 Plus

1,459.57 rating

Confidence interval: 1,454.61 – 1,464.53

28316 votes

Category
hard_prompts
Evaluated configuration
qwen3.7-plus
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

Qwen3.7 Plus

1,460.21 rating

Confidence interval: 1,453.82 – 1,466.61

12153 votes

Category
hard_prompts_english
Evaluated configuration
qwen3.7-plus
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

Qwen3.7 Plus

1,434.77 rating

Confidence interval: 1,427.51 – 1,442.02

8382 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
qwen3.7-plus
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

Qwen3.7 Plus

1,422.30 rating

Confidence interval: 1,415.41 – 1,429.18

10017 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
qwen3.7-plus
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

Qwen3.7 Plus

1,451.92 rating

Confidence interval: 1,441.68 – 1,462.17

3568 votes

Category
industry_legal_and_government
Evaluated configuration
qwen3.7-plus
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

Qwen3.7 Plus

1,464.58 rating

Confidence interval: 1,456.88 – 1,472.28

6771 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
qwen3.7-plus
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

Qwen3.7 Plus

1,470.13 rating

Confidence interval: 1,457.31 – 1,482.96

2260 votes

Category
industry_mathematical
Evaluated configuration
qwen3.7-plus
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

Qwen3.7 Plus

1,465.44 rating

Confidence interval: 1,454.07 – 1,476.81

2985 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
qwen3.7-plus
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

Qwen3.7 Plus

1,472.91 rating

Confidence interval: 1,467.24 – 1,478.59

17150 votes

Category
industry_software_and_it_services
Evaluated configuration
qwen3.7-plus
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

Qwen3.7 Plus

1,437.73 rating

Confidence interval: 1,431.09 – 1,444.37

10852 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
qwen3.7-plus
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

Qwen3.7 Plus

1,439.58 rating

Confidence interval: 1,433.67 – 1,445.49

15033 votes

Category
instruction_following
Evaluated configuration
qwen3.7-plus
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating

Qwen3.7 Plus

1,412.15 rating

Confidence interval: 1,388.00 – 1,436.29

678 votes

Category
japanese
Evaluated configuration
qwen3.7-plus
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating

Qwen3.7 Plus

1,414.41 rating

Confidence interval: 1,393.18 – 1,435.63

836 votes

Category
korean
Evaluated configuration
qwen3.7-plus
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

Qwen3.7 Plus

1,454.51 rating

Confidence interval: 1,448.87 – 1,460.15

19564 votes

Category
longer_query
Evaluated configuration
qwen3.7-plus
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

Qwen3.7 Plus

1,467.24 rating

Confidence interval: 1,453.55 – 1,480.92

1910 votes

Category
math
Evaluated configuration
qwen3.7-plus
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

Qwen3.7 Plus

1,459.75 rating

Confidence interval: 1,451.97 – 1,467.54

7009 votes

Category
multi_turn
Evaluated configuration
qwen3.7-plus
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

Qwen3.7 Plus

1,444.90 rating

Confidence interval: 1,439.84 – 1,449.96

24357 votes

Category
non_english
Evaluated configuration
qwen3.7-plus
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

Qwen3.7 Plus

1,454.58 rating

Confidence interval: 1,450.26 – 1,458.90

42075 votes

Category
overall
Evaluated configuration
qwen3.7-plus
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating

Qwen3.7 Plus

1,449.57 rating

Confidence interval: 1,429.16 – 1,469.99

807 votes

Category
polish
Evaluated configuration
qwen3.7-plus
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

Qwen3.7 Plus

1,457.94 rating

Confidence interval: 1,448.94 – 1,466.93

4669 votes

Category
russian
Evaluated configuration
qwen3.7-plus
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating

Qwen3.7 Plus

1,457.06 rating

Confidence interval: 1,439.49 – 1,474.64

1245 votes

Category
spanish
Evaluated configuration
qwen3.7-plus
Evaluation type
human preference

Run it locally

Inference · memory estimate

Qwen3.7 Plus

Closed weights. No supported local deployment or GPU requirement is published.

API cost

USD / month

Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.

Qwen3.7 Plus

Capabilities

Context window
1,000,000 tokens
Maximum output
64,000 tokens
Reasoning
Yes
Tool calling
Yes
Open weights
No
Knowledge cutoff
2025-04
Model license
Proprietary

Input modalities

  • text
  • image
  • video

Output modalities

  • text

System configuration

Detailed specifications

Specifications · 29 fields
Frontier agentic tasks Agents' Last Exam
suite
Frontier agentic tasks Agents' Last Exam
workload
pass@1
score
13.2*
Scope and conditions
Test conditions
Metric
pass@1*
Checkpoint version
Not specified*
Visual math problem solving MathVision
suite
Visual math problem solving MathVision
workload
reported score · Code interpreter disabled
score
90.3*
Scope and conditions
Test conditions
Metric
reported score*
Checkpoint version
Not specified*
Tool access
Code interpreter disabled*
Annotation set
Corrected ground-truth annotations*
Prompt
Best of two prompts, with and without boxed final-answer formatting*
Frontier agentic tasks Agents' Last Exam
suite
Frontier agentic tasks Agents' Last Exam
workload
score
score
33.6*
Scope and conditions
Test conditions
Metric
score*
Checkpoint version
Not specified*
General visual reasoning BabyVision
suite
General visual reasoning BabyVision
workload
reported score · Code interpreter disabled
score
64.7*
Scope and conditions
Test conditions
Metric
reported score*
Checkpoint version
Not specified*
Tool access
Code interpreter disabled*
General visual reasoning BabyVision
suite
General visual reasoning BabyVision
workload
reported score · Code interpreter enabled
score
70.4*
Scope and conditions
Test conditions
Metric
reported score*
Checkpoint version
Not specified*
Tool access
Code interpreter enabled*
Scientific chart analysis CharXiv (RQ)
suite
Scientific chart analysis CharXiv (RQ)
workload
reported score · Code interpreter disabled
score
85.8*
Scope and conditions
Test conditions
Metric
reported score*
Checkpoint version
Not specified*
Tool access
Code interpreter disabled*
Annotation set
Corrected ground-truth annotations*
Instruction following IFBench
suite
Instruction following IFBench
workload
reported score
score
79.1*
Scope and conditions
Test conditions
Metric
reported score*
Checkpoint version
Not specified*
Scientific chart analysis CharXiv (RQ)
suite
Scientific chart analysis CharXiv (RQ)
workload
reported score · Code interpreter enabled
score
85.9*
Scope and conditions
Test conditions
Metric
reported score*
Checkpoint version
Not specified*
Tool access
Code interpreter enabled*
Annotation set
Corrected ground-truth annotations*
Document intelligence OmniDocBench 1.5
suite
Document intelligence OmniDocBench 1.5
version
1.5
workload
reported score
score
91.4*
Scope and conditions
Test conditions
Metric
reported score*
Checkpoint version
Not specified*
Scientific reasoning GPQA Diamond
suite
Scientific reasoning GPQA Diamond
workload
reported score
score
90.3*
Scope and conditions
Test conditions
Metric
reported score*
Checkpoint version
Not specified*
Real-world perception RealWorldQA
suite
Real-world perception RealWorldQA
workload
reported score
score
86.9*
Scope and conditions
Test conditions
Metric
reported score*
Checkpoint version
Not specified*
Multidisciplinary reasoning HLE
suite
Multidisciplinary reasoning HLE
workload
reported score
score
34.7*
Scope and conditions
Test conditions
Metric
reported score*
Checkpoint version
Not specified*
Judge
GPT-4o*
Embodied intelligence ERQA
suite
Embodied intelligence ERQA
workload
reported score
score
69.8*
Scope and conditions
Test conditions
Metric
reported score*
Checkpoint version
Not specified*
Competitive coding LiveCodeBench v6
suite
Competitive coding LiveCodeBench v6
version
6
workload
reported score
score
89.6*
Scope and conditions
Test conditions
Metric
reported score*
Checkpoint version
Not specified*
Computer use OSWorld-Verified
suite
Computer use OSWorld-Verified
workload
reported score
score
73.3*
Scope and conditions
Test conditions
Metric
reported score*
Checkpoint version
Not specified*
Agentic terminal coding Terminal Bench 2.1 (Terminus)
suite
Agentic terminal coding Terminal Bench 2.1 (Terminus)
version
2.1
workload
reported score · Terminus
score
64.0*
Scope and conditions
Test conditions
Metric
reported score*
Checkpoint version
Not specified*
Harness
Terminus*
Browser use WebArena-Verified
suite
Browser use WebArena-Verified
workload
reported score · OSWorld scaffold; official WebArena-Verified grader
score
55.3*
Scope and conditions
Test conditions
Metric
reported score*
Checkpoint version
Not specified*
Harness
OSWorld scaffold; official WebArena-Verified grader*
Agentic coding SWE-bench Pro
suite
Agentic coding SWE-bench Pro
workload
reported score · Claude Code · Refined task set with corrected problematic tasks
score
57.6*
Scope and conditions
Test conditions
Metric
reported score*
Checkpoint version
Not specified*
Harness
Claude Code*
Task set
Refined task set with corrected problematic tasks*
Temperature
1.0*
Top p
0.95*
Context length
256K tokens*
Repo-level code generation NL2Repo-Bench
suite
Repo-level code generation NL2Repo-Bench
workload
reported score · Claude Code · Repository acquisition commands disabled
score
41.1*
Scope and conditions
Test conditions
Metric
reported score*
Checkpoint version
Not specified*
Harness
Claude Code*
Tool access
Repository acquisition commands disabled*
Mobile use AndroidWorld
suite
Mobile use AndroidWorld
workload
reported score
score
81.0*
Scope and conditions
Test conditions
Metric
reported score*
Checkpoint version
Not specified*
Agentic coding DeepSWE 1.1
suite
Agentic coding DeepSWE 1.1
version
1.1
workload
reported score · Claude Code
score
14.2*
Scope and conditions
Test conditions
Metric
reported score*
Checkpoint version
Not specified*
Harness
Claude Code*
Temperature
1.0*
Top p
0.95*
Context length
256K tokens*
Application recreation RecreationBench
suite
Application recreation RecreationBench
workload
reported score · Internal
score
30.2*
Scope and conditions
Test conditions
Metric
reported score*
Checkpoint version
Not specified*
Task set
Internal*
Variant
Application recreation across Ubuntu, macOS, Windows, Android and web*
Multimodal tool use ClawEval-MM
suite
Multimodal tool use ClawEval-MM
workload
pass@3 · At least one success in three trials
score
57.4*
unit
%
Scope and conditions
Test conditions
Metric
pass@3*
Checkpoint version
Not specified*
Statistic
At least one success in three trials*
Software engineering QwenSWEBench
suite
Software engineering QwenSWEBench
workload
reported score · Claude Code · Internal · avg@3
score
59.2*
Scope and conditions
Test conditions
Metric
reported score*
Checkpoint version
Not specified*
Harness
Claude Code*
Statistic
avg@3*
Timeout
8 hours*
Task set
Internal*
Maximum output
32,768*
Temperature
1.0*
Context length
256K tokens*
Multimodal tool use ClawEval-MM
suite
Multimodal tool use ClawEval-MM
workload
average score · Mean benchmark score over three trials
score
60.1*
Scope and conditions
Test conditions
Metric
average score*
Checkpoint version
Not specified*
Statistic
Mean benchmark score over three trials*
Multimodal software engineering SWE-MM
suite
Multimodal software engineering SWE-MM
workload
reported score · Claude Code · Public SWE-bench Multimodal dev split with Opus 4.7 system-card appendix 8.3 modifications
score
30.0*
Scope and conditions
Test conditions
Metric
reported score*
Checkpoint version
Not specified*
Harness
Claude Code*
Task set
Public SWE-bench Multimodal dev split with Opus 4.7 system-card appendix 8.3 modifications*
Long-horizon office work CoWorkBench
suite
Long-horizon office work CoWorkBench
workload
reported score · Internal
score
65.1*
Scope and conditions
Test conditions
Metric
reported score*
Checkpoint version
Not specified*
Task set
Internal*
Visual web development Vision2Web
suite
Visual web development Vision2Web
workload
reported score · Claude Code · Category average
score
42.1*
Scope and conditions
Test conditions
Metric
reported score*
Checkpoint version
Not specified*
Harness
Claude Code*
Judge
gpt-5.4-2026-03-05*
Categories
Frontend, webpage and website*
Statistic
Category average*
Professional job tasks JobBench
suite
Professional job tasks JobBench
workload
reported score
score
27.6*
Scope and conditions
Test conditions
Metric
reported score*
Checkpoint version
Not specified*

* Provisional data