Sign Up

Qwen3.6 Plus

Qwen
Announcement
Qwen3.6 Plus launch post cover

Cost/1M tokens

input
$0.325
output
$1.95
cache write
$0.4063
Context
1Mtokens
Released
7mo ago

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Arena leaderboards and other sourced evaluations appear below; missing scores are not zero.

How it ranks

Against its predecessor, similarly priced models and the models ranked around it.

DeepSWE 1.1

Best pass@1 per model · Higher is better

Not evaluated in DeepSWE 1.1

Arena Text

Best Arena rating per model · Higher is better

Arena #92

  1. 1446
    Gemini 2.5 ProNearby rank
  2. 1443
    InklingNearby rank
  3. 1443
    Qwen3.6 Plus
  4. 1442
    Grok 4.7Nearby rank
  5. 1442
    Grok 4.3Nearby rank
  6. 1434
    MiMo-V2.5Similar price
  7. 1415
    Mistral Large 3 2512Similar price
  8. 1396
    Qwen3.5-FlashEarlier version
  9. 1383
    GPT-4.1 MiniSimilar price
  10. 1293
    Llama 3.1 70B InstructSimilar price

+47 vs Qwen3.5-Flash (earlier version) · Ahead of 4 of 4 similarly priced models

Arena WebDev

Best Arena rating per model · Higher is better

Arena #81

  1. 1474
    Kimi K2.7 CodeNearby rank
  2. 1462
    GPT-5.4Nearby rank
  3. 1461
    Qwen3.6 Plus
  4. 1448
    DeepSeek V4 Pro 0423Nearby rank
  5. 1446
    Gemini 3.1 Pro PreviewNearby rank
  6. 1438
    MiMo-V2.5Similar price
  7. 1408
    Inkling SmallSimilar price
  8. 1245
    GPT-5.1-Codex-MiniSimilar price
  9. 1244
    Qwen3.5-FlashEarlier version
  10. 1233
    Mistral Large 3 2512Similar price

+218 vs Qwen3.5-Flash (earlier version) · Ahead of 4 of 4 similarly priced models

Arena Vision

Best Arena rating per model · Higher is better

Not ranked on Arena Vision yet

Arena Search

Best Arena rating per model · Higher is better

Not ranked on Arena Search yet

Agent Arena

Best IPS score per model · Higher is better

Not ranked on Agent Arena yet

FrontierMath-2025-02-28-Private

Best score per model · Higher is better

#18 of 58

  1. 28.3%
    GPT-5.4 MiniNearby rank
  2. 27.2%
    GPT-5 MiniNearby rank
  3. 26.2%
    Qwen3.6 Plus
  4. 25.9%
    GPT-5.4 NanoNearby rank
  5. 23.1%
    Qwen3.6 Max PreviewNearby rank
  6. 21.0%
    Qwen3.5 PlusPredecessor
  7. 4.8%
    Gemini 2.5 FlashSimilar price
  8. 4.5%
    GPT-4.1 MiniSimilar price
  9. 3.8%
    GLM 4.6Similar price
  10. 0.3%
    Mistral Medium 3Similar price

+5.2 pts vs Qwen3.5 Plus (predecessor) · Ahead of 4 of 4 similarly priced models

FrontierMath-Tier-4-2025-07-01-Private

Best score per model · Higher is better

#14 of 46

  1. 12.5%
    GPT-5.1Nearby rank
  2. 12.5%
    GLM 5.1Nearby rank
  3. 8.3%
    Qwen3.6 Plus
  4. 8.3%
    Claude Sonnet 4.6Nearby rank
  5. 6.3%
    GPT-5 MiniSimilar price
  6. 4.2%
    Gemini 2.5 FlashSimilar price
  7. 2.1%
    GLM 4.6Similar price
  8. 2.1%
    Qwen3.5 PlusPredecessor
  9. 0.0%
    Kimi K2 ThinkingSimilar price

+6.3 pts vs Qwen3.5 Plus (predecessor) · Ahead of 4 of 4 similarly priced models

FrontierMath-Tiers-1-3-v2-Private

Best score per model · Higher is better

#61 of 87

  1. 67.4%
    DeepSeek V4.1 FlashSimilar price
  2. 46.3%
    Inkling SmallSimilar price
  3. 44.9%
    Grok 4.20 (Reasoning)Nearby rank
  4. 42.8%
    Grok 4.3Nearby rank
  5. 38.2%
    Qwen3.6 Plus
  6. 36.8%
    GLM 5.1Nearby rank
  7. 35.1%
    Qwen3.6 27BNearby rank
  8. 26.0%
    Gemini 3.5 Flash LiteSimilar price
  9. 18.2%
    Qwen3.5-FlashEarlier version
  10. 6.7%
    GPT-4.1 MiniSimilar price

+20.0 pts vs Qwen3.5-Flash (earlier version) · Ahead of 2 of 4 similarly priced models

GPQA diamond

Best score per model · Higher is better

#52 of 161

  1. 88.8%
    Grok 4.3Nearby rank
  2. 88.5%
    Inkling SmallNearby rank
  3. 88.4%
    Qwen3.6 Plus
  4. 88.3%
    InklingNearby rank
  5. 88.1%
    Mistral Large 4Nearby rank
  6. 84.8%
    Qwen3.5 PlusPredecessor
  7. 65.8%
    GPT-4.1 MiniSimilar price
  8. 59.5%
    Mistral Medium 3Similar price
  9. 44.2%
    Llama 3.1 70B InstructSimilar price
  10. 36.5%
    Gemma 2 27BSimilar price

+3.5 pts vs Qwen3.5 Plus (predecessor) · Ahead of 4 of 4 similarly priced models

OTIS Mock AIME 2024-2025

Best score per model · Higher is better

#47 of 158

  1. 94.2%
    Gemini 3.6 FlashNearby rank
  2. 93.9%
    GLM 5.3 FlashNearby rank
  3. 93.3%
    Qwen3.6 Plus
  4. 93.3%
    Qwen3.7 PlusNearby rank
  5. 93.3%
    Grok 4.3Nearby rank
  6. 86.7%
    Qwen3.5 PlusPredecessor
  7. 44.7%
    GPT-4.1 MiniSimilar price
  8. 32.2%
    Mistral Medium 3Similar price
  9. 3.6%
    Llama 3.1 70B InstructSimilar price
  10. 1.4%
    Gemma 2 27BSimilar price

+6.7 pts vs Qwen3.5 Plus (predecessor) · Ahead of 4 of 4 similarly priced models

SimpleQA Verified

Best score per model · Higher is better

#45 of 87

  1. 45.7%
    Claude Opus 4.5Nearby rank
  2. 45.1%
    GPT-5.4Nearby rank
  3. 44.1%
    Qwen3.6 Plus
  4. 43.2%
    GPT-5.6 TerraNearby rank
  5. 42.9%
    DeepSeek V4.1 FlashNearby rank
  6. 34.3%
    Kimi K2.5Similar price
  7. 32.2%
    GLM 4.7Similar price
  8. 25.4%
    Qwen3.5 PlusPredecessor
  9. 19.1%
    Inkling SmallSimilar price
  10. 12.7%
    GPT-4.1 MiniSimilar price

+18.8 pts vs Qwen3.5 Plus (predecessor) · Ahead of 4 of 4 similarly priced models

SWE-bench Verified

Best score per model · Higher is better

#32 of 35

  1. 77.6%
    DeepSeek V4 Pro 0423Similar price
  2. 75.4%
    Gemini 3 Flash PreviewSimilar price
  3. 73.8%
    Kimi K2.5Similar price
  4. 64.7%
    GPT-5 MiniSimilar price
  5. 62.3%
    o3Nearby rank
  6. 61.0%
    Claude Sonnet 3.7Nearby rank
  7. 57.9%
    Qwen3.6 Plus
  8. 57.6%
    Gemini 2.5 ProNearby rank
  9. 48.5%
    GPT-4.1Nearby rank

Ahead of 0 of 4 similarly priced models

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

All published scores

  • Arena TextArena #921443

    +47 vs Qwen3.5-Flash (earlier version)

    • default144395% CI 1439 to 1447 · 47,601 votes
    Source:Arena Text leaderboard, 2026-11-09
  • Arena WebDevArena #811461

    +218 vs Qwen3.5-Flash (earlier version)

    • default146195% CI 1456 to 1467 · 18,263 votes
    Source:Arena WebDev leaderboard, 2026-11-10
  • FrontierMath-2025-02-28-Private#18 of 5826.2%

    +5.2 pts vs Qwen3.5 Plus (predecessor)

    • default26.2%
    Source:Epoch AI evaluation
  • FrontierMath-Tier-4-2025-07-01-Private#14 of 468.3%

    +6.3 pts vs Qwen3.5 Plus (predecessor)

    • default8.3%
    Source:Epoch AI evaluation
  • FrontierMath-Tiers-1-3-v2-Private#61 of 8738.2%

    +20.0 pts vs Qwen3.5-Flash (earlier version)

    • none32.3%
    • default38.2%
    Source:Epoch AI evaluation
  • GPQA diamond#52 of 16188.4%

    +3.5 pts vs Qwen3.5 Plus (predecessor)

    • default88.4%
    Source:Epoch AI evaluation
  • OTIS Mock AIME 2024-2025#47 of 15893.3%

    +6.7 pts vs Qwen3.5 Plus (predecessor)

    • default93.3%
    Source:Epoch AI evaluation
  • SimpleQA Verified#45 of 8744.1%

    +18.8 pts vs Qwen3.5 Plus (predecessor)

    • default44.1%
    Source:Epoch AI evaluation
  • SWE-bench Verified#32 of 3557.9%
    • default57.9%
    Source:Epoch AI evaluation

Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.

Arena ratings: Arena (lmarena-ai/leaderboard-dataset), licensed CC BY 4.0. Ratings come from pairwise human votes and are only comparable within one leaderboard; the interval is Arena's 95% confidence interval. Model names are matched to the Vertical Tabs catalog.

To give you the best experience, we use cookies for personalization, insights, and performance. Learn more.