Qwen3.8 Max (0902)
- Input
- $2.00/M tok
- Output
- $6.00/M tok
- Blended
- $3.00/M tok · 3:1
- Speed
- 39tok/s
- Context
- 1Mtokens
- Cost per task
- $10/task · AA
API-only; built on the Qwen3.8 2.4T A95B checkpoint with vision and 1M context.
Rankings
Coding
Verified#42 / 137rank by quality61.4±4.5quality / 1004/7 benchmarks measuredWriting & chat
Verified#10 / 162rank by quality78.4±6.0quality / 1002/5 benchmarks measuredVision
Verified#16 / 98rank by quality76.1±4.8quality / 1003/6 benchmarks measuredHard reasoning
Verified#21 / 218rank by quality77.2±3.7quality / 1003/4 benchmarks measuredAgents
Verified#10 / 187rank by quality82.9±5.9quality / 1003/7 benchmarks measured
Benchmark scores
~ italic, dashed = no published score yet, estimated from related benchmarks.
Coding
SWE-bench VerifiedEstimated
~#3 of 21 (estimated)~84.8%
- #1Claude Opus 596.0%
- #2Claude Sonnet 585.2%
- ~#3Qwen3.8 Max (0902)Estimated84.8%
- #3Beam 1.0 501B A23B81.6%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#7 of 24 (estimated)~67.0%
- #1Claude Fable 5.293.0%
- #2Claude Opus 5.589.9%
- #6Intern-S2-397B68.5%
- ~#7Qwen3.8 Max (0902)Estimated67.0%
- #7Beam 1.0 501B A23B66.1%
No published score — estimated from related benchmarks
DeepSWE v1.1Verified
#37 of 4551.0%
- #1Gemini 4 Argon78.8%
- #2DeepSeek V4.1 Flash 101777.0%
- #36Nex-N2.5-Pro55.8%
- #37Qwen3.8 Max (0902)51.0%
- #38Ripple-65B Preview44.3%
artificialanalysis.ai · 2026-09-24
Terminal-Bench 4.0Verified
#15 of 10138.9%
- #1Kimi K3.1 Pro67.2%
- #2Claude Sonnet 5.563.6%
- #14GLM-5.341.9%
- #15Qwen3.8 Max (0902)38.9%
- #16GPT-5.6 Terra35.4%
artificialanalysis.ai · 2026-09-24
LiveCodeBenchEstimated
~#10 of 28 (estimated)~84.2%
- #1Qwen3.8-Omni-Flash92.6%
- #2Qwen3.8 Flash-Next91.9%
- #9Nemotron 3.5 Super VL NVFP487.4%
- ~#10Qwen3.8 Max (0902)Estimated84.2%
- #10Ternary Bonsai 27B82.8%
No published score — estimated from related benchmarks
Writing & chat
IFBenchEstimated
~#20 of 140 (estimated)~75.9%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #19Muse Glimmer77.0%
- ~#20Qwen3.8 Max (0902)Estimated75.9%
- #20GPT-5.4 nano75.9%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Verified
#10 of 561470 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #9GPT-5.51474
- #10Qwen3.8 Max (0902)1470
- #11GPT-6.1 Sol1469
lmarena.ai · 2026-10-02
EQ-Bench Creative Writing v3 (Elo)Estimated
~#9 of 26 (estimated)~1962 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #8Grok 4.72007
- ~#9Qwen3.8 Max (0902)Estimated1962
- #9Muse Spark 1.31906
No published score — estimated from related benchmarks
Vision
MMMU-ProVerified
#8 of 8782.8%
- #1Claude Opus 5.587.7%
- #2GPT-6 Astra86.9%
- #7GPT-6 Sol83.3%
- #8Qwen3.8 Max (0902)82.8%
- #9Gemini 3.1 Pro82.4%
artificialanalysis.ai · 2026-09-24
CharXiv ReasoningEstimated
~#4 of 12 (estimated)~84.1%
- #1Gemini 3.8 Flash86.2%
- #2Kimi K384.8%
- #3Qwen3.8 Flash-Next84.6%
- ~#4Qwen3.8 Max (0902)Estimated84.1%
- #4Qwen3.8-Omni-Flash83.5%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#4 of 8 (estimated)~90.7%
- #1MiniMax-M391.6%
- #2Kimi K391.1%
- #2Qwen3.8 27B91.1%
- ~#4Qwen3.8 Max (0902)Estimated90.7%
- #4Gemini 3.1 Pro85.3%
No published score — estimated from related benchmarks
GDP.pdf (AA)Verified
#11 of 4722.8%
- #1Muse Wonder Full32.6%
- #2GPT-6 Astra31.0%
- #11GPT-6 Luna22.8%
- #11Qwen3.8 Max (0902)22.8%
- #13Kimi K322.0%
artificialanalysis.ai · 2026-09-24
ChartographyVerified
#10 of 2429.1%
- #1Claude Fable 5.273.4%
- #2GPT-6 Astra71.0%
- #10GPT-6 Luna29.1%
- #10Qwen3.8 Max (0902)29.1%
- #12Muse Spark 1.327.6%
surgehq.ai · 2026-09-24
Hard reasoning
GPQA DiamondVerified
#13 of 19292.8%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #13DeepSeek V4 Pro (0813)92.8%
- #13Qwen3.8 Max (0902)92.8%
- #15GLM-5.3 NVFP492.7%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#26 of 19843.1%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #26Grok 4.743.1%
- #26Qwen3.8 Max (0902)43.1%
- #28GPT-5.6 Terra42.9%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#2 of 34 (estimated)~98.0%
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Estimated
~#2 of 120 (estimated)~98.3%
No published score — estimated from related benchmarks
OSWorld-VerifiedEstimated
~#3 of 15 (estimated)~83.1%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~57.5%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#5 of 22 (estimated)~90.1%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #4Claude Opus 590.8%
- ~#5Qwen3.8 Max (0902)Estimated90.1%
- #5Nex-N2.5-Pro89.7%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Verified
#10 of 911668 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #9Muse Spark 1.31681
- #10Qwen3.8 Max (0902)1668
- #11GLM-5.31653
artificialanalysis.ai · 2026-09-24