Qwen3.8-Omni-Flash
- Input
- $0.15/M tok
- Output
- $0.47/M tok
- Blended
- $0.23/M tok · 3:1
- Speed
- ~54tok/sest.
- Context
- 1Mtokens
- Cost per task
- ~$0.20/taskest.
API-only native omnimodal model (text/image/audio/video in, text out). Not yet on Artificial Analysis (no speed).
Rankings
Coding
Lab-reported#26 / 137rank by quality68.1±8.6quality / 1002/7 benchmarks measuredWriting & chat
Lab-reported#19 / 162rank by quality76.7±9.7quality / 1001/5 benchmarks measuredVision
Lab-reported#12 / 98rank by quality77.7±10.0quality / 1001/6 benchmarks measuredPrice frontierHard reasoning
Lab-reported#45 / 218rank by quality69.5±6.6quality / 1002/4 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-Omni-FlashEstimated84.8%
- #3Beam 1.0 501B A23B81.6%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#6 of 24 (estimated)~69.2%
- #1Claude Fable 5.293.0%
- #2Claude Opus 5.589.9%
- #5Claude Opus 579.2%
- ~#6Qwen3.8-Omni-FlashEstimated69.2%
- #6Intern-S2-397B68.5%
No published score — estimated from related benchmarks
DeepSWE v1.1Lab-reported
#33 of 4557.8%
- #1Gemini 4 Argon78.8%
- #2DeepSeek V4.1 Flash 101777.0%
- #32Qwen3.8 Flash-Next58.7%
- #33Qwen3.8-Omni-Flash57.8%
- #34DeepSeek V4 Pro (0813)57.2%
qwen.ai · 2026-09-18
Terminal-Bench 4.0Estimated
~#24 of 102 (estimated)~27.3%
- #1Kimi K3.1 Pro67.2%
- #2Claude Sonnet 5.563.6%
- #22GLM-5.3 Flash32.8%
- ~#24Qwen3.8-Omni-FlashEstimated27.3%
- #24DeepSeek V4.1 Flash26.8%
No published score — estimated from related benchmarks
SciCodeEstimated
~#36 of 119 (estimated)~53.2%
- #1Claude Fable 5.267.7%
- #2Claude Opus 5.566.9%
- #35MiniMax-M3.1-Flash53.4%
- ~#36Qwen3.8-Omni-FlashEstimated53.2%
- #36Grok 4.653.0%
No published score — estimated from related benchmarks
AA Coding Agent IndexEstimated
~#18 of 26 (estimated)~45.2
- #1Claude Opus 5.561.7
- #2Claude Opus 559.7
- #17Muse Spark 1.345.7
- ~#18Qwen3.8-Omni-FlashEstimated45.2
- #18DeepSeek V4 Pro (0813)43.1
No published score — estimated from related benchmarks
Not comparable across labs (1)
Kept for reference, not counted in rankings: these use a lab-specific task set, answer key or scoring, so scores can't be compared fairly across labs. Only published scores are shown.
Writing & chat
LMArena Text, Non-English (Elo)Estimated
~#18 of 57 (estimated)~1453 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #17GPT-5.6 Terra1456
- ~#18Qwen3.8-Omni-FlashEstimated1453
- #18DeepSeek V4 Pro (0813)1448
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#18 of 57 (estimated)~1465 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #17GPT-5.6 Terra1466
- ~#18Qwen3.8-Omni-FlashEstimated1465
- #18DeepSeek V4 Pro (0813)1463
No published score — estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)Estimated
~#9 of 26 (estimated)~1949 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #8Grok 4.72007
- ~#9Qwen3.8-Omni-FlashEstimated1949
- #9Muse Spark 1.31906
No published score — estimated from related benchmarks
Vision
MMMU-ProEstimated
~#8 of 88 (estimated)~83.1%
- #1Claude Opus 5.587.7%
- #2GPT-6 Astra86.9%
- #7GPT-6 Sol83.3%
- ~#8Qwen3.8-Omni-FlashEstimated83.1%
- #8Qwen3.8 Max (0902)82.8%
No published score — estimated from related benchmarks
CharXiv ReasoningLab-reported
#4 of 1183.5%
- #1Gemini 3.8 Flash86.2%
- #2Kimi K384.8%
- #3Qwen3.8 Flash-Next84.6%
- #4Qwen3.8-Omni-Flash83.5%
- #5MiniMax-M3.1-Flash82.5%
qwen.ai · 2026-09-18
OmniDocBench v1.5Estimated
~#4 of 8 (estimated)~89.9%
- #1MiniMax-M391.6%
- #2Kimi K391.1%
- #2Qwen3.8 27B91.1%
- ~#4Qwen3.8-Omni-FlashEstimated89.9%
- #4Gemini 3.1 Pro85.3%
No published score — estimated from related benchmarks
GDP.pdf (AA)Estimated
~#13 of 48 (estimated)~22.0%
- #1Muse Wonder Full32.6%
- #2GPT-6 Astra31.0%
- #11Qwen3.8 Max (0902)22.8%
- ~#13Qwen3.8-Omni-FlashEstimated22.0%
- #13Kimi K322.0%
No published score — estimated from related benchmarks
ChartographyEstimated
~#8 of 25 (estimated)~35.9%
- #1Claude Fable 5.273.4%
- #2GPT-6 Astra71.0%
- #7Gemini 3.8 Flash40.9%
- ~#8Qwen3.8-Omni-FlashEstimated35.9%
- #8GPT-5.6 Terra34.0%
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondLab-reported
#27 of 19291.0%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #26Claude Sonnet 591.1%
- #27Qwen3.8-Omni-Flash91.0%
- #28DeepSeek V4.1 Flash90.9%
qwen.ai · 2026-09-18
Humanity's Last ExamLab-reported
#42 of 19836.5%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #41Motif 337.0%
- #42Qwen3.8-Omni-Flash36.5%
- #43Beam 1.0 501B A23B36.0%
qwen.ai · 2026-09-18
AIME (latest)Estimated
~#2 of 34 (estimated)~99.1%
No published score — estimated from related benchmarks
AA Intelligence IndexEstimated
~#37 of 103 (estimated)~35.7
- #1Gemini 4 Carbon59.4
- #2Claude Opus 5.557.6
- #36DeepSeek V4 Pro (0813)36.0
- ~#37Qwen3.8-Omni-FlashEstimated35.7
- #37Qwen3.8 27B33.7
No published score — estimated from related benchmarks