Gemini 3.8 Flash
- Input
- $0.75/M tok
- Output
- $3.75/M tok
- Blended
- $1.50/M tok · 3:1
- Speed
- 129tok/s
- Context
- 1Mtokens
- Cost per task
- $7.8/task · AA
Introductory price through 2026-12-31; regular price $1.50/$7.50.
Rankings
Coding
Verified#49 / 137rank by quality58.4±4.5quality / 1004/7 benchmarks measuredWriting & chat
Verified#21 / 162rank by quality74.2±4.6quality / 1003/5 benchmarks measuredSpeed frontierVision
Mixed#10 / 98rank by quality81.7±4.1quality / 1004/6 benchmarks measuredPrice frontierSpeed frontierHard reasoning
Verified#20 / 218rank by quality77.4±3.7quality / 1003/4 benchmarks measuredSpeed frontierAgents
Verified#21 / 187rank by quality74.7±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)~84.9%
- #1Claude Opus 596.0%
- #2Claude Sonnet 585.2%
- ~#3Gemini 3.8 FlashEstimated84.9%
- #3Beam 1.0 501B A23B81.6%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#7 of 24 (estimated)~66.7%
- #1Claude Fable 5.293.0%
- #2Claude Opus 5.589.9%
- #6Intern-S2-397B68.5%
- ~#7Gemini 3.8 FlashEstimated66.7%
- #7Beam 1.0 501B A23B66.1%
No published score — estimated from related benchmarks
DeepSWE v1.1Verified
#20 of 4565.8%
- #1Gemini 4 Argon78.8%
- #2DeepSeek V4.1 Flash 101777.0%
- #19GPT-5.567.0%
- #20Gemini 3.8 Flash65.8%
- #21Grok 4.664.9%
artificialanalysis.ai · 2026-09-24
Terminal-Bench 4.0Verified
#31 of 10119.7%
- #1Kimi K3.1 Pro67.2%
- #2Claude Sonnet 5.563.6%
- #30SWE-2 Flash20.0%
- #31Gemini 3.8 Flash19.7%
- #32Grok 4.617.2%
artificialanalysis.ai · 2026-09-24
LiveCodeBenchEstimated
~#10 of 28 (estimated)~85.3%
- #1Qwen3.8-Omni-Flash92.6%
- #2Qwen3.8 Flash-Next91.9%
- #9Nemotron 3.5 Super VL NVFP487.4%
- ~#10Gemini 3.8 FlashEstimated85.3%
- #10Ternary Bonsai 27B82.8%
No published score — estimated from related benchmarks
SciCodeVerified
#20 of 11856.6%
- #1Claude Fable 5.267.7%
- #2Claude Opus 5.566.9%
- #19Grok 4.757.4%
- #20Gemini 3.8 Flash56.6%
- #21GPT-6 Astra56.5%
artificialanalysis.ai · 2026-09-24
Writing & chat
IFBenchEstimated
~#18 of 140 (estimated)~77.2%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #17DeepSeek V4.1 Flash NVFP477.3%
- ~#18Gemini 3.8 FlashEstimated77.2%
- #18Gemini 3.1 Pro77.1%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Few votesVerified
#4 of 561486 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #3Claude Fable 5.1Few votes1496
- #4Gemini 3.8 FlashFew votes1486
- #5Muse Spark 1.3Few votes1484
lmarena.ai · 2026-10-08
LMArena Text (Elo)Verified
#4 of 561497 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #3Claude Fable 5.11501
- #4Gemini 3.8 Flash1497
- #5Muse Spark 1.31493
lmarena.ai · 2026-10-08
#15 of 251748 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #14Claude Sonnet 51794
- #15Gemini 3.8 Flash1748
- #16Nemotron 3 Ultra1692
eqbench.com · 2026-09-24
Vision
MMMU-ProVerified
#4 of 8785.6%
- #1Claude Opus 5.587.7%
- #2GPT-6 Astra86.9%
- #3GPT-6.1 Sol86.0%
- #4Gemini 3.8 Flash85.6%
- #5Claude Opus 584.7%
artificialanalysis.ai · 2026-09-24
OmniDocBench v1.5Estimated
~#4 of 8 (estimated)~89.8%
- #1MiniMax-M391.6%
- #2Kimi K391.1%
- #2Qwen3.8 27B91.1%
- ~#4Gemini 3.8 FlashEstimated89.8%
- #4Gemini 3.1 Pro85.3%
No published score — estimated from related benchmarks
GDP.pdf (AA)Verified
#16 of 4721.0%
- #1Muse Wonder Full32.6%
- #2GPT-6 Astra31.0%
- #15GPT-5.521.2%
- #16Gemini 3.8 Flash21.0%
- #17Claude Haiku 5.520.8%
artificialanalysis.ai · 2026-09-24
ChartographyVerified
#7 of 2440.9%
- #1Claude Fable 5.273.4%
- #2GPT-6 Astra71.0%
- #6Claude Fable 5.146.2%
- #7Gemini 3.8 Flash40.9%
- #8GPT-5.6 Terra34.0%
surgehq.ai · 2026-09-24
Hard reasoning
Humanity's Last ExamVerified
#16 of 19847.8%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #15GPT-6 Sol47.9%
- #16Gemini 3.8 Flash47.8%
- #17Gemini 3.1 Pro47.0%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#4 of 34 (estimated)~96.7%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #3Inkling97.1%
- ~#4Gemini 3.8 FlashEstimated96.7%
- #4Ternary Bonsai 2 27B95.8%
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
~#5 of 15 (estimated)~81.5%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #4MiMo-V2.6-Pro82.0%
- ~#5Gemini 3.8 FlashEstimated81.5%
- #5Claude Sonnet 581.2%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~54.2%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#7 of 22 (estimated)~87.9%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #6Step 5 Preview88.7%
- ~#7Gemini 3.8 FlashEstimated87.9%
- #7GPT-5.6 Terra87.5%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Verified
#24 of 911436 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #23DeepSeek V4 Pro (0813)1441
- #24Gemini 3.8 Flash1436
- #25GPT-5.6 Terra1432
artificialanalysis.ai · 2026-10-10