Gemini 3.5 Flash-Lite
- Input
- $0.30/M tok
- Output
- $2.50/M tok
- Blended
- $0.85/M tok · 3:1
- Speed
- 351tok/s
- Context
- 1Mtokens
- Cost per task
- ~$1.1/taskest.
Rankings
Coding
Mixed#92 / 137rank by quality35.8±6.7quality / 1003/7 benchmarks measuredSpeed frontierWriting & chat
Verified#61 / 162rank by quality57.6±4.3quality / 1003/5 benchmarks measuredSpeed frontierVision
Mixed#58 / 98rank by quality49.2±4.1quality / 1004/6 benchmarks measuredSpeed frontierHard reasoning
Verified#95 / 218rank by quality48.8±3.7quality / 1003/4 benchmarks measuredSpeed frontierAgents
Mixed#70 / 187rank by quality40.2±4.7quality / 1004/7 benchmarks measuredSpeed frontier
Benchmark scores
~ italic, dashed = no published score yet, estimated from related benchmarks.
Coding
SWE-bench VerifiedEstimated
~#14 of 21 (estimated)~72.5%
- #1Claude Opus 596.0%
- #2Claude Sonnet 585.2%
- #13Claude Haiku 4.573.3%
- ~#14Gemini 3.5 Flash-LiteEstimated72.5%
- #14Nemotron 3.5 Super VL71.1%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Lab-reported
#18 of 2354.2%
- #1Claude Fable 5.293.0%
- #2Claude Opus 5.589.9%
- #18Gemini 3.1 Pro54.2%
- #18Gemini 3.5 Flash-Lite54.2%
- #20Nemotron 3.5 Super VL51.8%
deepmind.google · 2026-07-21
DeepSWE v1.1Estimated
~#38 of 46 (estimated)~44.8%
- #1Gemini 4 Argon78.8%
- #2DeepSeek V4.1 Flash 101777.0%
- #37Qwen3.8 Max (0902)51.0%
- ~#38Gemini 3.5 Flash-LiteEstimated44.8%
- #38Ripple-65B Preview44.3%
No published score — estimated from related benchmarks
Terminal-Bench 4.0Verified
#46 of 1011.0%
- #1Kimi K3.1 Pro67.2%
- #2Claude Sonnet 5.563.6%
- #45K2 Horizon 375B A23B1.5%
- #46Gemini 3.5 Flash-Lite1.0%
- #46Inkling1.0%
artificialanalysis.ai · 2026-09-24
LiveCodeBenchEstimated
~#16 of 28 (estimated)~63.8%
- #1Qwen3.8-Omni-Flash92.6%
- #2Qwen3.8 Flash-Next91.9%
- #15Mistral Small 464.0%
- ~#16Gemini 3.5 Flash-LiteEstimated63.8%
- #16Claude Haiku 4.561.5%
No published score — estimated from related benchmarks
SciCodeVerified
#75 of 11841.3%
- #1Claude Fable 5.267.7%
- #2Claude Opus 5.566.9%
- #73Ling 3.0 Flash42.0%
- #75Gemini 3.5 Flash-Lite41.3%
- #76A.X-K241.0%
artificialanalysis.ai · 2026-09-24
AA Coding Agent IndexEstimated
~#24 of 26 (estimated)~31.3
- #1Claude Opus 5.561.7
- #2Claude Opus 559.7
- #23Gemini 3.8 Flash33.3
- ~#24Gemini 3.5 Flash-LiteEstimated31.3
- #24GPT-6 Luna31.1
No published score — estimated from related benchmarks
Writing & chat
IFBenchEstimated
~#56 of 140 (estimated)~60.8%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #55K2 Think V262.8%
- ~#56Gemini 3.5 Flash-LiteEstimated60.8%
- #56GLM-5.3 Flash NVFP460.5%
No published score — estimated from related benchmarks
MMMLUEstimated
~#3 of 5 (estimated)~87.3%
- #1Gemini 3.1 Pro92.6%
- #2Gemma 4 31B88.4%
- ~#3Gemini 3.5 Flash-LiteEstimated87.3%
- #3Claude Haiku 4.583.0%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Verified
#21 of 561445 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #19Grok 4.61447
- #21Gemini 3.5 Flash-Lite1445
- #22GPT-6 Sol1444
lmarena.ai · 2026-09-24
#19 of 251559 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #18Inkling1611
- #19Gemini 3.5 Flash-Lite1559
- #20DeepSeek V4.1 Flash1540
eqbench.com · 2026-09-24
Vision
MMMU-ProVerified
#20 of 8779.0%
- #1Claude Opus 5.587.7%
- #2GPT-6 Astra86.9%
- #19MiniMax-M3.1-Flash79.1%
- #20Gemini 3.5 Flash-Lite79.0%
- #20Ling-3.0-flash-VL79.0%
artificialanalysis.ai · 2026-09-24
OmniDocBench v1.5Estimated
~#5 of 8 (estimated)~82.1%
- #1MiniMax-M391.6%
- #2Kimi K391.1%
- #4Gemini 3.1 Pro85.3%
- ~#5Gemini 3.5 Flash-LiteEstimated82.1%
- #5Claude Haiku 4.579.6%
No published score — estimated from related benchmarks
GDP.pdf (AA)Verified
#26 of 4713.6%
- #1Muse Wonder Full32.6%
- #2GPT-6 Astra31.0%
- #25Step 5 Preview14.8%
- #26Gemini 3.5 Flash-Lite13.6%
- #27GPT-5.4 mini13.4%
artificialanalysis.ai · 2026-09-24
ChartographyVerified
#22 of 2410.2%
- #1Claude Fable 5.273.4%
- #2GPT-6 Astra71.0%
- #21DeepSeek V4.1 Flash11.6%
- #22Gemini 3.5 Flash-Lite10.2%
- #23Inkling10.0%
surgehq.ai · 2026-09-24
Hard reasoning
GPQA DiamondVerified
#64 of 19283.8%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #63Qwen3.6 35B A3B84.1%
- #64Gemini 3.5 Flash-Lite83.8%
- #65Muse Glimmer83.5%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#84 of 19818.8%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #83Gemma 4 26B A4B19.3%
- #84Gemini 3.5 Flash-Lite18.8%
- #85Quasar 438B18.7%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#21 of 34 (estimated)~83.0%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #20Claude Haiku 4.583.7%
- ~#21Gemini 3.5 Flash-LiteEstimated83.0%
- #21Magistral Small 1.280.3%
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Estimated
~#46 of 120 (estimated)~63.9%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #45Qwen3.5 0.8B65.2%
- ~#46Gemini 3.5 Flash-LiteEstimated63.9%
- #46HyperNova 60B 260563.2%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~last of 5 (estimated)below measured range (<47.5%)
No published score — estimated from related benchmarks
BrowseCompEstimated
~#19 of 22 (estimated)~68.9%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #18Nemotron 3.5 Bolt 74B-A9B70.0%
- ~#19Gemini 3.5 Flash-LiteEstimated68.9%
- #19Mistral Medium 3.548.6%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Verified
#45 of 91970 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #44MiMo-V2.5986
- #45Gemini 3.5 Flash-Lite970
- #46GPT-5.4 nano937
artificialanalysis.ai · 2026-09-24