Sign Up

Gemini 3.5 Flash Lite

Google DeepMind
Announcement
Gemini 3.5 Flash Lite launch post cover

Cost/1M tokens

input
$0.30
cached
$0.03
output
$2.50
cache write
$0.0833
Context
1Mtokens
Released
3mo 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 #75

  1. 1467
    MiMo-V2.5-ProSimilar price
  2. 1455
    GPT-5.1Nearby rank
  3. 1455
    Qwen3.7 PlusNearby rank
  4. 1455
    Gemini 3.5 Flash Lite
  5. 1454
    Hy3Nearby rank
  6. 1453
    GPT-5.6 LunaNearby rank
  7. 1433
    Gemini 3.1 Flash Lite PreviewEarlier version
  8. 1424
    GLM 4.6Similar price
  9. 1409
    Qwen3.5-27BSimilar price
  10. 1335
    Nova 2 LiteSimilar price

+22 vs Gemini 3.1 Flash Lite Preview (earlier version) · Ahead of 3 of 4 similarly priced models

Arena WebDev

Best Arena rating per model · Higher is better

Arena #91

  1. 1479
    MiMo-V2.5-ProSimilar price
  2. 1437
    Beam 1.0 501B A23BNearby rank
  3. 1436
    Kimi K2.5Nearby rank
  4. 1435
    Gemini 3.5 Flash Lite
  5. 1435
    GLM 5Nearby rank
  6. 1435
    GLM 4.7Nearby rank
  7. 1357
    Qwen3.5-27BSimilar price
  8. 1342
    GLM 4.6Similar price
  9. 1256
    Gemini 3.1 Flash Lite PreviewEarlier version
  10. 1196
    Devstral 2 2512Similar price

+180 vs Gemini 3.1 Flash Lite Preview (earlier version) · Ahead of 3 of 4 similarly priced models

Arena Vision

Best Arena rating per model · Higher is better

Arena #38

  1. 1272
    GLM 5.3 FlashNearby rank
  2. 1266
    GPT-5.6 TerraNearby rank
  3. 1266
    Gemini 3.5 Flash Lite
  4. 1265
    Gemma 4 31BNearby rank
  5. 1265
    Kimi K2.6Nearby rank
  6. 1235
    Gemini 3.1 Flash Lite PreviewEarlier version
  7. 1234
    MiMo-V2.5Similar price
  8. 1160
    Mistral Medium 3.1Similar price
  9. 1153
    GLM 4.5VSimilar price
  10. 1121
    Qwen2.5 VL 72B InstructSimilar price

+31 vs Gemini 3.1 Flash Lite Preview (earlier version) · Ahead of 4 of 4 similarly priced models

Arena Search

Best Arena rating per model · Higher is better

Not ranked on Arena Search yet

Arena Document

Best Arena rating per model · Higher is better

Not ranked on Arena Document yet

Agent Arena

Best IPS score per model · Higher is better

Not ranked on Agent Arena yet

ARC-AGI-2

Best score per model · Higher is better

#56 of 85

  1. 40.1%
    Inkling SmallSimilar price
  2. 13.6%
    Claude Sonnet 4.5Nearby rank
  3. 11.8%
    Kimi K2.5Similar price
  4. 10.3%
    Gemini 3.5 Flash Lite
  5. 9.9%
    GPT-5Nearby rank
  6. 8.6%
    Claude Opus 4Nearby rank
  7. 1.1%
    R1 0528Similar price
  8. 0.0%
    GPT-4.1 MiniSimilar price

Ahead of 2 of 4 similarly priced models

FrontierMath-Tier-4-v2-Private

Best score per model · Higher is better

#71 of 72

  1. 26.8%
    Mistral Large 4Similar price
  2. 17.1%
    Inkling SmallSimilar price
  3. 12.2%
    GPT-5 MiniSimilar price
  4. 2.4%
    DeepSeek V4 Pro 0423Similar price
  5. 2.4%
    GPT-5.5 InstantNearby rank
  6. 0.0%
    Gemini 2.5 ProNearby rank
  7. 0.0%
    Gemini 3.5 Flash Lite

Ahead of 0 of 4 similarly priced models

FrontierMath-Tiers-1-3-v2-Private

Best score per model · Higher is better

#72 of 87

  1. 58.6%
    Mistral Large 4Similar price
  2. 45.3%
    DeepSeek V4 Pro 0423Similar price
  3. 38.2%
    Qwen3.6 PlusSimilar price
  4. 27.7%
    Gemini 3.1 Flash LitePredecessor
  5. 26.3%
    GPT-5.5 InstantNearby rank
  6. 26.0%
    Gemini 3.5 Flash Lite
  7. 24.6%
    Gemini 2.5 ProNearby rank
  8. 23.9%
    Claude Sonnet 4.5Nearby rank
  9. 6.7%
    GPT-4.1 MiniSimilar price

-1.8 pts vs Gemini 3.1 Flash Lite (predecessor) · Ahead of 1 of 4 similarly priced models

GPQA diamond

Best score per model · Higher is better

#77 of 161

  1. 88.4%
    Qwen3.6 PlusSimilar price
  2. 83.5%
    Qwen3.5-35B-A3BNearby rank
  3. 83.4%
    DeepSeek ReasonerNearby rank
  4. 83.3%
    Gemini 3.5 Flash Lite
  5. 83.3%
    Qwen3.6 FlashNearby rank
  6. 83.3%
    GLM 4.7Similar price
  7. 81.8%
    Gemini 3.1 Flash LitePredecessor
  8. 76.3%
    R1 0528Similar price
  9. 59.5%
    Mistral Medium 3Similar price

+1.5 pts vs Gemini 3.1 Flash Lite (predecessor) · Ahead of 2 of 4 similarly priced models

OTIS Mock AIME 2024-2025

Best score per model · Higher is better

#91 of 158

  1. 93.3%
    Qwen3.6 PlusSimilar price
  2. 83.3%
    GLM 4.7Similar price
  3. 80.0%
    Gemini 3.1 Flash LitePredecessor
  4. 73.3%
    Gemma 4 31BNearby rank
  5. 71.1%
    Claude Sonnet 4Nearby rank
  6. 71.1%
    Gemini 3.5 Flash Lite
  7. 71.1%
    MiniMax M3Nearby rank
  8. 70.8%
    Gemini 2.5 Flash Preview 05-20Nearby rank
  9. 66.4%
    R1 0528Similar price
  10. 32.2%
    Mistral Medium 3Similar price

-8.9 pts vs Gemini 3.1 Flash Lite (predecessor) · Ahead of 2 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.

Reasoning effort

ARC-AGI-2

Score by reasoning effort · Higher is better

GPQA diamond

Score by reasoning effort · Higher is better

OTIS Mock AIME 2024-2025

Score by reasoning effort · Higher is better

All published scores

  • Arena TextArena #751455

    +22 vs Gemini 3.1 Flash Lite Preview (earlier version)

    • default145595% CI 1450 to 1459 · 35,114 votes
    Source:Arena Text leaderboard, 2026-11-09
  • Arena WebDevArena #911435

    +180 vs Gemini 3.1 Flash Lite Preview (earlier version)

    • default143595% CI 1394 to 1476 · 233 votes
    Source:Arena WebDev leaderboard, 2026-11-10
  • Arena VisionArena #381266

    +31 vs Gemini 3.1 Flash Lite Preview (earlier version)

    • default126695% CI 1258 to 1273 · 10,800 votes
    Source:Arena Vision leaderboard, 2026-11-09
  • ARC-AGI-2#56 of 8510.3%
    • minimal0.8%
    • low1.5%
    • medium5.3%
    • high10.3%
    Source:External evaluation via Epoch AIOriginal-source terms apply
  • FrontierMath-Tier-4-v2-Private#71 of 720.0%
    • high0.0%
    Source:Epoch AI evaluation
  • FrontierMath-Tiers-1-3-v2-Private#72 of 8726.0%

    -1.8 pts vs Gemini 3.1 Flash Lite (predecessor)

    • high26.0%
    Source:Epoch AI evaluation
  • GPQA diamond#77 of 16183.3%

    +1.5 pts vs Gemini 3.1 Flash Lite (predecessor)

    • minimal74.2%
    • low75.8%
    • high83.3%
    Source:Epoch AI evaluation
  • OTIS Mock AIME 2024-2025#91 of 15871.1%

    -8.9 pts vs Gemini 3.1 Flash Lite (predecessor)

    • minimal51.1%
    • low60.0%
    • high71.1%
    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.