Skip to content
Model Pareto

Gemini 3.8 Flash

Google DeepMindProprietaryblog.google ↗
Compare with nearest rivalsCompare with…
Input
$0.75/M tok
Output
$3.75/M tok
Blended
$1.50/M tok · 3:1
Speed
291tok/s
Context
1Mtokens

Introductory price through 2026-12-31; regular price $1.50/$7.50.

Rankings

Benchmark scores

~ italic, dashed = no published score yet, estimated from related benchmarks.

Coding

SWE-bench VerifiedEstimated
~#3 of 14 (estimated)~84.8%
  1. #1Claude Opus 596.0%
  2. #2Claude Sonnet 585.2%
  3. ~#3Gemini 3.8 FlashEstimated84.8%
  4. #3Gemini 3.1 Pro80.6%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#7 of 19 (estimated)~65.6%
  1. #1Claude Opus 5.589.9%
  2. #2Claude Sonnet 5.581.3%
  3. #6Hy4 preview65.7%
  4. ~#7Gemini 3.8 FlashEstimated65.6%
  5. #7GPT-5.6 Terra63.4%
No published score — estimated from related benchmarks
LiveCodeBenchEstimated
~#3 of 20 (estimated)~91.7%
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #2Qwen3.8 Flash-Next91.9%
  3. ~#3Gemini 3.8 FlashEstimated91.7%
  4. #3Qwen3.8 27B90.3%
No published score — estimated from related benchmarks

Writing & chat

IFBenchEstimated
~#3 of 126 (estimated)~82.6%
  1. #1MiniMax-M382.9%
  2. #2Qwen3.8 2.4T A95B82.8%
  3. ~#3Gemini 3.8 FlashEstimated82.6%
  4. #3Qwen3.8-Omni-Flash81.5%
No published score — estimated from related benchmarks
MMMLUEstimated
~#2 of 5 (estimated)~92.0%
  1. #1Gemini 3.1 Pro92.6%
  2. ~#2Gemini 3.8 FlashEstimated92.0%
  3. #2Gemma 4 31B88.4%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Few votesVerified
#4 of 531483 Elo
  1. #1Claude Opus 5.51501
  2. #2Claude Fable 5.1Few votes1496
  3. #4Claude Opus 51483
  4. #4Gemini 3.8 FlashFew votes1483
  5. #6Gemini 3.1 Pro1480
lmarena.ai · 2026-09-25
LMArena Text (Elo)Verified
#3 of 531493 Elo
  1. #1Claude Opus 5.51509
  2. #2Claude Fable 5.11501
  3. #3Claude Opus 51493
  4. #3Gemini 3.8 Flash1493
  5. #3Muse Spark 1.31493
lmarena.ai · 2026-09-24

Vision

MMMUEstimated
~#2 of 3 (estimated)~71.3%
  1. #1Claude Haiku 4.573.2%
  2. ~#2Gemini 3.8 FlashEstimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#4 of 8 (estimated)~89.9%
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
  3. #2Qwen3.8 27B91.1%
  4. ~#4Gemini 3.8 FlashEstimated89.9%
  5. #4Gemini 3.1 Pro85.3%
No published score — estimated from related benchmarks

Hard reasoning

AIME (latest)Estimated
~#2 of 25 (estimated)~96.8%
  1. #1Inkling97.1%
  2. ~#2Gemini 3.8 FlashEstimated96.8%
  3. #2Muse Glimmer94.7%
No published score — estimated from related benchmarks

Agents

τ²-bench (Telecom)Estimated
~#2 of 116 (estimated)~98.3%
  1. #1Step 3.7 Flash98.5%
  2. ~#2Gemini 3.8 FlashEstimated98.3%
  3. #2Gemini 3.1 Pro95.6%
No published score — estimated from related benchmarks
OSWorld-VerifiedEstimated
~#4 of 12 (estimated)~82.0%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. #3Nex-N2.5-Pro82.2%
  4. ~#4Gemini 3.8 FlashEstimated82.0%
  5. #4MiMo-V2.6-Pro82.0%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~54.1%
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. ~#3Gemini 3.8 FlashEstimated54.1%
  4. #3GPT-5.6 Terra50.2%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#7 of 18 (estimated)~88.0%
  1. #1Atria Dawn Preview92.5%
  2. #2GPT-6 Astra91.5%
  3. #6Step 5 Preview88.7%
  4. ~#7Gemini 3.8 FlashEstimated88.0%
  5. #7GPT-5.6 Terra87.5%
No published score — estimated from related benchmarks