ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Gemini 3.5 Flash-LitevsGemini 3.8 Flash

Gemini 3.8 Flash leads 4 of 4 shared benchmarks. Gemini 3.5 Flash-Lite is 1.6x cheaper per token. Both offer a 1.0M-token context window.

Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.

Shared benchmarks
0 – 4
Gemini 3.8 Flash leads
Cheaper per token
Gemini 3.5 Flash-Lite
1.6x cheaper, input + output
Larger context
Tie
both 1.0M tokens
Provider uptime (30d)
100%
Google
Gemini 3.5 Flash-Lite
Google · released 2026-07-21
textvisionaudio
Context
1.0M
Max out
66K
Input /1M
$0.3
Output /1M
$2.5
Cached /1M
$0.03
Scores
5 · 5 core
Gemini 3.8 Flash
Google · released 2026-09-02
textvisionaudio
Context
1.0M
Max out
66K
Input /1M
$0.75
Output /1M
$3.75
Cached /1M
$0.075
Scores
16 · 6 core
Quality

Benchmark matrix

BenchmarkGemini 3.5 Flash-LiteGemini 3.8 FlashΔEdge
Reported by both · 4
GPQA Diamond83.3% epoch95.3% -12 ptGemini 3.8 Flash
FrontierMath Tier 4 v2 (Epoch AI run)0% epoch22% epoch-22 ptGemini 3.8 Flash
FrontierMath Tiers 1-3 v2 (Epoch AI run)26% epoch68.4% epoch-42.4 ptGemini 3.8 Flash
OTIS Mock AIME 2024-2025 (Epoch AI run)71.1% epoch98.9% epoch-27.8 ptGemini 3.8 Flash
Only Gemini 3.5 Flash-Lite reports · 1
LMArena Elo1435.5 not reported
Only Gemini 3.8 Flash reports · 11
CharXiv Reasoning (no tools)not reported86.2%
DeepSWE v1.1not reported73.7%
GDPVal-AA v2not reported1545
Harvey's Legal Agent Benchmarknot reported10%
HLE-Verifiednot reported54.9%
LABBench2not reported86.2%
OSWorld-2.0not reported59%
SimpleQA Verifiednot reported69.7% epoch
Terminal-bench 2.1not reported89.4%
Terminal-bench 4.0not reported19.1%
Vals Finance Agent v2not reported61.4%
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Gemini 3.5 Flash-Lite minus Gemini 3.8 Flash in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing

Side by side

SpecGemini 3.5 Flash-LiteGemini 3.8 FlashEdge
Context window1.0M tokens1.0M tokensTie
Max output66K tokens66K tokensTie
Input price / 1M$0.3 $0.75 Gemini 3.5 Flash-Lite
Output price / 1M$2.5 $3.75 Gemini 3.5 Flash-Lite
Cached input / 1M$0.03 $0.075 Gemini 3.5 Flash-Lite
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$2.8$4.5Gemini 3.5 Flash-Lite
Modalitiestext · vision · audiotext · vision · audioTie
Released2026-07-212026-09-02
Cited benchmark scores516
Reliability

Google status

All providers
More matchups

Gemini 3.5 Flash-Lite vs …

More matchups

Gemini 3.8 Flash vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Gemini 3.5 Flash-Lite and Gemini 3.8 Flash on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.