Gemini 2.5 Flash Preview 05 20 vs Gemini 3.8 Flash

Wins 0 of 5 benchmarks
$0.93 / task
Wins 0 of 5 benchmarks
Different efforts: thinking · medium
Humanity's Last Exam Humanity's Last Exam: Very hard expert questions across many fields, written to stump today’s models
Gemini 2.5 Flash Preview 05 20—
Gemini 3.8 Flash42.1
Terminal-Bench 4.0 Terminal-Bench 4.0 · source setting 2: Agents use a terminal to complete executable coding, system administration and research tasks in the 4.0 suite
Gemini 2.5 Flash Preview 05 20—
Gemini 3.8 Flash19.7
AutomationBench-AA AutomationBench-AA: Agents orchestrate SaaS workflows through APIs; objectives receive credit only when the task has no guardrail violation
Gemini 2.5 Flash Preview 05 20—
Gemini 3.8 Flash60.9
Arena Text · creative writing Arena Text · creative writing: Human pairwise preferences in the stated text vote pool
Gemini 2.5 Flash Preview 05 20—
Gemini 3.8 Flash · high1,487
MMMU-Pro (vision) MMMU-Pro (vision): College-level questions that require understanding images: charts, diagrams, photos
Gemini 2.5 Flash Preview 05 20—
Gemini 3.8 Flash84.2

Specs

SpecGemini 2.5 Flash Preview 05 20Gemini 3.8 Flash
Input, per 1M!$0.14!$0.75
Output, per 1M!$3.33!$3.75
Cost per task?—$0.93
Context1M1M
WeightsNot verifiedClosed
ReleasedMay 2025Sep 2026
See images✓✓
Read PDFs—✓
Hear audio—✓
Watch video—✓
Call toolsPartial✓
Force a tool call?Partial
Return strict JSONPartial✓
Search the web?✓
Run code?✓
Use a computer??

What breaks when you switch

Gemini 2.5 Flash Preview 05 20 → Gemini 3.8 Flash
Sampling parameters are ignored›

temperature, top_p and top_k are ignored now and will cause HTTP 400 in future generations; remove them from requests.

No minimal thinking level›

The minimal thinking level returns an error; avoid minimal.

Gemini 3.8 Flash → Gemini 2.5 Flash Preview 05 20
No PDF input