ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Gemini 3.5 FlashvsGPT-5 mini

Gemini 3.5 Flash leads 6 of 6 shared benchmarks. GPT-5 mini is 4.7x cheaper per token. Gemini 3.5 Flash has the larger context window (1.0M tokens).

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

Shared benchmarks
6 – 0
Gemini 3.5 Flash leads
Cheaper per token
GPT-5 mini
4.7x cheaper, input + output
Larger context
Gemini 3.5 Flash
1.0M tokens
Provider uptime (30d)
100% · 94.2446%
Google · OpenAI
Gemini 3.5 Flash
Google · released 2026-05-19
textvisionaudio
Context
1.0M
Max out
66K
Input /1M
$1.5
Output /1M
$9
Cached /1M
$0.15
Scores
15 · 9 core
GPT-5 mini
OpenAI · released 2025-08-07
textvision
Context
400K
Max out
128K
Input /1M
$0.25
Output /1M
$2
Cached /1M
$0.025
Scores
9 · 8 core
Quality

Benchmark matrix

BenchmarkGemini 3.5 FlashGPT-5 miniΔEdge
Reported by both · 6
GPQA Diamond92.8% epoch81.6% +11.2 ptGemini 3.5 Flash
FrontierMath Tier 4 v2 (Epoch AI run)26.8% epoch12.2% epoch+14.6 ptGemini 3.5 Flash
FrontierMath Tiers 1-3 v2 (Epoch AI run)62.8% epoch46.7% epoch+16.1 ptGemini 3.5 Flash
OTIS Mock AIME 2024-2025 (Epoch AI run)95.6% epoch86.7% epoch+8.9 ptGemini 3.5 Flash
SimpleQA Verified66.2% epoch21.6% epoch+44.6 ptGemini 3.5 Flash
SWE-bench Verified (Epoch AI run)79.3% epoch64.7% epoch+14.6 ptGemini 3.5 Flash
Only Gemini 3.5 Flash reports · 9
AIME 202695% matharenanot reported
ARC-AGI-272.1% not reported
GDPVal-AA1656 not reported
Humanity's Last Exam (full set, text + MM)40.2% not reported
MCP Atlas83.6% not reported
MMMU-Pro83.6% not reported
OSWorld-Verified78.4% not reported
SWE-Bench Pro (Public)55.1% not reported
Terminal-bench 2.176.2% not reported
Only GPT-5 mini reports · 2
SWE-bench Verifiednot reported71%
AIME 2025not reported87.5% matharena
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 minus GPT-5 mini 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 FlashGPT-5 miniEdge
Context window1.0M tokens400K tokensGemini 3.5 Flash
Max output66K tokens128K tokensGPT-5 mini
Input price / 1M$1.5 $0.25 GPT-5 mini
Output price / 1M$9 $2 GPT-5 mini
Cached input / 1M$0.15 $0.025 GPT-5 mini
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$10.5$2.25GPT-5 mini
Modalitiestext · vision · audiotext · visionGemini 3.5 Flash
Released2026-05-192025-08-07
Cited benchmark scores159
Reliability

Provider status

All providers
More matchups

Gemini 3.5 Flash vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Gemini 3.5 Flash and GPT-5 mini on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.