ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Gemini 3.7 FlashvsGPT-5 mini

Gemini 3.7 Flash leads 5 of 5 shared benchmarks. GPT-5 mini is 2x cheaper per token. Gemini 3.7 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
5 – 0
Gemini 3.7 Flash leads
Cheaper per token
GPT-5 mini
2x cheaper, input + output
Larger context
Gemini 3.7 Flash
1.0M tokens
Provider uptime (30d)
100% · 94.2446%
Google · OpenAI
Gemini 3.7 Flash
Google · released 2026-08-13
textvisionaudio
Context
1.0M
Max out
66K
Input /1M
$0.75
Output /1M
$3.75
Cached /1M
$0.075
Scores
14 · 6 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 3.7 FlashGPT-5 miniΔEdge
Reported by both · 5
GPQA Diamond94.8% epoch81.6% +13.2 ptGemini 3.7 Flash
FrontierMath Tier 4 v2 (Epoch AI run)36.6% epoch12.2% epoch+24.4 ptGemini 3.7 Flash
FrontierMath Tiers 1-3 v2 (Epoch AI run)71.6% epoch46.7% epoch+24.9 ptGemini 3.7 Flash
OTIS Mock AIME 2024-2025 (Epoch AI run)97.2% epoch86.7% epoch+10.5 ptGemini 3.7 Flash
SimpleQA Verified69.2% epoch21.6% epoch+47.6 ptGemini 3.7 Flash
Only Gemini 3.7 Flash reports · 9
Artificial Analysis Intelligence Index56 not reported
Code Arena1588 not reported
DeepSWE v1.165.3% not reported
FrontierCode 1.143.6% not reported
GDPVal-AA v21525 not reported
HLE-Verified53.6% not reported
OSWorld-2.047.9% not reported
Terminal-bench 2.185.8% not reported
Terminal-bench 3.014.9% not reported
Only GPT-5 mini reports · 3
SWE-bench Verifiednot reported71%
AIME 2025not reported87.5% matharena
SWE-bench Verified (Epoch AI run)not reported64.7% epoch
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 3.7 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 3.7 FlashGPT-5 miniEdge
Context window1.0M tokens400K tokensGemini 3.7 Flash
Max output66K tokens128K tokensGPT-5 mini
Input price / 1M$0.75 $0.25 GPT-5 mini
Output price / 1M$3.75 $2 GPT-5 mini
Cached input / 1M$0.075 $0.025 GPT-5 mini
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$4.5$2.25GPT-5 mini
Modalitiestext · vision · audiotext · visionGemini 3.7 Flash
Released2026-08-132025-08-07
Cited benchmark scores149
Reliability

Provider status

All providers
More matchups

Gemini 3.7 Flash vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Gemini 3.7 Flash and GPT-5 mini on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.