Gemini 3.7 FlashvsGPT-5 mini

Gemini 3.7 Flash
GPT-5 mini
Specifications
Context window
1M
API pricing
Input price
$0.75$0.25
Output price
$3.75$2.00
Cached input price
$0.075$0.025
Cheapest input
$0.25Azure
Cheapest output
$2.00Azure
Benchmarks
ProgramBench
0%0%
Benchmarks
BullshitBench v2
35%
DeepSWE 1.1
65.3%
FrontierCode v1.1 (Main) · main split
43.6%
Terminal-Bench 4.0
11.21%
Terminal-Bench 3.0
14.9%
Terminal-Bench 2.1
85.8%
Humanity's Last Exam (Verified)
53.6%
BioMysteryBench · hard
43.5%
BioMysteryBench · human solved
87.1%
LAB-Bench 2
82.1%
OSWorld 2.0
38.1%
Agent's Last Exam · pass@1
26.3%
AutomationBench
30.4%
Harvey's Legal Agent Benchmark
8.8%
AA Intelligence Index
56
GDPval-AA v2
1525
CharXiv Reasoning
84.5%
GDP.PDF
34%
LVBench
85.4%
MRCR v2 (8-needle) · 128k average
97%
MRCR v2 (8-needle) · 1M pointwise
62.5%
threejseval
1526
Overview
CompanyGoogleOpenAI
Release dateAug 13 2026Aug 7 2025
AccessProprietaryProprietary

Other comparisons

Gemini 3.7 FlashvsClaude Fable 5.1GPT-5 minivsClaude Fable 5.1Gemini 3.7 FlashvsMuse Spark 1.3GPT-5 minivsMuse Spark 1.3Gemini 3.7 FlashvsGrok 4.6GPT-5 minivsGrok 4.6Gemini 3.7 FlashvsDeepSeek-V4.1-FlashGPT-5 minivsDeepSeek-V4.1-FlashGemini 3.7 FlashvsMistral Medium 3.5GPT-5 minivsMistral Medium 3.5Gemini 3.7 FlashvsKimi K3GPT-5 minivsKimi K3

Frequently asked questions

Gemini 3.7 Flash and GPT-5 mini are evenly matched across the 1 benchmark they both report (ProgramBench). GPT-5 mini is cheaper on both input and output: $0.25 vs $0.75 per million input tokens, and $2.00 vs $3.75 per million output tokens. GPT-5 mini shipped 371 days before Gemini 3.7 Flash, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On ProgramBench, both models score 0%.