GPT-5.4 nanovsQwen3.7-Plus

GPT-5.4 nano
Qwen3.7-Plus
API pricing
Input price
$0.20$0.40
Output price
$1.25$1.60
Cached input price
$0.02
Cheapest input
$0.20Azure
Cheapest output
$1.25Azure
Benchmarks
Humanity's Last Exam · with tools
37.7%34.7%
OSWorld-Verified
39%73.3%
Benchmarks
BullshitBench v2
14%
SWE-Bench Verified
77.7%
LiveCodeBench
89.6%
Overview
CompanyOpenAIQwen
Release dateMar 17 2026Jun 1 2026
AccessProprietaryProprietary

Other comparisons

GPT-5.4 nanovsClaude Opus 5Qwen3.7-PlusvsClaude Opus 5GPT-5.4 nanovsGemini 3.7 FlashQwen3.7-PlusvsGemini 3.7 FlashGPT-5.4 nanovsMuse GlimmerQwen3.7-PlusvsMuse GlimmerGPT-5.4 nanovsGrok 4.6Qwen3.7-PlusvsGrok 4.6GPT-5.4 nanovsDeepSeek-V4-Pro-0813Qwen3.7-PlusvsDeepSeek-V4-Pro-0813GPT-5.4 nanovsMistral Medium 3.5Qwen3.7-PlusvsMistral Medium 3.5

Frequently asked questions

GPT-5.4 nano and Qwen3.7-Plus are evenly matched across the 2 benchmarks they both report (Humanity's Last Exam, OSWorld-Verified). GPT-5.4 nano is cheaper on both input and output: $0.20 vs $0.40 per million input tokens, and $1.25 vs $1.60 per million output tokens. Figures are base-tier rates. GPT-5.4 nano shipped 76 days before Qwen3.7-Plus, 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 Humanity's Last Exam · with tools, GPT-5.4 nano leads at 37.7% vs Qwen3.7-Plus at 34.7%. On OSWorld-Verified, Qwen3.7-Plus leads at 73.3% vs GPT-5.4 nano at 39%.

GPT-5.4 nano was released by OpenAI on Mar 17 2026.

Qwen3.7-Plus was released by Qwen on Jun 1 2026.

GPT-5.4 nano leads on Humanity's Last Exam · with tools — GPT-5.4 nano 37.7% vs Qwen3.7-Plus 34.7%.

GPT-5.4 nano is cheaper on both input and output: $0.20 vs $0.40 per million input tokens, and $1.25 vs $1.60 per million output tokens. Figures are base-tier rates. Rates are pay-as-you-go API prices verified on August 18, 2026.