GPT-5.4 nanovsGrok 4.6

GPT-5.4 nano
Grok 4.6
API pricing
Input price
$0.20$2.00
Output price
$1.25$6.00
Cached input price
$0.02$0.50
Cheapest input
$0.20Azure$2.20Amazon Bedrock
Cheapest output
$1.25Azure$6.60Amazon Bedrock
Benchmarks
BullshitBench v2
14%66%
Benchmarks
DeepSWE 1.1
65.9%
FrontierCode v1.1 (Extended) · extended split
61.3%
APEX-SWE
56.4%
Next.js Evals
71%
Terminal-Bench 4.0
20.3%
Terminal-Bench 3.0
26%
APEX-Agents
57.5%
Humanity's Last Exam · with tools
37.7%
OSWorld-Verified
39%
Harvey's Legal Agent Benchmark
15.8%
AA Intelligence Index
61
GDPval-AA v2
1753
AA-Briefcase
1577
threejseval
1528
Overview
CompanyOpenAISpaceXAI
Release dateMar 17 2026Aug 12 2026
AccessProprietaryProprietary

Other comparisons

GPT-5.4 nanovsClaude Fable 5.1Grok 4.6vsClaude Fable 5.1GPT-5.4 nanovsGemini 3.8 FlashGrok 4.6vsGemini 3.8 FlashGPT-5.4 nanovsMuse Spark 1.3Grok 4.6vsMuse Spark 1.3GPT-5.4 nanovsDeepSeek-V4.1-FlashGrok 4.6vsDeepSeek-V4.1-FlashGPT-5.4 nanovsMistral Medium 3.5Grok 4.6vsMistral Medium 3.5GPT-5.4 nanovsKimi K3Grok 4.6vsKimi K3

Frequently asked questions

Grok 4.6 leads GPT-5.4 nano on 1 of the 1 benchmark they both report (BullshitBench v2). GPT-5.4 nano is cheaper on both input and output: $0.20 vs $2.00 per million input tokens, and $1.25 vs $6.00 per million output tokens. Figures are base-tier rates. GPT-5.4 nano shipped 148 days before Grok 4.6, 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 BullshitBench v2, Grok 4.6 leads at 66% vs GPT-5.4 nano at 14%.