Back

OpenAI

GPT-5.4 nano

ReasoningClosed weightsModels.dev
Intelligence
20.7
Rank 236 of 744 measured models
Coding
56.1
Rank 101 of 298 measured models
Output speed
166 t/s
Rank 65 of 403 measured models
Price/1M
$0.463
Rank 268 of 659 measured models
Context window
400K
Rank 357 of 1199 measured models
Cost per task
$0.183
Rank 69 of 193 measured models

GPT-5.4 nano (Xhigh) scores 20.7 on the Artificial Analysis Intelligence Index, ranking 236th of 744 measured models. The closest models on this index are MiniMax-M2.1 (20.9), GPT-5 Mini (batch) (20.6), and K2 Horizon 7B (20.6). At $0.463 per million tokens (3:1 input/output blended price), it is cheaper than MiniMax-M2.1 ($0.525). With an output speed of 166 t/s, it is faster than MiniMax-M2.1 (59.3 t/s).

Artificial Analysis Indices
Extra high
Intelligence20.7
Rank 236 of 744 measured models
Coding56.1
Rank 101 of 298 measured models
Agentic16.0
Rank 107 of 189 measured models
Reasoning levels
Each point is a reasoning level of this model: more reasoning often raises the score but costs more. Select a point to open that level.
Intelligence Indexmost efficient ↗Price / 1M tokens
Capability indexes
Performance in specific industries, measured by Artificial Analysis
Finance & Accounting20.7
Rank 155 of 218 measured models
Strategy & Ops15.8
Rank 155 of 218 measured models
Legal22.1
Rank 157 of 218 measured models
Healthcare & Medical16.8
Rank 72 of 82 measured models
Engineering22.7
Rank 151 of 217 measured models
Economics30.3
Rank 153 of 225 measured models
Standard Benchmarks
GPQA Diamond81.7%
Rank 190 of 619 measured models
HLE28.3%
Rank 166 of 664 measured models
SciCode47.2%
Rank 130 of 231 measured models
IFBench75.9%
Rank 25 of 450 measured models
AA-LCR76.7%
Rank 139 of 575 measured models
TerminalBench Hard42.4%
Rank 46 of 432 measured models
Terminal-Bench 2.160.7%
Rank 102 of 244 measured models
Terminal-Bench v40.5%
Rank 136 of 218 measured models
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy