GPT-5.4 nano Benchmark Scores & Performance

BenchLM is tracking GPT-5.4 nano by OpenAI. Some benchmark data is visible, but trusted coverage is not complete enough for ranking yet.

BenchLM is tracking GPT-5.4 nano, but this profile is currently excluded from the trusted leaderboard because its source-backed benchmark coverage is not complete enough yet. We keep the model metadata and any verified benchmark rows visible while the rest of the public eval record is re-checked.

GPT-5.4 nano is a proprietary model with a 400K token context window. It uses explicit chain-of-thought reasoning, which typically improves performance on math and complex reasoning tasks at the cost of higher latency and token usage.

GPT-5.4 nano sits inside the GPT-5.4 family alongside GPT-5.4, GPT-5.4 Pro, GPT-5.4 mini. BenchLM links it directly to GPT-5 nano as the earlier related model in that lineage. This profile currently has 1 trusted benchmark rows on BenchLM, but that is not enough for a leaderboard rank yet.

Creator

OpenAI

Source Type

Proprietary

Reasoning

Reasoning

Context Window

400K

Overall Score

Not ranked yet

Family & Lineage

Family

GPT-5.4

Nano

Canonical Entry

GPT-5.4

Related Earlier Model

GPT-5 nano

Rankings Overview

BenchLM is still verifying enough trusted benchmark coverage to place this model in the leaderboard. Category ranks will appear here once that source-backed coverage is complete.

Knowledge Benchmarks

GPQA
82.8%
HLE
37.7%
HLE w/o tools
24.3%

Coding Benchmarks

SWE-bench Pro
52.4%

Reasoning Benchmarks

MRCRv2
38.7%
MRCR v2 64K-128K
44.2%
MRCR v2 128K-256K
33.1%
Graphwalks BFS 128K
73.4%
Graphwalks Parents 128K
50.8%

Agentic Benchmarks

Terminal-Bench 2.0
46.3%
OSWorld-Verified
39%
MCP Atlas
56.1%
Toolathlon
35.5%
tau2-bench
92.5%

Multimodal & Grounded Benchmarks

MMMU-Pro
66.1%
MMMU-Pro w/ Python
69.5%
OmniDocBench 1.5
0.2419

Frequently Asked Questions

How does GPT-5.4 nano perform overall in AI benchmarks?

BenchLM is tracking GPT-5.4 nano, but trusted source-backed benchmark coverage is still coming soon. We currently list its creator, model type, and context window while we wait for verified public benchmark results.

Which sibling models are related to GPT-5.4 nano?

GPT-5.4 nano belongs to the GPT-5.4 family. Related variants on BenchLM include GPT-5.4, GPT-5.4 Pro, GPT-5.4 mini.

Does GPT-5.4 nano have full benchmark coverage on BenchLM?

GPT-5.4 nano is tracked on BenchLM, but its current source-backed benchmark coverage is not strong enough for a trusted leaderboard rank yet. We keep the model page live while we verify more public benchmark results.

What is the context window size of GPT-5.4 nano?

GPT-5.4 nano has a context window of 400K, which determines how much text it can process in a single interaction.

Last updated: March 17, 2026

Weekly LLM Updates

New model releases, benchmark scores, and leaderboard changes. Every Friday.

Free. Your signup is stored with a derived country code for compliance routing.