What are GPT-5.4 Pro's benchmark scores?

As of 24 Oct 2026, GPT-5.4 Pro scores 63.3 ±3.4 on the BenchLeader Index, top 100, strongest in knowledge (74) and weakest in instruction following (64). That rests on 6 independent benchmark results, and every score on this page links to its publisher.

How does GPT-5.4 Pro rank?

GPT-5.4 Pro is #68 of 785 ranked configurations on 24 Oct 2026 (top 100). 144 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.

How much does GPT-5.4 Pro cost per 1M tokens?

As of 24 Oct 2026, GPT-5.4 Pro costs $30.00 per 1M input tokens and $180.00 per 1M output tokens, $67.50 blended (three input tokens per output token).

Is GPT-5.4 Pro better than Qwen3.8 Max?

As of 24 Oct 2026, GPT-5.4 Pro and Qwen3.8 Max (max) are neck and neck on quality (63.3 vs 63.3 on the BenchLeader Index, inside the ±5.0 margin of error), and Qwen3.8 Max (max) costs 23× less, which makes it the better buy for most workloads. The head-to-head page has the benchmark-by-benchmark detail.

When was GPT-5.4 Pro released?

OpenAI released GPT-5.4 Pro on 4 Mar 2026. BenchLeader has results for it at 3 reasoning-effort settings.

OpenAIReasoning modelCompare with another model

GPT-5.4 Pro

Reasoning effort

GPT-5.4 Pro is an OpenAI proprietary reasoning model, released 4 Mar 2026. Its best configuration ranks #68 of 785 on the BenchLeader Index at 63.3 ±3.4, in the upper half. The ± is the point: 144 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in knowledge (74) and lowest in instruction following (64). At $67.50 per million tokens blended it is among the most expensive ranked models. Output speed of 7 tokens per second puts it in the slowest quarter, with a first token in 6.1 s. It has been measured at 3 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 7 Oct 2026.

Blended price: $67.50/M; $30.00 in · $180.00 out
Output speed: 7 tok/s; OpenRouter traffic, 7-day median; not yet measured by Artificial Analysis
First answer: 6.07 s
Context: 1.1M
Full answer: –
Cost per run: –
Released: 4 Mar 2026

How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.

Overall index63
Reasoning73
Knowledge74
Instruction following64
Multimodal70

Versions

OpenAI has shipped 4 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.

Model	Released	Index	Rank
GPT-5.5 Proxhigh	23 Apr 2026	65.3	#40
GPT-5.4 Prothis page	4 Mar 2026	63.3	#68
GPT-5.2 Proxhigh	11 Dec 2025	–	–
GPT-5 Pro	7 Aug 2025	59.8	#121

Reasoning-effort configurations

The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Not stated” collects results from publishers that did not say which setting they used; for a reasoning model that is usually its thinking mode, but we do not assume it. Pick a setting here or at the top of the page to see its price, speed and category scores.

Effort	Index	Rank	Speed	First answer	Chat reply cost	Categories
no reasoning	–	–	7 tok/s	6.07 s	$0.066	Coding 55
xhigh	61.9	#93	7 tok/s	6.07 s	$0.066	Knowledge 54 · Maths 71 · Reasoning 74
not statedbest	63.3	#68	7 tok/s	6.07 s	$0.066	Instruction following 64 · Knowledge 74 · Multimodal 70 · Reasoning 73

How its index has moved

8 Sept 2026 to 21 Oct 2026

not stated
xhigh

The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.

Benchmark results

See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

Benchmark	xhigh	not stated	Source
GPQA Diamond	94.6%#7	–	Epoch AI Benchmarking Hub
Humanity's Last Exameffort not stated	–	44.3%#6	Scale AI / CAIS
SimpleBencheffort not stated	–	74.1%#10	SimpleBench
ARC-AGI-1	94.5%#39	–	ARC Prize
ARC-AGI-2	83.3%#37	–	ARC Prize
CritPt	30.0%#16	–	Artificial Analysis
Chess Puzzlesnot in index	59.0%#10	–	Epoch AI Benchmarking Hub

Coding

Benchmark	no reasoning	Source	Trend
WeirdML	57.4%#53	WeirdML

Maths

Benchmark	xhigh	Source
FrontierMath Tiers 1–3	82.5%#14	Epoch AI Benchmarking Hub
FrontierMath Tier 4	58.5%#23	Epoch AI Benchmarking Hub
MathArena Apexpossible contamination	69.8%#3	MathArena

Knowledge

Benchmark	xhigh	not stated	Source	Trend
SimpleQA Verified	46.3%#37	–	Epoch AI Benchmarking Hub
MultiNRCeffort not statedpossible contamination	–	62.3%#4	Scale AI SEAL

Instruction following

Benchmark	not stated	Source	Trend
MultiChallenge	69.2%#7	Scale AI SEAL
TutorBench	56.6%#2	Scale AI SEAL

Multimodal

Benchmark	not stated	Source	Trend
VISTA	53.9%#2	Scale AI SEAL

Composite

Benchmark	not stated	Source	Trend
Epoch Capabilities Indexnot in index	159.6#15	Epoch AI Benchmarking Hub

Safety & honesty

Benchmark	not stated	Source	Trend
FORTRESSnot in index	14.8%#54	Scale AI SEAL
MASKnot in indexpossible contamination	91.7%#7	Scale AI SEAL

Where it wins

Benchmarks where this configuration ranks in the top five of every configuration measured.

Where to run it

Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.

Provider	Speed	First token	Input $/M	Output $/M	Context	Quantisation
Azure	7 tok/s	6.25 s	$30.00	$180.00	1.1M	–
OpenAI	5 tok/s	7.06 s	$30.00	$180.00	1.1M	–

What a task costs

Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.

Workload	Tokens in / out	Cost	With caching	Time
Chat reply	400 / 300	$0.066	–	48.9 s
Summarize a 30-page report	12,000 / 600	$0.468	–	1.5 min
Code edit	6,000 / 1,500	$0.450	–	3.7 min
Agentic coding session	60,000 / 4,000	$2.52	–	9.6 min
Structured extraction	2,000 / 200	$0.096	–	34.6 s

New this month

Compare GPT-5.4 Pro with…

Questions people ask

What are GPT-5.4 Pro's benchmark scores?: As of 24 Oct 2026, GPT-5.4 Pro scores 63.3 ±3.4 on the BenchLeader Index, top 100, strongest in knowledge (74) and weakest in instruction following (64). That rests on 6 independent benchmark results, and every score on this page links to its publisher.
How does GPT-5.4 Pro rank?: GPT-5.4 Pro is #68 of 785 ranked configurations on 24 Oct 2026 (top 100). 144 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
How much does GPT-5.4 Pro cost per 1M tokens?: As of 24 Oct 2026, GPT-5.4 Pro costs $30.00 per 1M input tokens and $180.00 per 1M output tokens, $67.50 blended (three input tokens per output token).
Is GPT-5.4 Pro better than Qwen3.8 Max?: As of 24 Oct 2026, GPT-5.4 Pro and Qwen3.8 Max (max) are neck and neck on quality (63.3 vs 63.3 on the BenchLeader Index, inside the ±5.0 margin of error), and Qwen3.8 Max (max) costs 23× less, which makes it the better buy for most workloads. The head-to-head page has the benchmark-by-benchmark detail.
When was GPT-5.4 Pro released?: OpenAI released GPT-5.4 Pro on 4 Mar 2026. BenchLeader has results for it at 3 reasoning-effort settings.

Data as of 24 Oct 2026. Compare these configurations.

Cite as: BenchLeader, “GPT-5.4 Pro: benchmarks, pricing, speed and rank”, data as of 24 Oct 2026, https://www.benchleader.com/models/gpt-5-4-pro.