The Known Good Updated 4 Sep 2026 Subscribe
DeepSeek: R1 vs OpenAI: GPT-5.4 ·DeepSeek vs OpenAI

DeepSeek: R1 vs OpenAI: GPT-5.4 — head-to-head comparison

DeepSeek: R1 profile OpenAI: GPT-5.4 profile All comparisons
DeepSeek: R1 — DeepSeek
Quality
#22 of 65
75based on 4 of 7 evaluations
Known Good Index
Speed
#307 of 338
20.3
Output tokens per second
Price
#252 of 442
$1.15
Blended per 1M tokens
In $0.70 · Out $2.50
Cache hit price
unranked
—
per 1M tokens
Context
#443 of 476
64k
tokens (~98 pages)
OpenAI: GPT-5.4 — OpenAI
Quality
#9 of 65
91based on 5 of 7 evaluations
Known Good Index
Speed
#78 of 338
79.6
Output tokens per second
Price
#393 of 442
$5.62
Blended per 1M tokens
In $2.50 · Out $15.00
Cache hit price
#265 of 324
$0.25
per 1M tokens (−90%)
Context
#31 of 476
1.05M
tokens (~1,600 pages)
Summary

On the Known Good Index, DeepSeek: R1 scores 75 and OpenAI: GPT-5.4 scores 91 — a 16-point lead for OpenAI: GPT-5.4. They share 2 published evaluations, with DeepSeek: R1 ahead on 0 and OpenAI: GPT-5.4 ahead on 2.

Blended pricing is $1.15 per 1M tokens for DeepSeek: R1 and $5.62 for OpenAI: GPT-5.4 — DeepSeek: R1 is about 4.9× cheaper.

Throughput is 20 tokens per second for DeepSeek: R1 and 80 for OpenAI: GPT-5.4, with time to first token at 1.2s and 1.6s. DeepSeek: R1 accepts 64k tokens of context against 1.05M.

DeepSeek: R1 is open weights under Open weights (unrestricted); OpenAI: GPT-5.4 is proprietary. 4 tracked hosts serve one or both, and 1 serve both.

Generated from tracked data on 4 Sep 2026 · how these comparisons are computed →

At a glance
MetricDeepSeek: R1OpenAI: GPT-5.4
Known Good Index 75 based on 4 of 7 evaluations 91 based on 5 of 7 evaluations
Blended $/1M $1.15 $5.62
Output tok/s 20 80
Context window 64k 1.05M
Providers 2 3
Jump to section

Quality

Known Good Index and the capability indices, side by side

Index scores

Each index is min-max normalised across tracked models and scaled 0–100 from published evaluations. We do not run these evaluations.

MetricDeepSeek: R1OpenAI: GPT-5.4
Known Good Index 75 91
Coding Index — 92
Mathematics Index 74 —
Reasoning Index 77 87
Openness Index 60 5
The Known Good

Quality Breakdown

Every evaluation both models report a published score for

Evaluations both models report

Bar = DeepSeek: R1 · marker = OpenAI: GPT-5.4 · scores ingested from Epoch AI (CC-BY 4.0)

GPQA Diamond69 / 93
Mock AIME 2024–2553 / 98

Right-hand figures read DeepSeek: R1 / OpenAI: GPT-5.4. DeepSeek: R1 leads on 0 of 2, OpenAI: GPT-5.4 on 2.

The Known Good

Arena Elo

Human preference rating from blind pairwise votes

Arena ratings

Elo from blind pairwise votes, ingested from Arena. Higher is better.

MetricDeepSeek: R1OpenAI: GPT-5.4
Text Arena 1,372 1,453
Text Arena (style controlled) 1,398 1,466
The Known Good

Price & Cost

Published API pricing by token type

Published pricing

USD per 1M tokens. Blended is a 3:1 input:output mix. Live from OpenRouter, cross-checked against models.dev. Lower is better.

MetricDeepSeek: R1OpenAI: GPT-5.4
Input $/1M $0.70 $2.50
Output $/1M $2.50 $15.00
Blended $/1M $1.15 $5.62
Cache read $/1M — $0.250
The Known Good
We publish blended price rather than cost-per-task. Cost-per-task requires token counts from an evaluation suite we do not run. Blended price is computed from published rates and is fully reproducible — see the pricing methodology.

Context Window

Maximum input accepted and maximum output emitted

Context and output limits

Provider-declared limits, from metadata via models.dev and OpenRouter. Higher is better.

MetricDeepSeek: R1OpenAI: GPT-5.4
Context window 64k 1.05M
Max output tokens 16k 128k
The Known Good

Speed & Latency

Mean throughput and time to first token across hosting providers, over successful measurements from the last 48 hours

Throughput and latency

Means across all tracked providers over successful measurements from the last 48 hours, derived from OpenRouter endpoint telemetry.

MetricDeepSeek: R1OpenAI: GPT-5.4
Output tokens/s 20 80
Time to first token 1.2s 1.6s
The Known Good

Providers

Which hosts serve each model, and at what price and speed

4 hosts · 1 serve both
Full provider benchmarks →
Provider DeepSeek: R1 blendedDeepSeek: R1 tok/s OpenAI: GPT-5.4 blendedOpenAI: GPT-5.4 tok/s
Novita $1.15 19 — —
Azure · first party $2.60 — $5.62 67
OpenAI · first party — — $2.81 71
Amazon Bedrock · first party — — $6.19 —

Per-host pricing and telemetry from OpenRouter. A dash means that host does not serve that model.

The Known Good
Sources for this page
Pricing & providers — OpenRouter Metadata — models.dev Benchmarks — Epoch AI (CC-BY 4.0)Elo — Arena Full attribution →