The Known Good Updated 29 Jul 2026
DeepSeek: DeepSeek V3 vs OpenAI: GPT-5.4 ·DeepSeek vs OpenAI

DeepSeek: DeepSeek V3 vs OpenAI: GPT-5.4 — head-to-head comparison

DeepSeek: DeepSeek V3 profile OpenAI: GPT-5.4 profile All comparisons
DeepSeek: DeepSeek V3 — DeepSeek
Quality
#40 of 62
62based on 4 of 7 evaluations
Known Good Index
Speed
#285 of 317
19.3
Output tokens per second
Price
#110 of 370
$0.35
Blended per 1M tokens
In $0.20 · Out $0.80
Cache hit price
#11 of 238
$0.003
per 1M tokens (−99%)
Context
#255 of 375
164k
tokens (~300 pages)
OpenAI: GPT-5.4 — OpenAI
Quality
#10 of 62
90based on 5 of 7 evaluations
Known Good Index
Speed
#90 of 317
68.0
Output tokens per second
Price
#328 of 370
$5.62
Blended per 1M tokens
In $2.50 · Out $15.00
Cache hit price
#192 of 238
$0.25
per 1M tokens (−90%)
Context
#17 of 375
1.05M
tokens (~1,600 pages)
Summary

On the Known Good Index, DeepSeek: DeepSeek V3 scores 62 and OpenAI: GPT-5.4 scores 90 — a 28-point lead for OpenAI: GPT-5.4. They share 2 published evaluations, with DeepSeek: DeepSeek V3 ahead on 0 and OpenAI: GPT-5.4 ahead on 2.

Blended pricing is $0.35 per 1M tokens for DeepSeek: DeepSeek V3 and $5.62 for OpenAI: GPT-5.4 — DeepSeek: DeepSeek V3 is about 16.1× cheaper.

Throughput is 19 tokens per second for DeepSeek: DeepSeek V3 and 68 for OpenAI: GPT-5.4, with time to first token at 1.4s and 2.5s. DeepSeek: DeepSeek V3 accepts 164k tokens of context against 1.05M.

DeepSeek: DeepSeek V3 is open weights under Open weights (unrestricted); OpenAI: GPT-5.4 is proprietary. 5 tracked hosts serve one or both.

Generated from tracked data on 29 Jul 2026 · how these comparisons are computed →

At a glance
MetricDeepSeek: DeepSeek V3OpenAI: GPT-5.4
Known Good Index 62 based on 4 of 7 evaluations 90 based on 5 of 7 evaluations
Blended $/1M $0.35 $5.62
Output tok/s 19 68
Context window 164k 1.05M
Providers 3 2
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: DeepSeek V3OpenAI: GPT-5.4
Known Good Index 62 90
Coding Index — 89
Mathematics Index 57 98
Reasoning Index 61 88
Agentic Index — 89
Openness Index 60 5
The Known Good

Quality Breakdown

Every evaluation both models report a published score for

Evaluations both models report

Bar = DeepSeek: DeepSeek V3 · marker = OpenAI: GPT-5.4 · scores ingested from Epoch AI (CC-BY 4.0)

GPQA Diamond71 / 93
Mock AIME 2024–2549 / 98

Right-hand figures read DeepSeek: DeepSeek V3 / OpenAI: GPT-5.4. DeepSeek: DeepSeek V3 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: DeepSeek V3OpenAI: GPT-5.4
Text Arena 1,333 1,452
Text Arena (style controlled) 1,359 1,465
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: DeepSeek V3OpenAI: GPT-5.4
Input $/1M $0.20 $2.50
Output $/1M $0.80 $15.00
Blended $/1M $0.35 $5.62
Cache read $/1M $0.003 $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: DeepSeek V3OpenAI: GPT-5.4
Context window 164k 1.05M
Max output tokens 16k 128k
The Known Good

Speed & Latency

Median throughput and time to first token across hosting providers

Output speedTime to first token
Throughput and latency

Medians across all tracked providers, derived from OpenRouter endpoint telemetry.

MetricDeepSeek: DeepSeek V3OpenAI: GPT-5.4
Output tokens/s 19 68
Time to first token 1.4s 2.5s
The Known Good

Providers

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

5 hosts
Full provider benchmarks →
Provider DeepSeek: DeepSeek V3 blendedDeepSeek: DeepSeek V3 tok/s OpenAI: GPT-5.4 blendedOpenAI: GPT-5.4 tok/s
StreamLake $0.35 21 — —
Novita $0.62 20 — —
DeepInfra $0.46 12 — —
Azure · first party — — $5.62 59
OpenAI · first party — — $2.81 59

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 →