The Known Good Updated 8 Sep 2026 Subscribe
DeepSeek: DeepSeek V3 vs OpenAI: GPT-5.2 ·DeepSeek vs OpenAI

DeepSeek: DeepSeek V3 vs OpenAI: GPT-5.2 — head-to-head comparison

DeepSeek: DeepSeek V3 profile OpenAI: GPT-5.2 profile All comparisons
DeepSeek: DeepSeek V3 — DeepSeek
Quality
#43 of 65
62based on 4 of 7 evaluations
Known Good Index
Speed
#316 of 341
18.7
Output tokens per second
Price
#155 of 450
$0.46
Blended per 1M tokens
In $0.32 · Out $0.89
Cache hit price
#114 of 344
$0.050
per 1M tokens (−84%)
Context
#341 of 487
164k
tokens (~300 pages)
OpenAI: GPT-5.2 — OpenAI
Quality
#17 of 65
81based on 5 of 7 evaluations
Known Good Index
Speed
#133 of 341
58.3
Output tokens per second
Price
#389 of 450
$4.81
Blended per 1M tokens
In $1.75 · Out $14.00
Cache hit price
#234 of 344
$0.17
per 1M tokens (−90%)
Context
#183 of 487
400k
tokens (~600 pages)
Summary

On the Known Good Index, DeepSeek: DeepSeek V3 scores 62 and OpenAI: GPT-5.2 scores 81 — a 19-point lead for OpenAI: GPT-5.2. They share 2 published evaluations, with DeepSeek: DeepSeek V3 ahead on 0 and OpenAI: GPT-5.2 ahead on 2.

Blended pricing is $0.46 per 1M tokens for DeepSeek: DeepSeek V3 and $4.81 for OpenAI: GPT-5.2 — DeepSeek: DeepSeek V3 is about 10.4× cheaper.

Throughput is 19 tokens per second for DeepSeek: DeepSeek V3 and 58 for OpenAI: GPT-5.2, with time to first token at 1.6s and 4.0s. DeepSeek: DeepSeek V3 accepts 164k tokens of context against 400k.

DeepSeek: DeepSeek V3 is open weights under Open weights (unrestricted); OpenAI: GPT-5.2 is proprietary. 5 tracked hosts serve one or both.

Generated from tracked data on 9 Sep 2026 · how these comparisons are computed →

At a glance
MetricDeepSeek: DeepSeek V3OpenAI: GPT-5.2
Known Good Index 62 based on 4 of 7 evaluations 81 based on 5 of 7 evaluations
Blended $/1M $0.46 $4.81
Output tok/s 19 58
Context window 164k 400k
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-5.2
Known Good Index 62 81
Coding Index — 79
Mathematics Index 57 —
Reasoning Index 62 76
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-5.2 · scores ingested from Epoch AI (CC-BY 4.0)

GPQA Diamond71 / 91
Mock AIME 2024–2549 / 96

Right-hand figures read DeepSeek: DeepSeek V3 / OpenAI: GPT-5.2. DeepSeek: DeepSeek V3 leads on 0 of 2, OpenAI: GPT-5.2 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-5.2
Text Arena 1,332 1,412
Text Arena (style controlled) 1,358 1,436
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-5.2
Input $/1M $0.32 $1.75
Output $/1M $0.89 $14.00
Blended $/1M $0.46 $4.81
Cache read $/1M $0.050 $0.175
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-5.2
Context window 164k 400k
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: DeepSeek V3OpenAI: GPT-5.2
Output tokens/s 19 58
Time to first token 1.6s 4.0s
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-5.2 blendedOpenAI: GPT-5.2 tok/s
StreamLake $0.45 24 — —
Novita $0.62 17 — —
DeepInfra $0.46 11 — —
OpenAI · first party — — $2.41 108
Azure · first party — — $4.81 39

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 →