The Known Good Updated 25 Jul 2026
deepseek-r1 vs OpenAI: o3 ·DeepSeek vs OpenAI

deepseek-r1 vs OpenAI: o3 — head-to-head comparison

deepseek-r1 profile OpenAI: o3 profile All comparisons
deepseek-r1 — DeepSeek
Quality
#25 of 61
68based on 3 of 6 evaluations
Known Good Index
Speed
unranked
—
Output tokens per second
Price
unranked
—
Blended per 1M tokens
Cache hit price
unranked
—
per 1M tokens
Context
unranked
—
tokens
OpenAI: o3 — OpenAI
Quality
#28 of 61
67based on 4 of 6 evaluations
Known Good Index
Speed
#69 of 316
89.1
Output tokens per second
Price
#269 of 340
$3.50
Blended per 1M tokens
In $2.00 · Out $8.00
Cache hit price
#175 of 206
$0.50
per 1M tokens (−75%)
Context
#203 of 345
200k
tokens (~300 pages)
Summary

On the Known Good Index, deepseek-r1 scores 68 and OpenAI: o3 scores 67 — a 1-point lead for deepseek-r1. They share 3 published evaluations, with deepseek-r1 ahead on 0 and OpenAI: o3 ahead on 3.

Published pricing is tracked for OpenAI: o3 only, at $3.50 per 1M tokens blended.

deepseek-r1 is open weights under Open weights (unrestricted); OpenAI: o3 is proprietary. 1 tracked host serve one or both.

Generated from tracked data on 26 Jul 2026 · how these comparisons are computed →

At a glance
Metricdeepseek-r1OpenAI: o3
Known Good Index 68 based on 3 of 6 evaluations 67 based on 4 of 6 evaluations
Blended $/1M — $3.50
Output tok/s — 89
Context window — 200k
Providers 0 1
Jump to section

Quality

Known Good Index and the capability indices, side by side

IndicesComponents
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: o3
Known Good Index 68 67
Mathematics Index 74 92
Science Index 69 84
Reasoning Index 77 62
Agentic Index — 60
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: o3 · scores ingested from Epoch AI (CC-BY 4.0)

GPQA Diamond69 / 82
MATH / AIME53 / 84
MATH Level 593 / 98

Right-hand figures read deepseek-r1 / OpenAI: o3. deepseek-r1 leads on 0 of 3, OpenAI: o3 on 3.

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: o3
Text Arena 1,373 —
Text Arena (style controlled) 1,398 —
The Known Good

Price & Cost

Published API pricing by token type

Per token typeCache discount
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: o3
Input $/1M — $2.00
Output $/1M — $8.00
Blended $/1M — $3.50
Cache read $/1M — $0.500
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: o3
Context window — 200k
Max output tokens — 100k
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-r1OpenAI: o3
Output tokens/s — 89
Time to first token — 2.7s
The Known Good

Providers

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

1 host
Full provider benchmarks →
Provider deepseek-r1 blendeddeepseek-r1 tok/s OpenAI: o3 blendedOpenAI: o3 tok/s
OpenAI · first party — — $3.50 102

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 →