The Known Good Updated 9 Sep 2026 Subscribe
DeepSeek: DeepSeek V3 vs OpenAI: o3 Mini ·DeepSeek vs OpenAI

DeepSeek: DeepSeek V3 vs OpenAI: o3 Mini — head-to-head comparison

DeepSeek: DeepSeek V3 profile OpenAI: o3 Mini profile All comparisons
DeepSeek: DeepSeek V3 — DeepSeek
Quality
#43 of 65
62based on 4 of 7 evaluations
Known Good Index
Speed
#314 of 341
18.6
Output tokens per second
Price
#156 of 450
$0.46
Blended per 1M tokens
In $0.32 · Out $0.89
Cache hit price
#119 of 344
$0.050
per 1M tokens (−84%)
Context
#342 of 487
164k
tokens (~300 pages)
OpenAI: o3 Mini — OpenAI
Quality
#14 of 65
86based on 4 of 7 evaluations
Known Good Index
Speed
#36 of 341
118.8
Output tokens per second
Price
#309 of 450
$1.93
Blended per 1M tokens
In $1.10 · Out $4.40
Cache hit price
#322 of 344
$0.55
per 1M tokens (−50%)
Context
#334 of 487
200k
tokens (~300 pages)
Summary

On the Known Good Index, DeepSeek: DeepSeek V3 scores 62 and OpenAI: o3 Mini scores 86 — a 23-point lead for OpenAI: o3 Mini. They share 10 published evaluations, with DeepSeek: DeepSeek V3 ahead on 0 and OpenAI: o3 Mini ahead on 10.

Blended pricing is $0.46 per 1M tokens for DeepSeek: DeepSeek V3 and $1.93 for OpenAI: o3 Mini — DeepSeek: DeepSeek V3 is about 4.2× cheaper.

Throughput is 19 tokens per second for DeepSeek: DeepSeek V3 and 119 for OpenAI: o3 Mini, with time to first token at 1.5s and 3.1s. DeepSeek: DeepSeek V3 accepts 164k tokens of context against 200k.

DeepSeek: DeepSeek V3 is open weights under Open weights (unrestricted); OpenAI: o3 Mini is proprietary. 4 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: o3 Mini
Known Good Index 62 based on 4 of 7 evaluations 86 based on 4 of 7 evaluations
Blended $/1M $0.46 $1.93
Output tok/s 19 119
Context window 164k 200k
Providers 3 1
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: o3 Mini
Known Good Index 62 86
Mathematics Index 57 88
Reasoning Index 62 85
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: o3 Mini · scores ingested from Epoch AI (CC-BY 4.0), LiveBench (Apache-2.0)

GPQA Diamond71 / 77
Mock AIME 2024–2549 / 77
MATH Level 565 / 96
LiveBench60 / 76
LiveBench Coding62 / 83
LiveBench Data Analysis61 / 71
LiveBench Instruction Following75 / 84
LiveBench Language47 / 51
LiveBench Mathematics61 / 77
LiveBench Reasoning57 / 90

Right-hand figures read DeepSeek: DeepSeek V3 / OpenAI: o3 Mini. DeepSeek: DeepSeek V3 leads on 0 of 10, OpenAI: o3 Mini on 10.

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: o3 Mini
Text Arena 1,332 1,319
Text Arena (style controlled) 1,358 1,348
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: o3 Mini
Input $/1M $0.32 $1.10
Output $/1M $0.89 $4.40
Blended $/1M $0.46 $1.93
Cache read $/1M $0.050 $0.550
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: o3 Mini
Context window 164k 200k
Max output tokens 16k 100k
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: o3 Mini
Output tokens/s 19 119
Time to first token 1.5s 3.1s
The Known Good

Providers

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

4 hosts
Full provider benchmarks →
Provider DeepSeek: DeepSeek V3 blendedDeepSeek: DeepSeek V3 tok/s OpenAI: o3 Mini blendedOpenAI: o3 Mini tok/s
StreamLake $0.45 26 — —
DeepInfra $0.46 20 — —
Novita $0.62 17 — —
OpenAI · first party — — $1.93 110

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)Benchmarks — LiveBench (Apache-2.0)Elo — Arena Full attribution →