The Known Good Updated 25 Oct 2026 Subscribe
DeepSeek: DeepSeek V3 vs OpenAI: GPT-5.1 ·DeepSeek vs OpenAI

DeepSeek: DeepSeek V3 vs OpenAI: GPT-5.1 — head-to-head comparison

DeepSeek: DeepSeek V3 profile OpenAI: GPT-5.1 profile All comparisons
DeepSeek: DeepSeek V3 — DeepSeek
Quality
#43 of 65
62based on 4 of 7 evaluations
Known Good Index
Speed
#312 of 345
29.4
Output tokens per second
Price
#191 of 526
$0.45
Blended per 1M tokens
In $0.26 · Out $1.03
Cache hit price
#173 of 412
$0.050
per 1M tokens (−81%)
Context
#428 of 575
164k
tokens (~300 pages)
OpenAI: GPT-5.1 — OpenAI
Quality
#25 of 65
73based on 6 of 7 evaluations
Known Good Index
Speed
#70 of 345
113.3
Output tokens per second
Price
#401 of 526
$3.44
Blended per 1M tokens
In $1.25 · Out $10.00
Cache hit price
#240 of 412
$0.12
per 1M tokens (−90%)
Context
#232 of 575
400k
tokens (~600 pages)
Summary

On the Known Good Index, DeepSeek: DeepSeek V3 scores 62 and OpenAI: GPT-5.1 scores 73 — a 11-point lead for OpenAI: GPT-5.1. They share 9 published evaluations, with DeepSeek: DeepSeek V3 ahead on 0 and OpenAI: GPT-5.1 ahead on 9.

Blended pricing is $0.45 per 1M tokens for DeepSeek: DeepSeek V3 and $3.44 for OpenAI: GPT-5.1 — DeepSeek: DeepSeek V3 is about 7.6× cheaper.

Throughput is 29 tokens per second for DeepSeek: DeepSeek V3 and 113 for OpenAI: GPT-5.1, with time to first token at 1.1s and 1.1s. DeepSeek: DeepSeek V3 accepts 164k tokens of context against 400k.

DeepSeek: DeepSeek V3 is open weights under Open weights (unrestricted); OpenAI: GPT-5.1 is proprietary. 5 tracked hosts serve one or both.

Generated from tracked data on 25 Oct 2026 · how these comparisons are computed →

At a glance
MetricDeepSeek: DeepSeek V3OpenAI: GPT-5.1
Known Good Index 62 based on 4 of 7 evaluations 73 based on 6 of 7 evaluations
Blended $/1M $0.45 $3.44
Output tok/s 29 113
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-5.1
Known Good Index 62 73
Coding Index — 69
Mathematics Index 57 —
Reasoning Index 61 77
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-5.1 · scores ingested from Epoch AI (CC-BY 4.0), LiveBench (Apache-2.0)

GPQA Diamond71 / 88
Mock AIME 2024–2549 / 89
LiveBench60 / 79
LiveBench Coding62 / 72
LiveBench Data Analysis61 / 72
LiveBench Instruction Following75 / 93
LiveBench Language47 / 80
LiveBench Mathematics61 / 94
LiveBench Reasoning57 / 96

Right-hand figures read DeepSeek: DeepSeek V3 / OpenAI: GPT-5.1. DeepSeek: DeepSeek V3 leads on 0 of 9, OpenAI: GPT-5.1 on 9.

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-5.1
Text Arena 1,375 1,422
Text Arena (style controlled) 1,395 1,439
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-5.1
Input $/1M $0.26 $1.25
Output $/1M $1.03 $10.00
Blended $/1M $0.45 $3.44
Cache read $/1M $0.050 $0.125
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-5.1
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-5.1
Output tokens/s 29 113
Time to first token 1.1s 1.1s
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-5.1 blendedOpenAI: GPT-5.1 tok/s
StreamLake $0.45 35 — —
DeepInfra $0.37 24 — —
Novita $0.62 17 — —
OpenAI · first party — — $1.72 158
Azure · first party — — $3.44 65

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 →