The Known Good Updated 25 Jul 2026
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
#44 of 61
44based on 3 of 6 evaluations
Known Good Index
Speed
#280 of 316
20.9
Output tokens per second
Price
#105 of 340
$0.35
Blended per 1M tokens
In $0.20 · Out $0.80
Cache hit price
#10 of 206
$0.003
per 1M tokens (−99%)
Context
#225 of 345
164k
tokens (~300 pages)
OpenAI: GPT-5.1 — OpenAI
Quality
#20 of 61
74based on 6 of 6 evaluations
Known Good Index
Speed
#119 of 316
61.9
Output tokens per second
Price
#261 of 340
$3.44
Blended per 1M tokens
In $1.25 · Out $10.00
Cache hit price
#105 of 206
$0.12
per 1M tokens (−90%)
Context
#101 of 345
400k
tokens (~600 pages)
Summary

On the Known Good Index, DeepSeek: DeepSeek V3 scores 44 and OpenAI: GPT-5.1 scores 74 — a 30-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 $0.35 per 1M tokens for DeepSeek: DeepSeek V3 and $3.44 for OpenAI: GPT-5.1 — DeepSeek: DeepSeek V3 is about 9.8× cheaper.

Throughput is 21 tokens per second for DeepSeek: DeepSeek V3 and 62 for OpenAI: GPT-5.1, with time to first token at 1.1s and 1.3s. DeepSeek: DeepSeek V3 accepts 164k tokens of context against 400k.

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

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

At a glance
MetricDeepSeek: DeepSeek V3OpenAI: GPT-5.1
Known Good Index 44 based on 3 of 6 evaluations 74 based on 6 of 6 evaluations
Blended $/1M $0.35 $3.44
Output tok/s 21 62
Context window 164k 400k
Providers 3 2
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: DeepSeek V3OpenAI: GPT-5.1
Known Good Index 44 74
Coding Index — 68
Mathematics Index 40 89
Science Index 53 91
Reasoning Index 52 80
Agentic Index — 61
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 Diamond57 / 88
MATH / AIME16 / 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 1,333 1,422
Text Arena (style controlled) 1,358 1,439
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: DeepSeek V3OpenAI: GPT-5.1
Input $/1M $0.20 $1.25
Output $/1M $0.80 $10.00
Blended $/1M $0.35 $3.44
Cache read $/1M $0.003 $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

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-5.1
Output tokens/s 21 62
Time to first token 1.1s 1.3s
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 $0.35 24 — —
DeepInfra $0.46 20 — —
Novita $0.62 14 — —
OpenAI · first party — — $1.72 82
Azure · first party — — $3.44 58

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 →