The Known Good Updated 8 Sep 2026 Subscribe
DeepSeek: R1 vs Qwen: Qwen3.6 Plus ·DeepSeek vs Alibaba

DeepSeek: R1 vs Qwen: Qwen3.6 Plus — head-to-head comparison

DeepSeek: R1 profile Qwen: Qwen3.6 Plus profile All comparisons
DeepSeek: R1 — DeepSeek
Quality
#22 of 65
75based on 4 of 7 evaluations
Known Good Index
Speed
#310 of 341
19.9
Output tokens per second
Price
#259 of 450
$1.15
Blended per 1M tokens
In $0.70 · Out $2.50
Cache hit price
unranked
—
per 1M tokens
Context
#455 of 487
64k
tokens (~98 pages)
Qwen: Qwen3.6 Plus — Alibaba
Quality
#19 of 65
79based on 3 of 7 evaluations
Known Good Index
Speed
#240 of 341
34.8
Output tokens per second
Price
#198 of 450
$0.73
Blended per 1M tokens
In $0.33 · Out $1.95
Cache hit price
#116 of 344
$0.050
per 1M tokens (−85%)
Context
#119 of 487
1.00M
tokens (~1,500 pages)
Summary

On the Known Good Index, DeepSeek: R1 scores 75 and Qwen: Qwen3.6 Plus scores 79 — a 4-point lead for Qwen: Qwen3.6 Plus. They share 2 published evaluations, with DeepSeek: R1 ahead on 0 and Qwen: Qwen3.6 Plus ahead on 2.

Blended pricing is $1.15 per 1M tokens for DeepSeek: R1 and $0.73 for Qwen: Qwen3.6 Plus — Qwen: Qwen3.6 Plus is about 1.6× cheaper.

Throughput is 20 tokens per second for DeepSeek: R1 and 35 for Qwen: Qwen3.6 Plus, with time to first token at 1.1s and 0.9s. DeepSeek: R1 accepts 64k tokens of context against 1.00M.

DeepSeek: R1 is open weights under Open weights (unrestricted); Qwen: Qwen3.6 Plus is proprietary. 3 tracked hosts serve one or both.

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

At a glance
MetricDeepSeek: R1Qwen: Qwen3.6 Plus
Known Good Index 75 based on 4 of 7 evaluations 79 based on 3 of 7 evaluations
Blended $/1M $1.15 $0.73
Output tok/s 20 35
Context window 64k 1.00M
Providers 2 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: R1Qwen: Qwen3.6 Plus
Known Good Index 75 79
Mathematics Index 74 —
Reasoning Index 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: R1 · marker = Qwen: Qwen3.6 Plus · scores ingested from Epoch AI (CC-BY 4.0)

GPQA Diamond69 / 88
Mock AIME 2024–2553 / 93

Right-hand figures read DeepSeek: R1 / Qwen: Qwen3.6 Plus. DeepSeek: R1 leads on 0 of 2, Qwen: Qwen3.6 Plus 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: R1Qwen: Qwen3.6 Plus
Text Arena 1,372 1,437
Text Arena (style controlled) 1,398 1,444
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: R1Qwen: Qwen3.6 Plus
Input $/1M $0.70 $0.33
Output $/1M $2.50 $1.95
Blended $/1M $1.15 $0.73
Cache read $/1M — $0.050
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: R1Qwen: Qwen3.6 Plus
Context window 64k 1.00M
Max output tokens 16k 66k
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: R1Qwen: Qwen3.6 Plus
Output tokens/s 20 35
Time to first token 1.1s 0.9s
The Known Good

Providers

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

3 hosts
Full provider benchmarks →
Provider DeepSeek: R1 blendedDeepSeek: R1 tok/s Qwen: Qwen3.6 Plus blendedQwen: Qwen3.6 Plus tok/s
Novita $1.15 20 — —
Azure · first party $2.60 — — —
Alibaba · first party — — $0.73 33

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 →