The Known Good Updated 9 Sep 2026 Subscribe
OpenAI: GPT-4.1 vs Qwen: Qwen3.6 Max Preview ·OpenAI vs Alibaba

OpenAI: GPT-4.1 vs Qwen: Qwen3.6 Max Preview — head-to-head comparison

OpenAI: GPT-4.1 profile Qwen: Qwen3.6 Max Preview profile All comparisons
OpenAI: GPT-4.1 — OpenAI
Quality
#50 of 65
46based on 5 of 7 evaluations
Known Good Index
Speed
#131 of 341
59.1
Output tokens per second
Price
#359 of 450
$3.50
Blended per 1M tokens
In $2.00 · Out $8.00
Cache hit price
#317 of 344
$0.50
per 1M tokens (−75%)
Context
#101 of 487
1.05M
tokens (~1,600 pages)
Qwen: Qwen3.6 Max Preview — Alibaba
Quality
#12 of 65
89based on 3 of 7 evaluations
Known Good Index
Speed
#164 of 341
50.8
Output tokens per second
Price
#326 of 450
$2.31
Blended per 1M tokens
In $1.03 · Out $6.16
Cache hit price
#206 of 344
$0.13
per 1M tokens (−87%)
Context
#281 of 487
262k
tokens (~400 pages)
Summary

On the Known Good Index, OpenAI: GPT-4.1 scores 46 and Qwen: Qwen3.6 Max Preview scores 89 — a 44-point lead for Qwen: Qwen3.6 Max Preview. They share 3 published evaluations, with OpenAI: GPT-4.1 ahead on 0 and Qwen: Qwen3.6 Max Preview ahead on 3.

Blended pricing is $3.50 per 1M tokens for OpenAI: GPT-4.1 and $2.31 for Qwen: Qwen3.6 Max Preview — Qwen: Qwen3.6 Max Preview is about 1.5× cheaper.

Throughput is 59 tokens per second for OpenAI: GPT-4.1 and 51 for Qwen: Qwen3.6 Max Preview, with time to first token at 1.1s and 1.9s. OpenAI: GPT-4.1 accepts 1.05M tokens of context against 262k.

OpenAI: GPT-4.1 is proprietary; Qwen: Qwen3.6 Max Preview 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
MetricOpenAI: GPT-4.1Qwen: Qwen3.6 Max Preview
Known Good Index 46 based on 5 of 7 evaluations 89 based on 3 of 7 evaluations
Blended $/1M $3.50 $2.31
Output tok/s 59 51
Context window 1.05M 262k
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.

MetricOpenAI: GPT-4.1Qwen: Qwen3.6 Max Preview
Known Good Index 46 89
Mathematics Index 61 —
Reasoning Index 36 —
Openness Index 5 5
The Known Good

Quality Breakdown

Every evaluation both models report a published score for

Evaluations both models report

Bar = OpenAI: GPT-4.1 · marker = Qwen: Qwen3.6 Max Preview · scores ingested from Epoch AI (CC-BY 4.0)

GPQA Diamond67 / 87
Mock AIME 2024–2538 / 91
SWE-bench Verified49 / 77

Right-hand figures read OpenAI: GPT-4.1 / Qwen: Qwen3.6 Max Preview. OpenAI: GPT-4.1 leads on 0 of 3, Qwen: Qwen3.6 Max Preview 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.

MetricOpenAI: GPT-4.1Qwen: Qwen3.6 Max Preview
Text Arena — 1,446
Text Arena (style controlled) — 1,460
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.

MetricOpenAI: GPT-4.1Qwen: Qwen3.6 Max Preview
Input $/1M $2.00 $1.03
Output $/1M $8.00 $6.16
Blended $/1M $3.50 $2.31
Cache read $/1M $0.500 $0.130
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.

MetricOpenAI: GPT-4.1Qwen: Qwen3.6 Max Preview
Context window 1.05M 262k
Max output tokens 33k 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.

MetricOpenAI: GPT-4.1Qwen: Qwen3.6 Max Preview
Output tokens/s 59 51
Time to first token 1.1s 1.9s
The Known Good

Providers

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

3 hosts
Full provider benchmarks →
Provider OpenAI: GPT-4.1 blendedOpenAI: GPT-4.1 tok/s Qwen: Qwen3.6 Max Preview blendedQwen: Qwen3.6 Max Preview tok/s
Azure · first party $3.50 111 — —
OpenAI · first party $3.50 62 — —
Alibaba · first party — — $2.31 44

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 →