The Known Good Updated 25 Jul 2026
OpenAI: gpt-oss-120b vs Qwen: Qwen3.6 Max Preview ·OpenAI vs Alibaba

OpenAI: gpt-oss-120b vs Qwen: Qwen3.6 Max Preview — head-to-head comparison

OpenAI: gpt-oss-120b profile Qwen: Qwen3.6 Max Preview profile All comparisons
OpenAI: gpt-oss-120b — OpenAI
Quality
#33 of 61
61based on 3 of 6 evaluations
Known Good Index
Speed
#9 of 316
172.8
Output tokens per second
Price
#33 of 340
$0.07
Blended per 1M tokens
In $0.04 · Out $0.17
Cache hit price
#25 of 206
$0.015
per 1M tokens (−59%)
Context
#238 of 345
131k
tokens (~200 pages)
Qwen: Qwen3.6 Max Preview — Alibaba
Quality
#9 of 61
90based on 3 of 6 evaluations
Known Good Index
Speed
#182 of 316
44.6
Output tokens per second
Price
#246 of 340
$2.34
Blended per 1M tokens
In $1.04 · Out $6.24
Cache hit price
#113 of 206
$0.13
per 1M tokens (−88%)
Context
#130 of 345
262k
tokens (~400 pages)
Summary

On the Known Good Index, OpenAI: gpt-oss-120b scores 61 and Qwen: Qwen3.6 Max Preview scores 90 — a 29-point lead for Qwen: Qwen3.6 Max Preview. They share 2 published evaluations, with OpenAI: gpt-oss-120b ahead on 0 and Qwen: Qwen3.6 Max Preview ahead on 2.

Blended pricing is $0.07 per 1M tokens for OpenAI: gpt-oss-120b and $2.34 for Qwen: Qwen3.6 Max Preview — OpenAI: gpt-oss-120b is about 33.3× cheaper.

Throughput is 173 tokens per second for OpenAI: gpt-oss-120b and 45 for Qwen: Qwen3.6 Max Preview, with time to first token at 0.7s and 1.4s. OpenAI: gpt-oss-120b accepts 131k tokens of context against 262k.

OpenAI: gpt-oss-120b is open weights under Open weights (unrestricted); Qwen: Qwen3.6 Max Preview is proprietary. 18 tracked hosts serve one or both.

Generated from tracked data on 26 Jul 2026 · how these comparisons are computed →

At a glance
MetricOpenAI: gpt-oss-120bQwen: Qwen3.6 Max Preview
Known Good Index 61 based on 3 of 6 evaluations 90 based on 3 of 6 evaluations
Blended $/1M $0.07 $2.34
Output tok/s 173 45
Context window 131k 262k
Providers 17 1
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.

MetricOpenAI: gpt-oss-120bQwen: Qwen3.6 Max Preview
Known Good Index 61 90
Mathematics Index 89 91
Science Index 77 93
Agentic Index 18 87
Openness Index 60 5
The Known Good

Quality Breakdown

Every evaluation both models report a published score for

Evaluations both models report

Bar = OpenAI: gpt-oss-120b · marker = Qwen: Qwen3.6 Max Preview · scores ingested from Epoch AI (CC-BY 4.0)

GPQA Diamond76 / 89
MATH / AIME89 / 91

Right-hand figures read OpenAI: gpt-oss-120b / Qwen: Qwen3.6 Max Preview. OpenAI: gpt-oss-120b leads on 0 of 2, Qwen: Qwen3.6 Max Preview 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.

MetricOpenAI: gpt-oss-120bQwen: Qwen3.6 Max Preview
Text Arena 1,366 1,456
Text Arena (style controlled) 1,352 1,460
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.

MetricOpenAI: gpt-oss-120bQwen: Qwen3.6 Max Preview
Input $/1M $0.04 $1.04
Output $/1M $0.17 $6.24
Blended $/1M $0.07 $2.34
Cache read $/1M $0.015 $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-oss-120bQwen: Qwen3.6 Max Preview
Context window 131k 262k
Max output tokens 131k 66k
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.

MetricOpenAI: gpt-oss-120bQwen: Qwen3.6 Max Preview
Output tokens/s 173 45
Time to first token 0.7s 1.4s
The Known Good

Providers

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

18 hosts
Full provider benchmarks →
Provider OpenAI: gpt-oss-120b blendedOpenAI: gpt-oss-120b tok/s Qwen: Qwen3.6 Max Preview blendedQwen: Qwen3.6 Max Preview tok/s
Cerebras $0.45 505
Groq $0.26 445
SambaNova $0.34 304
DeepInfra $0.07 282
BaseTen $0.20 255
Nebius $0.26 255
Mara $0.30 198
Parasail $0.26 198
Google · first party $0.16 197
Together $0.26 108
Amazon Bedrock · first party $0.26 103
Phala $0.26 86
Novita $0.10 67
DigitalOcean $0.17 63
Mancer 2 $0.17 49
SiliconFlow $0.15 29
CoreWeave $0.07 24
Alibaba · first party $2.34 2

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 →