The Known Good Updated 29 Jul 2026
gpt-4.5-preview vs Qwen: Qwen3.7 Max ·OpenAI vs Alibaba

gpt-4.5-preview vs Qwen: Qwen3.7 Max — head-to-head comparison

gpt-4.5-preview profile Qwen: Qwen3.7 Max profile All comparisons
gpt-4.5-preview — OpenAI
Quality
#44 of 62
54based on 5 of 7 evaluations
Known Good Index
Speed
unranked
—
Output tokens per second
Price
unranked
—
Blended per 1M tokens
Cache hit price
unranked
—
per 1M tokens
Context
unranked
—
tokens
Qwen: Qwen3.7 Max — Alibaba
Quality
#5 of 62
93based on 3 of 7 evaluations
Known Good Index
Speed
#188 of 317
43.3
Output tokens per second
Price
#252 of 370
$1.88
Blended per 1M tokens
In $1.25 · Out $3.75
Cache hit price
#191 of 238
$0.25
per 1M tokens (−80%)
Context
#103 of 375
1.00M
tokens (~1,500 pages)
Summary

On the Known Good Index, gpt-4.5-preview scores 54 and Qwen: Qwen3.7 Max scores 93 — a 39-point lead for Qwen: Qwen3.7 Max. They share 2 published evaluations, with gpt-4.5-preview ahead on 0 and Qwen: Qwen3.7 Max ahead on 2.

Published pricing is tracked for Qwen: Qwen3.7 Max only, at $1.88 per 1M tokens blended.

gpt-4.5-preview is proprietary; Qwen: Qwen3.7 Max is proprietary. 1 tracked host serve one or both.

Generated from tracked data on 29 Jul 2026 · how these comparisons are computed →

At a glance
Metricgpt-4.5-previewQwen: Qwen3.7 Max
Known Good Index 54 based on 5 of 7 evaluations 93 based on 3 of 7 evaluations
Blended $/1M — $1.88
Output tok/s — 43
Context window — 1.00M
Providers 0 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.

Metricgpt-4.5-previewQwen: Qwen3.7 Max
Known Good Index 54 93
Mathematics Index 59 95
Reasoning Index 48 —
Agentic Index — 88
Openness Index 5 5
The Known Good

Quality Breakdown

Every evaluation both models report a published score for

Evaluations both models report

Bar = gpt-4.5-preview · marker = Qwen: Qwen3.7 Max · scores ingested from Epoch AI (CC-BY 4.0)

GPQA Diamond69 / 92
Mock AIME 2024–2538 / 95

Right-hand figures read gpt-4.5-preview / Qwen: Qwen3.7 Max. gpt-4.5-preview leads on 0 of 2, Qwen: Qwen3.7 Max 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.

Neither model currently appears in an arena we ingest.

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.

Metricgpt-4.5-previewQwen: Qwen3.7 Max
Input $/1M — $1.25
Output $/1M — $3.75
Blended $/1M — $1.88
Cache read $/1M — $0.250
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.

Metricgpt-4.5-previewQwen: Qwen3.7 Max
Context window — 1.00M
Max output tokens — 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.

Metricgpt-4.5-previewQwen: Qwen3.7 Max
Output tokens/s — 43
Time to first token — 1.2s
The Known Good

Providers

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

1 host
Full provider benchmarks →
Provider gpt-4.5-preview blendedgpt-4.5-preview tok/s Qwen: Qwen3.7 Max blendedQwen: Qwen3.7 Max tok/s
Alibaba · first party — — $1.88 50

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) Full attribution →