The Known Good Updated 25 Jul 2026
OpenAI: GPT-5.2 vs OpenAI: o3 ·OpenAI vs OpenAI

OpenAI: GPT-5.2 vs OpenAI: o3 — head-to-head comparison

OpenAI: GPT-5.2 profile OpenAI: o3 profile All comparisons
OpenAI: GPT-5.2 — OpenAI
Quality
#16 of 61
80based on 5 of 6 evaluations
Known Good Index
Speed
#151 of 316
53.9
Output tokens per second
Price
#295 of 340
$4.81
Blended per 1M tokens
In $1.75 · Out $14.00
Cache hit price
#134 of 206
$0.17
per 1M tokens (−90%)
Context
#106 of 345
400k
tokens (~600 pages)
OpenAI: o3 — OpenAI
Quality
#28 of 61
67based on 4 of 6 evaluations
Known Good Index
Speed
#70 of 316
88.5
Output tokens per second
Price
#269 of 340
$3.50
Blended per 1M tokens
In $2.00 · Out $8.00
Cache hit price
#175 of 206
$0.50
per 1M tokens (−75%)
Context
#203 of 345
200k
tokens (~300 pages)
Summary

On the Known Good Index, OpenAI: GPT-5.2 scores 80 and OpenAI: o3 scores 67 — a 13-point lead for OpenAI: GPT-5.2. They share 4 published evaluations, with OpenAI: GPT-5.2 ahead on 4 and OpenAI: o3 ahead on 0.

Blended pricing is $4.81 per 1M tokens for OpenAI: GPT-5.2 and $3.50 for OpenAI: o3 — OpenAI: o3 is about 1.4× cheaper.

Throughput is 54 tokens per second for OpenAI: GPT-5.2 and 88 for OpenAI: o3, with time to first token at 2.5s and 2.7s. OpenAI: GPT-5.2 accepts 400k tokens of context against 200k.

OpenAI: GPT-5.2 is proprietary; OpenAI: o3 is proprietary. 2 tracked hosts serve one or both, and 1 serve both.

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

At a glance
MetricOpenAI: GPT-5.2OpenAI: o3
Known Good Index 80 based on 5 of 6 evaluations 67 based on 4 of 6 evaluations
Blended $/1M $4.81 $3.50
Output tok/s 54 88
Context window 400k 200k
Providers 2 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-5.2OpenAI: o3
Known Good Index 80 67
Coding Index 76 —
Mathematics Index 96 92
Science Index 96 84
Reasoning Index 77 62
Agentic Index 76 60
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-5.2 · marker = OpenAI: o3 · scores ingested from Epoch AI (CC-BY 4.0)

GPQA Diamond91 / 82
MATH / AIME96 / 84
SWE-bench Verified74 / 62
Humanity's Last Exam28 / 20

Right-hand figures read OpenAI: GPT-5.2 / OpenAI: o3. OpenAI: GPT-5.2 leads on 4 of 4, OpenAI: o3 on 0.

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-5.2OpenAI: o3
Text Arena 1,411 —
Text Arena (style controlled) 1,434 —
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-5.2OpenAI: o3
Input $/1M $1.75 $2.00
Output $/1M $14.00 $8.00
Blended $/1M $4.81 $3.50
Cache read $/1M $0.175 $0.500
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-5.2OpenAI: o3
Context window 400k 200k
Max output tokens 128k 100k
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-5.2OpenAI: o3
Output tokens/s 54 88
Time to first token 2.5s 2.7s
The Known Good

Providers

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

2 hosts · 1 serve both
Full provider benchmarks →
Provider OpenAI: GPT-5.2 blendedOpenAI: GPT-5.2 tok/s OpenAI: o3 blendedOpenAI: o3 tok/s
OpenAI · first party $2.41 49 $3.50 72
Azure · first party $4.81 43 — —

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 →