The Known Good Updated 25 Jul 2026
OpenAI: GPT-5 vs OpenAI: GPT-5.1 ·OpenAI vs OpenAI

OpenAI: GPT-5 vs OpenAI: GPT-5.1 — head-to-head comparison

OpenAI: GPT-5 profile OpenAI: GPT-5.1 profile All comparisons
OpenAI: GPT-5 — OpenAI
Quality
#21 of 61
73based on 5 of 6 evaluations
Known Good Index
Speed
#138 of 316
57.0
Output tokens per second
Price
#265 of 340
$3.44
Blended per 1M tokens
In $1.25 · Out $10.00
Cache hit price
#109 of 206
$0.12
per 1M tokens (−90%)
Context
#109 of 345
400k
tokens (~600 pages)
OpenAI: GPT-5.1 — OpenAI
Quality
#20 of 61
74based on 6 of 6 evaluations
Known Good Index
Speed
#119 of 316
61.9
Output tokens per second
Price
#261 of 340
$3.44
Blended per 1M tokens
In $1.25 · Out $10.00
Cache hit price
#105 of 206
$0.12
per 1M tokens (−90%)
Context
#101 of 345
400k
tokens (~600 pages)
Summary

On the Known Good Index, OpenAI: GPT-5 scores 73 and OpenAI: GPT-5.1 scores 74, which puts them level. They share 5 published evaluations, with OpenAI: GPT-5 ahead on 4 and OpenAI: GPT-5.1 ahead on 1.

Blended pricing is $3.44 per 1M tokens for OpenAI: GPT-5 and $3.44 for OpenAI: GPT-5.1, within 10% of each other.

Throughput is 57 tokens per second for OpenAI: GPT-5 and 62 for OpenAI: GPT-5.1, with time to first token at 2.6s and 1.3s. OpenAI: GPT-5 accepts 400k tokens of context against 400k.

OpenAI: GPT-5 is proprietary; OpenAI: GPT-5.1 is proprietary. 2 tracked hosts serve one or both, and 2 serve both.

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

At a glance
MetricOpenAI: GPT-5OpenAI: GPT-5.1
Known Good Index 73 based on 5 of 6 evaluations 74 based on 6 of 6 evaluations
Blended $/1M $3.44 $3.44
Output tok/s 57 62
Context window 400k 400k
Providers 2 2
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-5OpenAI: GPT-5.1
Known Good Index 73 74
Coding Index 67 68
Mathematics Index 96 89
Science Index 90 91
Reasoning Index 71 80
Agentic Index 67 61
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 · marker = OpenAI: GPT-5.1 · scores ingested from Epoch AI (CC-BY 4.0)

GPQA Diamond86 / 88
MATH / AIME91 / 89
SWE-bench Verified74 / 68
Humanity's Last Exam25 / 24
Terminal-Bench50 / 48

Right-hand figures read OpenAI: GPT-5 / OpenAI: GPT-5.1. OpenAI: GPT-5 leads on 4 of 5, OpenAI: GPT-5.1 on 1.

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-5OpenAI: GPT-5.1
Text Arena — 1,422
Text Arena (style controlled) — 1,439
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-5OpenAI: GPT-5.1
Input $/1M $1.25 $1.25
Output $/1M $10.00 $10.00
Blended $/1M $3.44 $3.44
Cache read $/1M $0.125 $0.125
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-5OpenAI: GPT-5.1
Context window 400k 400k
Max output tokens 128k 128k
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-5OpenAI: GPT-5.1
Output tokens/s 57 62
Time to first token 2.6s 1.3s
The Known Good

Providers

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

2 hosts · 2 serve both
Full provider benchmarks →
Provider OpenAI: GPT-5 blendedOpenAI: GPT-5 tok/s OpenAI: GPT-5.1 blendedOpenAI: GPT-5.1 tok/s
OpenAI · first party $3.44 84 $1.72 82
Azure · first party $3.44 40 $3.44 58

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 →