The Known Good Updated 29 Jul 2026
Anthropic: Claude Opus 4.6 vs OpenAI: GPT-4.1 ·Anthropic vs OpenAI

Anthropic: Claude Opus 4.6 vs OpenAI: GPT-4.1 — head-to-head comparison

Anthropic: Claude Opus 4.6 profile OpenAI: GPT-4.1 profile All comparisons
Anthropic: Claude Opus 4.6 — Anthropic
Quality
#11 of 62
88based on 5 of 7 evaluations
Known Good Index
Speed
#216 of 317
36.0
Output tokens per second
Price
#344 of 370
$10.00
Blended per 1M tokens
In $5.00 · Out $25.00
Cache hit price
#217 of 238
$0.50
per 1M tokens (−90%)
Context
#104 of 375
1.00M
tokens (~1,500 pages)
OpenAI: GPT-4.1 — OpenAI
Quality
#48 of 62
46based on 5 of 7 evaluations
Known Good Index
Speed
#186 of 317
43.5
Output tokens per second
Price
#293 of 370
$3.50
Blended per 1M tokens
In $2.00 · Out $8.00
Cache hit price
#208 of 238
$0.50
per 1M tokens (−75%)
Context
#62 of 375
1.05M
tokens (~1,600 pages)
Summary

On the Known Good Index, Anthropic: Claude Opus 4.6 scores 88 and OpenAI: GPT-4.1 scores 46 — a 42-point lead for Anthropic: Claude Opus 4.6. They share 4 published evaluations, with Anthropic: Claude Opus 4.6 ahead on 4 and OpenAI: GPT-4.1 ahead on 0.

Blended pricing is $10.00 per 1M tokens for Anthropic: Claude Opus 4.6 and $3.50 for OpenAI: GPT-4.1 — OpenAI: GPT-4.1 is about 2.9× cheaper.

Throughput is 36 tokens per second for Anthropic: Claude Opus 4.6 and 44 for OpenAI: GPT-4.1, with time to first token at 2.4s and 0.8s. Anthropic: Claude Opus 4.6 accepts 1.00M tokens of context against 1.05M.

Anthropic: Claude Opus 4.6 is proprietary; OpenAI: GPT-4.1 is proprietary. 5 tracked hosts serve one or both, and 1 serve both.

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

At a glance
MetricAnthropic: Claude Opus 4.6OpenAI: GPT-4.1
Known Good Index 88 based on 5 of 7 evaluations 46 based on 5 of 7 evaluations
Blended $/1M $10.00 $3.50
Output tok/s 36 44
Context window 1.00M 1.05M
Providers 4 2
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.

MetricAnthropic: Claude Opus 4.6OpenAI: GPT-4.1
Known Good Index 88 46
Coding Index 89 —
Mathematics Index 93 61
Reasoning Index 84 36
Agentic Index 89 33
Openness Index 5 5
The Known Good

Quality Breakdown

Every evaluation both models report a published score for

Evaluations both models report

Bar = Anthropic: Claude Opus 4.6 · marker = OpenAI: GPT-4.1 · scores ingested from Epoch AI (CC-BY 4.0)

GPQA Diamond91 / 67
Mock AIME 2024–2593 / 38
SWE-bench Verified79 / 49
Humanity's Last Exam34 / 5

Right-hand figures read Anthropic: Claude Opus 4.6 / OpenAI: GPT-4.1. Anthropic: Claude Opus 4.6 leads on 4 of 4, OpenAI: GPT-4.1 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.

MetricAnthropic: Claude Opus 4.6OpenAI: GPT-4.1
Text Arena 1,497 —
Text Arena (style controlled) 1,497 —
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.

MetricAnthropic: Claude Opus 4.6OpenAI: GPT-4.1
Input $/1M $5.00 $2.00
Output $/1M $25.00 $8.00
Blended $/1M $10.00 $3.50
Cache read $/1M $0.500 $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.

MetricAnthropic: Claude Opus 4.6OpenAI: GPT-4.1
Context window 1.00M 1.05M
Max output tokens 128k 33k
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.

MetricAnthropic: Claude Opus 4.6OpenAI: GPT-4.1
Output tokens/s 36 44
Time to first token 2.4s 0.8s
The Known Good

Providers

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

5 hosts · 1 serve both
Full provider benchmarks →
Provider Anthropic: Claude Opus 4.6 blendedAnthropic: Claude Opus 4.6 tok/s OpenAI: GPT-4.1 blendedOpenAI: GPT-4.1 tok/s
Google · first party $10.00 34 — —
Amazon Bedrock · first party $10.00 32 — —
Anthropic · first party $10.00 31 — —
Azure · first party $10.00 28 $3.50 50
OpenAI · first party — — $3.50 57

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 →