The Known Good Updated 25 Jul 2026
Anthropic: Claude Sonnet 4.6 vs OpenAI: o3 Mini ·Anthropic vs OpenAI

Anthropic: Claude Sonnet 4.6 vs OpenAI: o3 Mini — head-to-head comparison

Anthropic: Claude Sonnet 4.6 profile OpenAI: o3 Mini profile All comparisons
Anthropic: Claude Sonnet 4.6 — Anthropic
Quality
#17 of 61
80based on 4 of 6 evaluations
Known Good Index
Speed
#197 of 316
41.2
Output tokens per second
Price
#301 of 340
$6.00
Blended per 1M tokens
In $3.00 · Out $15.00
Cache hit price
#165 of 206
$0.30
per 1M tokens (−90%)
Context
#55 of 345
1.00M
tokens (~1,500 pages)
OpenAI: o3 Mini — OpenAI
Quality
#15 of 61
82based on 3 of 6 evaluations
Known Good Index
Speed
#22 of 316
131.8
Output tokens per second
Price
#236 of 340
$1.93
Blended per 1M tokens
In $1.10 · Out $4.40
Cache hit price
#189 of 206
$0.55
per 1M tokens (−50%)
Context
#205 of 345
200k
tokens (~300 pages)
Summary

On the Known Good Index, Anthropic: Claude Sonnet 4.6 scores 80 and OpenAI: o3 Mini scores 82 — a 2-point lead for OpenAI: o3 Mini. They share 2 published evaluations, with Anthropic: Claude Sonnet 4.6 ahead on 2 and OpenAI: o3 Mini ahead on 0.

Blended pricing is $6.00 per 1M tokens for Anthropic: Claude Sonnet 4.6 and $1.93 for OpenAI: o3 Mini — OpenAI: o3 Mini is about 3.1× cheaper.

Throughput is 41 tokens per second for Anthropic: Claude Sonnet 4.6 and 132 for OpenAI: o3 Mini, with time to first token at 1.6s and 3.2s. Anthropic: Claude Sonnet 4.6 accepts 1.00M tokens of context against 200k.

Anthropic: Claude Sonnet 4.6 is proprietary; OpenAI: o3 Mini is proprietary. 5 tracked hosts serve one or both.

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

At a glance
MetricAnthropic: Claude Sonnet 4.6OpenAI: o3 Mini
Known Good Index 80 based on 4 of 6 evaluations 82 based on 3 of 6 evaluations
Blended $/1M $6.00 $1.93
Output tok/s 41 132
Context window 1.00M 200k
Providers 4 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.

MetricAnthropic: Claude Sonnet 4.6OpenAI: o3 Mini
Known Good Index 80 82
Coding Index 71 —
Mathematics Index 86 88
Science Index 91 78
Reasoning Index — 85
Agentic Index 71 —
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 Sonnet 4.6 · marker = OpenAI: o3 Mini · scores ingested from Epoch AI (CC-BY 4.0)

GPQA Diamond87 / 77
MATH / AIME86 / 77

Right-hand figures read Anthropic: Claude Sonnet 4.6 / OpenAI: o3 Mini. Anthropic: Claude Sonnet 4.6 leads on 2 of 2, OpenAI: o3 Mini 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 Sonnet 4.6OpenAI: o3 Mini
Text Arena 1,458 1,319
Text Arena (style controlled) 1,473 1,348
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.

MetricAnthropic: Claude Sonnet 4.6OpenAI: o3 Mini
Input $/1M $3.00 $1.10
Output $/1M $15.00 $4.40
Blended $/1M $6.00 $1.93
Cache read $/1M $0.300 $0.550
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 Sonnet 4.6OpenAI: o3 Mini
Context window 1.00M 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.

MetricAnthropic: Claude Sonnet 4.6OpenAI: o3 Mini
Output tokens/s 41 132
Time to first token 1.6s 3.2s
The Known Good

Providers

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

5 hosts
Full provider benchmarks →
Provider Anthropic: Claude Sonnet 4.6 blendedAnthropic: Claude Sonnet 4.6 tok/s OpenAI: o3 Mini blendedOpenAI: o3 Mini tok/s
Amazon Bedrock · first party $6.00 41 — —
Google · first party $6.00 41 — —
Anthropic · first party $6.00 38 — —
Azure · first party $6.00 — — —
OpenAI · first party — — $1.93 127

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 →