The Known Good Updated 25 Jul 2026
claude-sonnet-4-5-20250929 vs Google: Gemini 3 Flash Preview ·Anthropic vs Google

claude-sonnet-4-5-20250929 vs Google: Gemini 3 Flash Preview — head-to-head comparison

claude-sonnet-4-5-20250929 profile Google: Gemini 3 Flash Preview profile All comparisons
claude-sonnet-4-5-20250929 — Anthropic
Quality
#36 of 61
59based on 5 of 6 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
Google: Gemini 3 Flash Preview — Google
Quality
#13 of 61
83based on 4 of 6 evaluations
Known Good Index
Speed
#68 of 316
88.9
Output tokens per second
Price
#205 of 340
$1.12
Blended per 1M tokens
In $0.50 · Out $3.00
Cache hit price
#67 of 206
$0.050
per 1M tokens (−90%)
Context
#27 of 345
1.05M
tokens (~1,600 pages)
Summary

On the Known Good Index, claude-sonnet-4-5-20250929 scores 59 and Google: Gemini 3 Flash Preview scores 83 — a 24-point lead for Google: Gemini 3 Flash Preview. They share 4 published evaluations, with claude-sonnet-4-5-20250929 ahead on 0 and Google: Gemini 3 Flash Preview ahead on 4.

Published pricing is tracked for Google: Gemini 3 Flash Preview only, at $1.12 per 1M tokens blended.

claude-sonnet-4-5-20250929 is proprietary; Google: Gemini 3 Flash Preview is proprietary. 2 tracked hosts serve one or both.

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

At a glance
Metricclaude-sonnet-4-5-20250929Google: Gemini 3 Flash Preview
Known Good Index 59 based on 5 of 6 evaluations 83 based on 4 of 6 evaluations
Blended $/1M $1.12
Output tok/s 89
Context window 1.05M
Providers 0 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.

Metricclaude-sonnet-4-5-20250929Google: Gemini 3 Flash Preview
Known Good Index 59 83
Coding Index 61 77
Mathematics Index 89 93
Science Index 84 86
Reasoning Index 48
Agentic Index 61 77
Openness Index 5 5
The Known Good

Quality Breakdown

Every evaluation both models report a published score for

Evaluations both models report

Bar = claude-sonnet-4-5-20250929 · marker = Google: Gemini 3 Flash Preview · scores ingested from Epoch AI (CC-BY 4.0)

GPQA Diamond82 / 83
MATH / AIME78 / 93
SWE-bench Verified71 / 75
Terminal-Bench43 / 64

Right-hand figures read claude-sonnet-4-5-20250929 / Google: Gemini 3 Flash Preview. claude-sonnet-4-5-20250929 leads on 0 of 4, Google: Gemini 3 Flash Preview on 4.

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.

Metricclaude-sonnet-4-5-20250929Google: Gemini 3 Flash Preview
Text Arena 1,438
Text Arena (style controlled) 1,455
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.

Metricclaude-sonnet-4-5-20250929Google: Gemini 3 Flash Preview
Input $/1M $0.50
Output $/1M $3.00
Blended $/1M $1.12
Cache read $/1M $0.050
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.

Metricclaude-sonnet-4-5-20250929Google: Gemini 3 Flash Preview
Context window 1.05M
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.

Metricclaude-sonnet-4-5-20250929Google: Gemini 3 Flash Preview
Output tokens/s 89
Time to first token 2.0s
The Known Good

Providers

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

2 hosts
Full provider benchmarks →
Provider claude-sonnet-4-5-20250929 blendedclaude-sonnet-4-5-20250929 tok/s Google: Gemini 3 Flash Preview blendedGoogle: Gemini 3 Flash Preview tok/s
Google · first party $0.56 85
Google AI Studio $0.56 60

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 →