The Known Good Updated 25 Jul 2026
claude-opus-4-20250514 vs gemma-3-27b-it ·Anthropic vs Google

claude-opus-4-20250514 vs gemma-3-27b-it — head-to-head comparison

claude-opus-4-20250514 profile gemma-3-27b-it profile All comparisons
claude-opus-4-20250514 — Anthropic
Quality
#31 of 61
62based on 3 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
gemma-3-27b-it — Google
Quality
#48 of 61
37based on 3 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
Summary

On the Known Good Index, claude-opus-4-20250514 scores 62 and gemma-3-27b-it scores 37 — a 26-point lead for claude-opus-4-20250514. They share 3 published evaluations, with claude-opus-4-20250514 ahead on 3 and gemma-3-27b-it ahead on 0.

claude-opus-4-20250514 is proprietary; gemma-3-27b-it is open weights under Open weights (restricted use).

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

At a glance
Metricclaude-opus-4-20250514gemma-3-27b-it
Known Good Index 62 based on 3 of 6 evaluations 37 based on 3 of 6 evaluations
Blended $/1M — —
Output tok/s — —
Context window — —
Providers 0 0
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-opus-4-20250514gemma-3-27b-it
Known Good Index 62 37
Mathematics Index 64 47
Science Index 69 44
Reasoning Index — 40
Agentic Index 76 —
Openness Index 5 60
The Known Good

Quality Breakdown

Every evaluation both models report a published score for

Evaluations both models report

Bar = claude-opus-4-20250514 · marker = gemma-3-27b-it · scores ingested from Epoch AI (CC-BY 4.0)

GPQA Diamond69 / 49
MATH / AIME42 / 20
MATH Level 585 / 74

Right-hand figures read claude-opus-4-20250514 / gemma-3-27b-it. claude-opus-4-20250514 leads on 3 of 3, gemma-3-27b-it 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.

Metricclaude-opus-4-20250514gemma-3-27b-it
Text Arena 1,364 1,358
Text Arena (style controlled) 1,412 1,366
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-opus-4-20250514gemma-3-27b-it
Input $/1M — —
Output $/1M — —
Blended $/1M — —
Cache read $/1M — —
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-opus-4-20250514gemma-3-27b-it
Context window — —
Max output tokens — —
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-opus-4-20250514gemma-3-27b-it
Output tokens/s — —
Time to first token — —
The Known Good

Providers

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

0 hosts
Full provider benchmarks →

No hosting providers are currently tracked for either 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 →