The Known Good Updated 25 Jul 2026
Google ·Open weights (restricted use) ·Released June 2024·Tracked since 25 Jul 2026

Google: Gemma 2 27B — quality, speed & price analysis

Compare with another model Provider benchmarks Data sources
Quality
#59 of 61
19based on 3 of 6 evaluations
Known Good Index
Speed
#294 of 316
14.4
Output tokens per second
Price
#157 of 340
$0.65
Blended per 1M tokens
In $0.65 · Out $0.65
Cache hit price
unranked
per 1M tokens
Context
#336 of 345
8k
tokens (~13 pages)
Summary

Google: Gemma 2 27B is in the lowest quarter of the models we track for quality, and inexpensive for its standing, and notably slow. It accepts text input, outputs text, and supports a 8k-token context window.

It scores 19 on the Known Good Index, well below the tracked average of 60, from 3 of the six component evaluations. Measured against the tracked average, its strongest result is LiveBench (38 against 52) and its weakest is MATH / AIME (1 against 53).

Pricing is $0.65 per 1M input tokens (below the $2.18 average) and $0.65 per 1M output (below the $9.91 average). At 14 tokens per second it sits in the slowest quarter of the models we track.

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

Technical specifications
ReasoningNo
Input modalitytext
Output modalitytext
Context window8,192 tokens
Max output2,048 tokens
WeightsOpen weights · Open weights (restricted use) (commercial use restricted)
Knowledge cutoffJune 2024
Tool callingNo
Providers1 host · compare →
Highlights — where Google: Gemma 2 27B sits
Price

Blended USD per 1M tokens · Lower is better · Published pricing via OpenRouter

Jump to section

Quality

How Google: Gemma 2 27B compares against every tracked model

Known Good IndexCoding IndexCapability indicesBy open weights
Known Good Index

Composite of GPQA Diamond, MATH / AIME, SWE-bench Verified, LiveBench, Humanity's Last Exam and Terminal-Bench, normalised 0–100. Scores are ingested from Epoch AI, LiveBench; we do not run these evaluations.

14 of 908 models +Add model from specific provider
💡 Reasoning models are indicated by a lightbulb
The Known Good

Quality Breakdown

Google: Gemma 2 27B on each evaluation feeding the index, against the tracked average

Evaluation scores

Bar = Google: Gemma 2 27B · grey marker = average across tracked models · scores ingested from Epoch AI, LiveBench

GPQA Diamond36 / 63
MATH / AIME1 / 53
LiveBench38 / 52
The Known Good

Arena Elo

Human preference rating from blind pairwise votes

Arena Elo

Elo from blind pairwise votes, ingested from Arena

Google: Gemma 2 27B does not currently appear in any arena we ingest.

The Known Good

Price & Cost

Published API pricing by token type

BlendedInput vs outputCache discountQuality per dollar
Blended Price

USD per 1M tokens at a 3:1 input:output blend. Live from OpenRouter, cross-checked against models.dev. Lower is better.

14 of 908 models +Add model from specific provider
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 tokens accepted

Context windowMax output tokens
Context Window

Maximum input context from provider metadata via models.dev and OpenRouter. Higher is better.

13 of 908 models +Add model from specific provider
The Known Good

Speed

Median output throughput across hosting providers

Output speedBy provider
Output Speed

Median output tokens per second across all tracked providers. Derived from OpenRouter endpoint telemetry. Higher is better.

13 of 908 models +Add model from specific provider
The Known Good

Latency

Time to first token, median across providers

Time to first tokenEnd-to-end response
Latency (TTFT)

Seconds to first streamed chunk, median across tracked providers. Derived from OpenRouter endpoint telemetry. Lower is better.

13 of 908 models +Add model from specific provider
The Known Good

Providers

Hosts serving Google: Gemma 2 27B, with their own price and speed

1 provider
Full provider benchmarks →
ProviderInput $/MOutput $/M BlendedSpeedTTFTContext
NextBit $0.65 $0.65 $0.65 8k

Per-host pricing and telemetry from OpenRouter. Speed is output tokens per second; TTFT is time to first token.

The Known Good

History

How price and quality have moved since we began tracking this model

Quality & price over time

Since 25 Jul 2026

Known Good Index 19 · based on 3 of 6 evaluations
Blended price $0.65 per 1M · observed 25 Jul 2026
Output speed 14 tok/s · observed 25 Jul 2026
Time to first token 2.1s

No recorded changes for this model since tracking began.

The Known Good

Comparisons

Head-to-head pages pairing Google: Gemma 2 27B with other tracked models

Head-to-head pages are generated for the top 50 models by Known Good Index, which Google: Gemma 2 27B is not currently in. Its nearest tracked models by index are below.

gemma-2-27b-it OpenAI: GPT-4o OpenAI: GPT-4o-mini claude-3-5-haiku-20241022 mistral-small-2501 mistral-small-2503 gemma-2-9b-it claude-3-opus-20240229
Sources for this page
Pricing & providers — OpenRouter Metadata — models.dev Benchmarks — Epoch AI (CC-BY 4.0)Benchmarks — LiveBench (Apache-2.0) Full attribution →