modelbenchmark.io

Google: Gemma 2 27B

Google · gemma-2-27b-it

Compare

Open Gemma instruction model for efficient chat and self-hosted deployments

Specification

most-agreed values

Context
8K
Max output
2K
Released
2024-07-13
Knowledge cutoff
2024-06-30
Retires
Open weights
no
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.65
Output
$0.65

Quality

3 benchmarks · 1 source

Composite
15th
percentile of 334 scored models
Rank
285 / 334
±0.06 sd
Evidence
3 × 1
one source, or fewer than 3 benchmarks
Effort range
one configuration only
reasoning14th1/4 bench
math14th2/7 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
MATH level 527.9 ±1.0defaultEpoch AI2025-01-27
GPQA diamond36.5 ±2.4defaultEpoch AI2025-01-27
OTIS Mock AIME 2024-20251.4 ±0.9defaultEpoch AI2025-03-07

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 3 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
kilo$0.65$0.658K2K
openrouter$0.65$0.658K2K
together_ai$0.80$0.80

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02openrouterInput$0.65
2026-09-06openrouterInput$0.65
2026-09-02openrouterOutput$0.65
2026-09-06openrouterOutput$0.65

More from Google

most-hosted first