modelbenchmark.io

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
2025-08-28
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.65
Output
$0.65

Quality

3 benchmarks · 1 source

Composite
14th
percentile of 344 scored models
Rank
296 / 344
±0.06 sd
Evidence
3 × 1
one source, or fewer than 3 benchmarks
Effort range
—
one configuration only
reasoning14th1/4 bench
math13th2/7 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 4 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
kilo$0.65$0.65——8K2K—
openrouter$0.65$0.65——8K2K—
aimlapi$0.6877$0.6877——8K2K—
together_ai$0.80$0.80——8K8K2025-08-28

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
2026-10-10openrouterInput$0.65
2026-09-02openrouterOutput$0.65
2026-09-06openrouterOutput$0.65
2026-10-10openrouterOutput$0.65
2026-09-15together_aiInput$0.80
2026-09-24together_aiInput$0.80
2026-09-15together_aiOutput$0.80
2026-09-24together_aiOutput$0.80
2026-10-13aimlapiInput$0.894
2026-10-23aimlapiInput$0.6877
2026-10-13aimlapiOutput$0.894
2026-10-23aimlapiOutput$0.6877

More from Google

most-hosted first