Gemma 3 27B
ModelOpen sourceActiveby Google · family “gemmab”
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,... (description from the OpenRouter listing)
in: textin: imageout: textTool useStructured output
Epoch Capabilities Index
130.0 #152 of 268
90% CI 123.2 – 132.1
Released
12 Mar 2025
Context window
131K tokens
Max output
118K tokens
Input $ / 1M tokens
$0.080
Output $ / 1M tokens
$0.45
Cached input $ / 1M
$0.040
Each benchmark shown separately with its own source
Benchmark results (10)
| Benchmark | Domain | Score | vs best recorded | Setting | Run | Source |
|---|---|---|---|---|---|---|
| LMCA | agents | 12.3% | 18% | — | — | External ↗ |
| DTBench | reasoning | 52.5% | 53% | — | — | External ↗ |
| Chess Puzzles | games | 0.0% | 0% | — | 27 Aug 2026 | Eval log ↗ |
| GeoBench | multimodal | 52.0% | 59% | — | — | External ↗ |
| Fiction.LiveBench | long-context | 33.3% | 34% | — | — | External ↗ |
| Lech Mazur Writing | other | 79.9% | 93% | — | — | External ↗ |
| Aider polyglot | coding | 4.9% | 6% | — | — | External ↗ |
| OTIS Mock AIME 2024-2025 | math | 22.5% ±5.3 | 23% | — | 27 Aug 2026 | Eval log ↗ |
| GPQA diamond | science | 47.7% ±2.7 | 50% | — | 27 Aug 2026 | Eval log ↗ |
| MATH level 5 | math | 74.0% ±1.1 | 75% | — | 13 Mar 2025 | Epoch ↗ |
Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.
API list price over time
Price history
$ per 1M tokens
13 recorded prices on 1 Oct 2025 (OpenRouter listing + Internet Archive snapshots); re-read on every data refresh, most recently 7h ago. Steps show when the price changed.
Events
- BenchmarkEpoch AI evaluates Gemma 3 27BEpoch AI Benchmarking Hub