# Google Gemma 2 27B

Google Gemma 2 27B costs $0.65 per million input tokens and $0.65 per million output tokens, as of October 22, 2026. None of the 6 coding benchmarks behind the index has measured it, so it has no coding index, but 36 benchmarks outside the index have a result below.

Page: https://llmbenchmark.ai/models/gemma-2-27b-it
Data from October 22, 2026. Every figure below names the board it was read from and the day.

- Maker: Google
- Released: July 13, 2024
- Price per million input tokens: $0.65
- Price per million output tokens: $0.65
- Context window: 8K tokens

Benchmark results (36 of 195):

- LegalBench (Vals AI): 68.0% (source: Vals AI boards, read October 22, 2026)
- GPQA Diamond (Epoch AI run): 36.5% (source: Epoch AI benchmarking hub, read October 22, 2026)
- OTIS Mock AIME: 1.4% (source: Epoch AI benchmarking hub, read October 22, 2026)
- MATH level 5: 27.9% (source: Epoch AI benchmarking hub, read October 22, 2026)
- MMLU: 75.7% (source: Epoch AI benchmarking hub, read October 22, 2026)
- DTBench: 48.0% (source: Epoch AI benchmarking hub, read October 22, 2026)
- LMCA: 7.1% (source: Epoch AI benchmarking hub, read October 22, 2026)
- Epoch Capabilities Index: 122.1 (source: Epoch AI benchmarking hub, read October 22, 2026)
- LMArena Text: 1231 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: coding: 1211 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: hard prompts: 1198 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: math: 1212 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: instruction following: 1206 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: creative writing: 1240 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: English: 1242 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: non-English: 1217 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Chinese: 1221 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: German: 1209 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Japanese: 1175 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Korean: 1174 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: French: 1248 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Spanish: 1228 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Russian: 1234 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Polish: 1277 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: multi-turn: 1224 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: longer queries: 1230 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: expert: 1171 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: hard prompts in English: 1206 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: software and IT: 1228 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: mathematical work: 1221 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: science: 1228 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: medicine and healthcare: 1198 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: legal and government: 1241 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: business and finance: 1208 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: writing and language: 1249 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: entertainment and media: 1212 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)