Google DeepMind

Gemma 2 2b It

Type
language model
Context
128K tokens
Max output
4K
Released
16 July 2024
API string
google/gemma-2-2b-it
Weights
open

Prices by provider

Providers do have offers, but we have not collected a current price yet. That is a gap on our side, not a model missing from the market.

Measurement results

Task set Result Run conditions Measured by
Arena Score in English 1,181.61 1,177–1,187 — —
Arena Score in French 1,155.96 1,126–1,186 — —
Arena Score, overall 1,155.93 1,152–1,160 — —
Arena Score, creative writing 1,147.17 1,139–1,155 — —
Arena Score in Spanish 1,139.06 1,112–1,166 — —
Arena Score, mathematics 1,134.56 1,127–1,143 — —
Arena Score, long queries 1,130.24 1,122–1,139 — —
Arena Score, instruction following 1,118.1 1,113–1,124 — —
Arena Score, multi-turn dialogue 1,118.02 1,110–1,126 — —
Arena Score in Russian 1,117.22 1,108–1,126 — —
Arena Score, hard prompts 1,112.81 1,106–1,119 — —
Arena Score, programming 1,112.75 1,105–1,121 — —
Arena Score, expert questions 1,095.71 1,083–1,108 — —