Shanghai AI Lab (InternLM)

Internlm2.5 20B Chat

Type
language model
Context
33K tokens
Max output
8K
API string
ollama/internlm2_5-20b-chat

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 1,203.08 1,194–1,212 — —
Arena Score, mathematics 1,179.79 1,165–1,195 — —
Arena Score, programming 1,159.5 1,145–1,174 — —
Arena Score, overall 1,158.61 1,152–1,166 — —
Arena Score, hard prompts 1,158.33 1,147–1,170 — —
Arena Score, expert questions 1,150.13 1,128–1,172 — —
Arena Score, long queries 1,149.46 1,133–1,166 — —
Arena Score, multi-turn dialogue 1,135.6 1,121–1,150 — —
Arena Score, instruction following 1,135.55 1,126–1,146 — —
Arena Score, creative writing 1,123.15 1,107–1,139 — —
Arena Score in Russian 1,106.04 1,090–1,122 — —