Scores updated · 13 tests both models report · How we compare
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
DeepSeek-V3$0.24 to read · $0.90 to writePrice from Artificial Analysis
Gemma 2 27B IT$0.65 to read · $0.65 to writePrice from google
DeepSeek-V3 costs 12% less for the same work.
Every test, side by side
All 13 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results13 tests
- ARC-ChallengeDeepSeek-V3 by 23.995.371.4+23.9
- MMLUDeepSeek-V3 by 22.188.566.4+22.1
- GSM8KDeepSeek-V3 by 209474+20
- MATHDeepSeek-V3 by 15.690.274.6+15.6
- HumanEvalDeepSeek-V3 by 13.465.251.8+13.4
- MBPPDeepSeek-V3 by 12.875.462.6+12.8
- naturalquestions_closedbookDeepSeek-V3 by 11.446.735.3+11.4
- NaturalQuestionsDeepSeek-V3 by 5.54034.5+5.5
- OpenBookQADeepSeek-V3 by 3.695.491.8+3.6
- HellaSwagDeepSeek-V3 by 2.588.986.4+2.5
- PIQADeepSeek-V3 by 1.584.783.2+1.5
- WinoGrandeDeepSeek-V3 by 1.284.983.7+1.2
- NarrativeQAtie79.679tie
Questions people ask
Which is cheaper?
DeepSeek-V3 costs $0.24 per million input tokens and $0.90 per million output tokens; Gemma 2 27B IT costs $0.65 and $0.65. That makes DeepSeek-V3 about 12% cheaper for the same work.
How do you compare the two?
We use the 13 benchmark tests both models have published scores on. None of them is in the eight capability areas we count, so this page lists them without a verdict. Each score is the one shown on the model's own page.