Arctic Instruct is the stronger all-rounder.
Scores updated · 11 tests both models report · How we compare
Where each one wins
Tests won in each of the one area where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
Facts rests on a single test.
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.
Every test, side by side
All 11 tests both models report. The winning score is in its model's colour; marks a score checked independently.
FactsArctic Instruct
- Vectara HHEM hallucination ratelower is betterArctic Instruct by 1.84.36.1+1.8
Other results10 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- MATHDeepSeek-V3 by 38.351.990.2+38.3
- vectara_answer_rateDeepSeek-V3 by 34.862.797.5+34.8
- MMLUDeepSeek-V3 by 3157.588.5+31
- GSM8KDeepSeek-V3 by 17.276.894+17.2
- NarrativeQADeepSeek-V3 by 14.265.379.6+14.2
- OpenBookQADeepSeek-V3 by 12.682.895.4+12.6
- naturalquestions_closedbookDeepSeek-V3 by 7.73946.7+7.7
- AA IntelligenceDeepSeek-V3 by 4.35.49.7+4.3
- vectara_factual_consistencyArctic Instruct by 1.895.793.9+1.8
- vectara_avg_summary_lengthtie81.481.7tie
Questions people ask
Which is better, Arctic Instruct or DeepSeek-V3?
Arctic Instruct wins the one area where both have results: facts. DeepSeek-V3 wins none.
How do you compare the two?
We use the 11 benchmark tests both models have published scores on. The verdict counts the 1 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 10 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.