A.X-K2 vs mercury-2.5-preview
Wins 3 of 5 areas
Coding · Agents · Reasoning
Wins 1 of 5 areas
Long documents
A.X-K2 is the stronger all-rounder.mercury-2.5-preview is better at long documents.
Scores updated · 10 tests both models report · How we compare
Where each one wins
Tests won in each of the five areas 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.
- ReasoningHard problems that need careful thinking20A.X-K22 of 2 tests
- AgentsCarrying out multi-step tasks on its own10A.X-K21 of 2 tests · 1 tie
- CodingWriting and fixing software10A.X-K21 of 1 test
- Long documentsFinding answers in very long texts01mercury-2.5-preview1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
Coding and long documents rest on a single test each.
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.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where A.X-K2 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+47.3points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+17.8points ahead
- Code for real scientific research problemsSciCode+2.5points ahead
Where mercury-2.5-preview pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+4.1points ahead
- Reasons across sets of long documentsAA-LCR+1.7points ahead
Every test, side by side
All 10 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningA.X-K2
- Humanity's Last ExamA.X-K2 by 17.829.611.8+17.8
- CritPtA.X-K2 by 8.98.90+8.9
FactsEven
- AA-Omniscience · Non-hallucinationA.X-K2 by 47.36719.7+47.3
- AA-Omniscience · Accuracymercury-2.5-preview by 4.118.622.6+4.1
Long documentsmercury-2.5-preview
- AA-LCRmercury-2.5-preview by 1.77071.7+1.7
Other results2 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.
- AA-OmniscienceA.X-K2 by 31.3-8.2-39.5+31.3
- AA IntelligenceA.X-K2 by 9.221.512.3+9.2
Questions people ask
Which is better, A.X-K2 or mercury-2.5-preview?
A.X-K2 wins three of the five areas where both have results: coding, agents and reasoning. mercury-2.5-preview wins long documents. They are level on facts.
Which is better for coding?
A.X-K2. It wins the one coding test both models report.
How do you compare the two?
We use the 10 benchmark tests both models have published scores on. The verdict counts the 8 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 2 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.