A.X-K2 vs Celeris-1
Wins 5 of 5 areas
Coding · Agents · Reasoning · Facts · Long documents
Wins 0 of 5 areas
—
A.X-K2 is the stronger all-rounder.
Scores updated · 14 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 thinking30A.X-K23 of 3 tests
- AgentsCarrying out multi-step tasks on its own20A.X-K22 of 3 tests · 1 tie
- CodingWriting and fixing software20A.X-K22 of 2 tests
- FactsGetting facts right instead of making them up20A.X-K22 of 2 tests
- Long documentsFinding answers in very long texts10A.X-K21 of 1 test
Long documents 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.
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+59.8points ahead
- Reasons across sets of long documentsAA-LCR+32points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+27.8points ahead
Where Celeris-1 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 14 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingA.X-K2
- Terminal-Bench 2.1A.X-K2 by 27.83911.2+27.8
- SciCodeA.X-K2 by 19.44121.6+19.4
AgentsA.X-K2
- GDPValA.X-K2 by 23.223.20+23.2
- τ-Bench V3 · BankingA.X-K2 by 12.216.13.9+12.2
- Terminal-Bench 4.0tie00tie
ReasoningA.X-K2
- Humanity's Last ExamA.X-K2 by 22.829.66.8+22.8
- GPQA DiamondA.X-K2 by 22.685.763.1+22.6
- CritPtA.X-K2 by 8.98.90+8.9
FactsA.X-K2
- AA-Omniscience · Non-hallucinationA.X-K2 by 59.8677.2+59.8
- AA-Omniscience · AccuracyA.X-K2 by 7.618.611+7.6
Other results3 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 63.4-8.2-71.6+63.4
- Artificial Analysis Coding IndexA.X-K2 by 24.438.814.4+24.4
- AA IntelligenceA.X-K2 by 15.221.56.3+15.2
Questions people ask
Which is better, A.X-K2 or Celeris-1?
A.X-K2 wins all five areas where both have results: coding, agents, reasoning, facts and long documents. Celeris-1 wins none.
Which is better for coding?
A.X-K2. It wins 2 of the 2 coding tests both models report; Celeris-1 wins none.
How do you compare the two?
We use the 14 benchmark tests both models have published scores on. The verdict counts the 11 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 3 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.