A.X-K2 vs Motif-3-Beta
Wins 0 of 5 areas
—
Wins 4 of 5 areas
Coding · Agents · Reasoning · Long documents
Motif-3-Beta 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.
- CodingWriting and fixing software02Motif-3-Beta2 of 2 tests
- AgentsCarrying out multi-step tasks on its own02Motif-3-Beta2 of 2 tests
- ReasoningHard problems that need careful thinking12Motif-3-Beta2 of 3 tests
- Long documentsFinding answers in very long texts01Motif-3-Beta1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
Long documents rests on a single test.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Motif-3-Beta pulls ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+31.8points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+12.8points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+10.8points ahead
Where A.X-K2 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+16.1points ahead
- Research-level physics problemsCritPt+2.9points ahead
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.
CodingMotif-3-Beta
- Terminal-Bench 2.1Motif-3-Beta by 31.83970.8+31.8
- SciCodeMotif-3-Beta by 3.34144.3+3.3
AgentsMotif-3-Beta
- τ-Bench V3 · BankingMotif-3-Beta by 12.816.128.9+12.8
- GDPValMotif-3-Beta by 7.123.230.3+7.1
ReasoningMotif-3-Beta
- Humanity's Last ExamMotif-3-Beta by 10.829.640.4+10.8
- CritPtA.X-K2 by 2.98.96+2.9
- GPQA DiamondMotif-3-Beta by 1.285.786.9+1.2
FactsEven
- AA-Omniscience · Non-hallucinationA.X-K2 by 16.16750.9+16.1
- AA-Omniscience · AccuracyMotif-3-Beta by 2.418.621+2.4
Other results4 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.
- Artificial Analysis Coding IndexMotif-3-Beta by 23.238.862+23.2
- AA IntelligenceMotif-3-Beta by 10.821.532.3+10.8
- AA-OmniscienceA.X-K2 by 9.6-8.2-17.8+9.6
- AA Agentic IndexMotif-3-Beta by 9.225.734.9+9.2
Questions people ask
Which is better, A.X-K2 or Motif-3-Beta?
Motif-3-Beta wins four of the five areas where both have results: coding, agents, reasoning and long documents. A.X-K2 wins none. They are level on facts.
Which is better for coding?
Motif-3-Beta. It wins 2 of the 2 coding tests both models report; A.X-K2 wins none.
How do you compare the two?
We use the 14 benchmark tests both models have published scores on. The verdict counts the 10 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 4 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.