Motif-3 wins more areas, narrowly.Agnes 2.5 Pro Alpha is better at reasoning.
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.
- AgentsCarrying out multi-step tasks on its own02Motif-32 of 2 tests
- CodingWriting and fixing software01Motif-31 of 2 tests · 1 tie
- ReasoningHard problems that need careful thinking21Agnes 2.5 Pro Alpha2 of 3 tests
- FactsGetting facts right instead of making them up11Even1 each
- Long documentsFinding answers in very long texts00Even0 each · 1 tie
Long documents rests on a single test.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Motif-3 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+59.7points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+22.9points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+7.9points ahead
Where Agnes 2.5 Pro Alpha pulls ahead
- Research-level physics problemsCritPt+4.3points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+4.2points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+3.4points 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.
AgentsMotif-3
- τ-Bench V3 · BankingMotif-3 by 22.912.435.3+22.9
- GDPValMotif-3 by 1.729.431.1+1.7
ReasoningAgnes 2.5 Pro Alpha
- CritPtAgnes 2.5 Pro Alpha by 4.310.96.6+4.3
- GPQA DiamondAgnes 2.5 Pro Alpha by 4.287.683.4+4.2
- Humanity's Last ExamMotif-3 by 3.433.637+3.4
FactsEven
- AA-Omniscience · Non-hallucinationMotif-3 by 59.711.971.6+59.7
- AA-Omniscience · AccuracyAgnes 2.5 Pro Alpha by 3.433.530.1+3.4
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.
- AA-OmniscienceMotif-3 by 35.3-25.110.2+35.3
- AA Agentic IndexMotif-3 by 8.229.437.6+8.2
- AA IntelligenceMotif-3 by 6.826.833.6+6.8
- Artificial Analysis Coding IndexMotif-3 by 4.758.863.5+4.7
Questions people ask
Which is better, Agnes 2.5 Pro Alpha or Motif-3?
Motif-3 wins two of the five areas where both have results: coding and agents. Agnes 2.5 Pro Alpha wins reasoning. They are level on facts and long documents.
Which is better for coding?
Motif-3. It wins 1 of the 2 coding tests both models report; Agnes 2.5 Pro Alpha wins none, and 1 is a tie.
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.