Agnes 2.5 Pro Alpha vs K2 Horizon 375B A23B
Wins 1 of 5 areas
Reasoning
Wins 3 of 5 areas
Coding · Agents · Long documents
K2 Horizon 375B A23B is the stronger all-rounder.Agnes 2.5 Pro Alpha is better at reasoning.
Scores updated · 15 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 own12K2 Horizon 375B A23B2 of 3 tests
- CodingWriting and fixing software01K2 Horizon 375B A23B1 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts01K2 Horizon 375B A23B1 of 1 test
- ReasoningHard problems that need careful thinking20Agnes 2.5 Pro Alpha2 of 3 tests · 1 tie
- FactsGetting facts right instead of making them up11Even1 each
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 K2 Horizon 375B A23B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+62.2points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+21.8points ahead
- Real work tasks from 44 professionsGDPVal+13.6points ahead
Where Agnes 2.5 Pro Alpha pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+15.3points ahead
- Research-level physics problemsCritPt+6.3points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+1.6points ahead
Every test, side by side
All 15 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingK2 Horizon 375B A23B
- Terminal-Bench 2.1K2 Horizon 375B A23B by 4.96771.9+4.9
- SciCodetie42.942.9tie
AgentsK2 Horizon 375B A23B
- τ-Bench V3 · BankingK2 Horizon 375B A23B by 21.812.434.2+21.8
- GDPValK2 Horizon 375B A23B by 13.629.443+13.6
- Terminal-Bench 4.0Agnes 2.5 Pro Alpha by 1.531.5+1.5
ReasoningAgnes 2.5 Pro Alpha
- CritPtAgnes 2.5 Pro Alpha by 6.310.94.6+6.3
- Humanity's Last ExamAgnes 2.5 Pro Alpha by 1.633.632+1.6
- GPQA Diamondtie87.687.3tie
FactsEven
- AA-Omniscience · Non-hallucinationK2 Horizon 375B A23B by 62.211.974.1+62.2
- AA-Omniscience · AccuracyAgnes 2.5 Pro Alpha by 15.333.518.2+15.3
Long documentsK2 Horizon 375B A23B
- AA-LCRK2 Horizon 375B A23B by 4.375.780+4.3
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-OmniscienceK2 Horizon 375B A23B by 22.1-25.1-3+22.1
- AA Agentic IndexK2 Horizon 375B A23B by 11.529.440.9+11.5
- AA IntelligenceK2 Horizon 375B A23B by 3.726.830.5+3.7
- Artificial Analysis Coding IndexK2 Horizon 375B A23B by 2.758.861.5+2.7
Questions people ask
Which is better, Agnes 2.5 Pro Alpha or K2 Horizon 375B A23B?
K2 Horizon 375B A23B wins three of the five areas where both have results: coding, agents and long documents. Agnes 2.5 Pro Alpha wins reasoning. They are level on facts.
Which is better for coding?
K2 Horizon 375B A23B. 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 15 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 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.