Agnes 2.5 Pro Alpha vs K2 Horizon 3.7B
Wins 4 of 5 areas
Coding · Agents · Reasoning · Long documents
Wins 0 of 5 areas
—
Agnes 2.5 Pro Alpha is the stronger all-rounder.
Scores updated · 13 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 thinking30Agnes 2.5 Pro Alpha3 of 3 tests
- CodingWriting and fixing software20Agnes 2.5 Pro Alpha2 of 2 tests
- AgentsCarrying out multi-step tasks on its own21Agnes 2.5 Pro Alpha2 of 3 tests
- Long documentsFinding answers in very long texts10Agnes 2.5 Pro Alpha1 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 Agnes 2.5 Pro Alpha pulls ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+38.9points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+22.7points ahead
- Code for real scientific research problemsSciCode+20.9points ahead
Where K2 Horizon 3.7B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+44points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+7.2points ahead
Every test, side by side
All 13 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingAgnes 2.5 Pro Alpha
- Terminal-Bench 2.1Agnes 2.5 Pro Alpha by 38.96728.1+38.9
- SciCodeAgnes 2.5 Pro Alpha by 20.942.922+20.9
AgentsAgnes 2.5 Pro Alpha
- GDPValAgnes 2.5 Pro Alpha by 10.229.419.2+10.2
- τ-Bench V3 · BankingK2 Horizon 3.7B by 7.212.419.6+7.2
- Terminal-Bench 4.0Agnes 2.5 Pro Alpha by 330+3
ReasoningAgnes 2.5 Pro Alpha
- Humanity's Last ExamAgnes 2.5 Pro Alpha by 19.733.613.9+19.7
- GPQA DiamondAgnes 2.5 Pro Alpha by 18.487.669.2+18.4
- CritPtAgnes 2.5 Pro Alpha by 10.910.90+10.9
FactsEven
- AA-Omniscience · Non-hallucinationK2 Horizon 3.7B by 4411.955.9+44
- AA-Omniscience · AccuracyAgnes 2.5 Pro Alpha by 22.733.510.8+22.7
Long documentsAgnes 2.5 Pro Alpha
- AA-LCRAgnes 2.5 Pro Alpha by 13.475.762.3+13.4
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 IntelligenceAgnes 2.5 Pro Alpha by 11.226.815.6+11.2
- AA-OmniscienceAgnes 2.5 Pro Alpha by 3.5-25.1-28.6+3.5
Questions people ask
Which is better, Agnes 2.5 Pro Alpha or K2 Horizon 3.7B?
Agnes 2.5 Pro Alpha wins four of the five areas where both have results: coding, agents, reasoning and long documents. K2 Horizon 3.7B wins none. They are level on facts.
Which is better for coding?
Agnes 2.5 Pro Alpha. It wins 2 of the 2 coding tests both models report; K2 Horizon 3.7B wins none.
How do you compare the two?
We use the 13 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 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.