Apodex 1.1 vs K2 Horizon 36B-A4B
Wins 3 of 5 areas
Coding · Reasoning · Long documents
Wins 1 of 5 areas
Agents
Apodex 1.1 is the stronger all-rounder.K2 Horizon 36B-A4B is better at agents.
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 thinking30Apodex 1.13 of 3 tests
- CodingWriting and fixing software20Apodex 1.12 of 2 tests
- Long documentsFinding answers in very long texts10Apodex 1.11 of 1 test
- AgentsCarrying out multi-step tasks on its own01K2 Horizon 36B-A4B1 of 3 tests · 2 ties
- FactsGetting facts right instead of making them up11Even1 each
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 Apodex 1.1 pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+16.7points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+13.1points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+10.7points ahead
Where K2 Horizon 36B-A4B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+47.9points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+6.8points 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.
CodingApodex 1.1
- Terminal-Bench 2.1Apodex 1.1 by 13.169.756.6+13.1
- SciCodeApodex 1.1 by 5.545.540+5.5
AgentsK2 Horizon 36B-A4B
- τ-Bench V3 · BankingK2 Horizon 36B-A4B by 6.825.232+6.8
- GDPValtie34.834.7tie
- Terminal-Bench 4.0tie00tie
ReasoningApodex 1.1
- Humanity's Last ExamApodex 1.1 by 10.734.123.4+10.7
- GPQA DiamondApodex 1.1 by 4.286.482.2+4.2
- CritPtApodex 1.1 by 2.34.62.3+2.3
FactsEven
- AA-Omniscience · Non-hallucinationK2 Horizon 36B-A4B by 47.921.669.5+47.9
- AA-Omniscience · AccuracyApodex 1.1 by 16.731.715+16.7
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-OmniscienceK2 Horizon 36B-A4B by 11-21.9-10.9+11
- AA IntelligenceApodex 1.1 by 1.126.425.3+1.1
Questions people ask
Which is better, Apodex 1.1 or K2 Horizon 36B-A4B?
Apodex 1.1 wins three of the five areas where both have results: coding, reasoning and long documents. K2 Horizon 36B-A4B wins agents. They are level on facts.
Which is better for coding?
Apodex 1.1. It wins 2 of the 2 coding tests both models report; K2 Horizon 36B-A4B 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.