Claude Haiku 4.5 vs K2 Horizon 7B
Wins 3 of 5 areas
Coding · Facts · Long documents
Wins 2 of 5 areas
Agents · Reasoning
Claude Haiku 4.5 is the stronger all-rounder.K2 Horizon 7B 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.
- FactsGetting facts right instead of making them up20Claude Haiku 4.52 of 2 tests
- CodingWriting and fixing software10Claude Haiku 4.51 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts10Claude Haiku 4.51 of 1 test
- AgentsCarrying out multi-step tasks on its own03K2 Horizon 7B3 of 3 tests
- ReasoningHard problems that need careful thinking02K2 Horizon 7B2 of 3 tests · 1 tie
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 three tests each model wins by the widest margin. Scores are out of 100.
Where Claude Haiku 4.5 pulls ahead
- Code for real scientific research problemsSciCode+14.7points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+6.3points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+5.2points ahead
Where K2 Horizon 7B pulls ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+18.3points ahead
- Real work tasks from 44 professionsGDPVal+14.4points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+8.1points 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.
CodingClaude Haiku 4.5
- SciCodeClaude Haiku 4.5 by 14.742.227.5+14.7
- Terminal-Bench 2.1tie44.244.2tie
AgentsK2 Horizon 7B
- τ-Bench V3 · BankingK2 Horizon 7B by 18.39.327.6+18.3
- GDPValK2 Horizon 7B by 14.411.826.2+14.4
- Terminal-Bench 4.0K2 Horizon 7B by 101+1
ReasoningK2 Horizon 7B
- GPQA DiamondK2 Horizon 7B by 8.167.275.3+8.1
- Humanity's Last ExamK2 Horizon 7B by 7.810.418.2+7.8
- CritPttie00.3tie
FactsClaude Haiku 4.5
- AA-Omniscience · Non-hallucinationClaude Haiku 4.5 by 6.372.766.4+6.3
- AA-Omniscience · AccuracyClaude Haiku 4.5 by 5.21812.8+5.2
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-OmniscienceClaude Haiku 4.5 by 12.2-4.4-16.6+12.2
- AA IntelligenceK2 Horizon 7B by 3.716.920.6+3.7
Questions people ask
Which is better, Claude Haiku 4.5 or K2 Horizon 7B?
Claude Haiku 4.5 wins three of the five areas where both have results: coding, facts and long documents. K2 Horizon 7B wins agents and reasoning.
Which is better for coding?
Claude Haiku 4.5. It wins 1 of the 2 coding tests both models report; K2 Horizon 7B wins none, and 1 is a tie.
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.