A.X-K2 vs Claude Haiku 4.5
Wins 2 of 5 areas
Agents · Reasoning
Wins 3 of 5 areas
Coding · Facts · Long documents
Claude Haiku 4.5 is the stronger all-rounder.A.X-K2 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.
- CodingWriting and fixing software02Claude Haiku 4.52 of 2 tests
- FactsGetting facts right instead of making them up01Claude Haiku 4.51 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts01Claude Haiku 4.51 of 1 test
- ReasoningHard problems that need careful thinking30A.X-K23 of 3 tests
- AgentsCarrying out multi-step tasks on its own20A.X-K22 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
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+5.7points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+5.2points ahead
- Reasons across sets of long documentsAA-LCR+4.3points ahead
Where A.X-K2 pulls ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+19.2points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+18.5points ahead
- Real work tasks from 44 professionsGDPVal+11.4points 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.
CodingClaude Haiku 4.5
- Terminal-Bench 2.1Claude Haiku 4.5 by 5.23944.2+5.2
- SciCodeClaude Haiku 4.5 by 1.24142.2+1.2
AgentsA.X-K2
- GDPValA.X-K2 by 11.423.211.8+11.4
- τ-Bench V3 · BankingA.X-K2 by 6.816.19.3+6.8
- Terminal-Bench 4.0tie00tie
ReasoningA.X-K2
- Humanity's Last ExamA.X-K2 by 19.229.610.4+19.2
- GPQA DiamondA.X-K2 by 18.585.767.2+18.5
- CritPtA.X-K2 by 8.98.90+8.9
FactsClaude Haiku 4.5
- AA-Omniscience · Non-hallucinationClaude Haiku 4.5 by 5.76772.7+5.7
- AA-Omniscience · Accuracytie18.618tie
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 Agentic IndexA.X-K2 by 15.425.710.3+15.4
- Artificial Analysis Coding IndexClaude Haiku 4.5 by 5.138.843.9+5.1
- AA IntelligenceA.X-K2 by 4.621.516.9+4.6
- AA-OmniscienceClaude Haiku 4.5 by 3.8-8.2-4.4+3.8
Questions people ask
Which is better, A.X-K2 or Claude Haiku 4.5?
Claude Haiku 4.5 wins three of the five areas where both have results: coding, facts and long documents. A.X-K2 wins agents and reasoning.
Which is better for coding?
Claude Haiku 4.5. It wins 2 of the 2 coding tests both models report; A.X-K2 wins none.
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.