Claude 3.5 Haiku vs K-EXAONE
Wins 0 of 6 areas
—
Wins 5 of 6 areas
Coding · Agents · Reasoning · Long documents · Following instructions
K-EXAONE is the stronger all-rounder.
Scores updated · 17 tests both models report · How we compare
Where each one wins
Tests won in each of the six 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 software03K-EXAONE3 of 3 tests
- ReasoningHard problems that need careful thinking03K-EXAONE3 of 3 tests
- AgentsCarrying out multi-step tasks on its own01K-EXAONE1 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts01K-EXAONE1 of 1 test
- Following instructionsDoing exactly what it is asked01K-EXAONE1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
Long documents and following instructions rest on a single test each.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where K-EXAONE pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+37.5points ahead
- Reasons across sets of long documentsAA-LCR+34points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+21.9points ahead
Where Claude 3.5 Haiku pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+47.7points ahead
Every test, side by side
All 17 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingK-EXAONE
- Terminal-Bench HardK-EXAONE by 20.42.322.7+20.4
- Terminal-Bench 2.1K-EXAONE by 20.210.130.3+20.2
- SciCodeK-EXAONE by 8.227.435.6+8.2
ReasoningK-EXAONE
- GPQA DiamondK-EXAONE by 37.540.878.3+37.5
- Humanity's Last ExamK-EXAONE by 10.33.613.9+10.3
- CritPtK-EXAONE by 1.101.1+1.1
FactsEven
- AA-Omniscience · Non-hallucinationClaude 3.5 Haiku by 47.758.911.2+47.7
- AA-Omniscience · AccuracyK-EXAONE by 3.213.216.4+3.2
Following instructionsK-EXAONE
- IFBenchK-EXAONE by 21.942.864.7+21.9
Other results5 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.
- τ²-Bench Telecom (AA run)K-EXAONE by 49.724.674.3+49.7
- AA-OmniscienceClaude 3.5 Haiku by 35.5-22.5-58+35.5
- Artificial Analysis Coding IndexK-EXAONE by 16.215.932.1+16.2
- AA Agentic IndexK-EXAONE by 6.11.98+6.1
- AA IntelligenceK-EXAONE by 5.58.914.4+5.5
Questions people ask
Which is better, Claude 3.5 Haiku or K-EXAONE?
K-EXAONE wins five of the six areas where both have results: coding, agents, reasoning, long documents and following instructions. Claude 3.5 Haiku wins none. They are level on facts.
Which is better for coding?
K-EXAONE. It wins 3 of the 3 coding tests both models report; Claude 3.5 Haiku wins none.
How do you compare the two?
We use the 17 benchmark tests both models have published scores on. The verdict counts the 12 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 5 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.