Claude Opus 4.8 vs K2 Horizon 375B A23B
Wins 3 of 5 areas
Coding · Agents · Reasoning
Wins 1 of 5 areas
Long documents
Claude Opus 4.8 is the stronger all-rounder.K2 Horizon 375B A23B is better at long documents.
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.
- ReasoningHard problems that need careful thinking30Claude Opus 4.83 of 3 tests
- AgentsCarrying out multi-step tasks on its own20Claude Opus 4.82 of 3 tests · 1 tie
- CodingWriting and fixing software20Claude Opus 4.82 of 2 tests
- Long documentsFinding answers in very long texts01K2 Horizon 375B A23B1 of 1 test
- 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 Claude Opus 4.8 pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+30.6points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+20.2points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+16.7points ahead
Where K2 Horizon 375B A23B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+13.4points ahead
- Reasons across sets of long documentsAA-LCR+2.3points 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 Opus 4.8
- Terminal-Bench 2.1Claude Opus 4.8 by 12.784.671.9+12.7
- SciCodeClaude Opus 4.8 by 11.554.442.9+11.5
AgentsClaude Opus 4.8
- Terminal-Bench 4.0Claude Opus 4.8 by 20.221.71.5+20.2
- GDPValClaude Opus 4.8 by 4.747.743+4.7
- τ-Bench V3 · Bankingtie34.234.2tie
ReasoningClaude Opus 4.8
- Humanity's Last ExamClaude Opus 4.8 by 16.748.732+16.7
- CritPtClaude Opus 4.8 by 16.320.94.6+16.3
- GPQA DiamondClaude Opus 4.8 by 4.79287.3+4.7
FactsEven
- AA-Omniscience · AccuracyClaude Opus 4.8 by 30.648.818.2+30.6
- AA-Omniscience · Non-hallucinationK2 Horizon 375B A23B by 13.460.774.1+13.4
Long documentsK2 Horizon 375B A23B
- AA-LCRK2 Horizon 375B A23B by 2.377.780+2.3
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-OmniscienceClaude Opus 4.8 by 31.828.8-3+31.8
- Artificial Analysis Coding IndexClaude Opus 4.8 by 12.874.361.5+12.8
- AA IntelligenceClaude Opus 4.8 by 11.341.830.5+11.3
- AA Agentic IndexClaude Opus 4.8 by 1.742.640.9+1.7
Questions people ask
Which is better, Claude Opus 4.8 or K2 Horizon 375B A23B?
Claude Opus 4.8 wins three of the five areas where both have results: coding, agents and reasoning. K2 Horizon 375B A23B wins long documents. They are level on facts.
Which is better for coding?
Claude Opus 4.8. It wins 2 of the 2 coding tests both models report; K2 Horizon 375B A23B 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.