Claude Haiku 4.5 is the stronger all-rounder.
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 software20Claude Haiku 4.52 of 2 tests
- FactsGetting facts right instead of making them up20Claude Haiku 4.52 of 2 tests
- Long documentsFinding answers in very long texts10Claude Haiku 4.51 of 1 test
- AgentsCarrying out multi-step tasks on its own11Even1 each · 1 tie
- ReasoningHard problems that need careful thinking11Even1 each · 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 tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Claude Haiku 4.5 pulls ahead
- Code for real scientific research problemsSciCode+18points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+16.5points ahead
- Reasons across sets of long documentsAA-LCR+14points ahead
Where Ling 3.0 Tiny pulls ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+11.5points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+6.2points 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
- SciCodeClaude Haiku 4.5 by 1842.224.2+18
- Terminal-Bench 2.1Claude Haiku 4.5 by 16.544.227.7+16.5
AgentsEven
- τ-Bench V3 · BankingLing 3.0 Tiny by 11.59.320.8+11.5
- GDPValClaude Haiku 4.5 by 8.611.83.2+8.6
- Terminal-Bench 4.0tie00tie
ReasoningEven
- GPQA DiamondLing 3.0 Tiny by 6.267.273.4+6.2
- Humanity's Last ExamClaude Haiku 4.5 by 1.110.49.3+1.1
- CritPttie00tie
FactsClaude Haiku 4.5
- AA-Omniscience · AccuracyClaude Haiku 4.5 by 9.5188.5+9.5
- AA-Omniscience · Non-hallucinationClaude Haiku 4.5 by 3.272.769.5+3.2
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.
- Artificial Analysis Coding IndexClaude Haiku 4.5 by 17.443.926.5+17.4
- AA-OmniscienceClaude Haiku 4.5 by 14.9-4.4-19.4+14.9
- AA IntelligenceClaude Haiku 4.5 by 5.816.911.1+5.8
- AA Agentic IndexClaude Haiku 4.5 by 3.210.37.1+3.2
Questions people ask
Which is better, Claude Haiku 4.5 or Ling 3.0 Tiny?
Claude Haiku 4.5 wins three of the five areas where both have results: coding, facts and long documents. Ling 3.0 Tiny wins none. They are level on agents and reasoning.
Which is better for coding?
Claude Haiku 4.5. It wins 2 of the 2 coding tests both models report; Ling 3.0 Tiny 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.