Claude Haiku 4.5 vs Mercury 2
Wins 4 of 6 areas
Coding · Agents · Facts · Long documents
Wins 2 of 6 areas
Reasoning · Following instructions
Claude Haiku 4.5 is the stronger all-rounder.Mercury 2 is cheaper and better at reasoning.
Scores updated · 25 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 software30Claude Haiku 4.53 of 4 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own10Claude Haiku 4.51 of 3 tests · 2 ties
- FactsGetting facts right instead of making them up21Claude Haiku 4.52 of 3 tests
- Long documentsFinding answers in very long texts10Claude Haiku 4.51 of 1 test
- ReasoningHard problems that need careful thinking02Mercury 22 of 3 tests · 1 tie
- Following instructionsDoing exactly what it is asked01Mercury 21 of 1 test
Long documents and following instructions rest on a single test each.
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.
Mercury 2 costs 83% less for the same work.
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+63.9points ahead
- Reasons across sets of long documentsAA-LCR+30.6points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+16.9points ahead
Where Mercury 2 pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+15.5points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+9.8points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+6.7points ahead
Every test, side by side
All 25 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 16.944.227.3+16.9
- LMArena · WebDevClaude Haiku 4.5 by 163 rating points13291166+163 rating
- SciCodeClaude Haiku 4.5 by 4.542.237.7+4.5
- Terminal-Bench Hardtie27.326.5tie
AgentsClaude Haiku 4.5
- GDPValClaude Haiku 4.5 by 11.811.80+11.8
- τ-Bench V3 · Bankingtie9.39.5tie
- Terminal-Bench 4.0tie00tie
ReasoningMercury 2
- GPQA DiamondMercury 2 by 9.867.277+9.8
- Humanity's Last ExamMercury 2 by 6.710.417.1+6.7
- CritPttie00.8tie
FactsClaude Haiku 4.5
- AA-Omniscience · Non-hallucinationClaude Haiku 4.5 by 63.972.78.8+63.9
- AA-Omniscience · AccuracyMercury 2 by 3.21821.2+3.2
- Vectara HHEM hallucination ratelower is betterClaude Haiku 4.5 by 2.59.812.3+2.5
Long documentsClaude Haiku 4.5
- AA-LCRClaude Haiku 4.5 by 30.674.343.7+30.6
Following instructionsMercury 2
- IFBenchMercury 2 by 15.554.369.8+15.5
Other results10 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 46.3-4.4-50.7+46.3
- τ²-Bench Telecom (AA run)Mercury 2 by 16.154.770.8+16.1
- Artificial Analysis Coding IndexClaude Haiku 4.5 by 12.843.931.1+12.8
- Tau2 airlineClaude Haiku 4.5 by 10.663.653+10.6
- AIME 2025Mercury 2 by 10.480.791.1+10.4
- AA Agentic IndexClaude Haiku 4.5 by 6.310.34+6.3
- vectara_avg_summary_lengthMercury 2 by 34 rating points115.1149.1+34 rating
- AA IntelligenceClaude Haiku 4.5 by 3.116.913.8+3.1
- vectara_factual_consistencyClaude Haiku 4.5 by 2.590.287.7+2.5
- vectara_answer_ratetie99.5100tie
Questions people ask
Which is better, Claude Haiku 4.5 or Mercury 2?
Claude Haiku 4.5 wins four of the six areas where both have results: coding, agents, facts and long documents. Mercury 2 wins reasoning and following instructions, and costs 83% less.
Which is better for coding?
Claude Haiku 4.5. It wins 3 of the 4 coding tests both models report; Mercury 2 wins none, and 1 is a tie.
Which is cheaper?
Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; Mercury 2 costs $0.25 and $0.75. That makes Mercury 2 about 83% cheaper for the same work.
How do you compare the two?
We use the 25 benchmark tests both models have published scores on. The verdict counts the 15 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 10 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.