Claude 3 Haiku vs ERNIE 4.5 300B A47B
Wins 1 of 5 areas
Long documents
Wins 4 of 5 areas
Coding · Reasoning · Facts · Following instructions
ERNIE 4.5 300B A47B is the stronger all-rounder.Claude 3 Haiku is better at long documents.
Scores updated · 14 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 software02ERNIE 4.5 300B A47B2 of 2 tests
- FactsGetting facts right instead of making them up02ERNIE 4.5 300B A47B2 of 2 tests
- ReasoningHard problems that need careful thinking01ERNIE 4.5 300B A47B1 of 3 tests · 2 ties
- Following instructionsDoing exactly what it is asked01ERNIE 4.5 300B A47B1 of 1 test
- Long documentsFinding answers in very long texts10Claude 3 Haiku1 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.
ERNIE 4.5 300B A47B costs 8% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where ERNIE 4.5 300B A47B pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+43.7points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+13.6points ahead
- Code for real scientific research problemsSciCode+12.9points ahead
Where Claude 3 Haiku pulls ahead
- Reasons across sets of long documentsAA-LCR+23.7points ahead
Every test, side by side
All 14 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingERNIE 4.5 300B A47B
- SciCodeERNIE 4.5 300B A47B by 12.918.631.5+12.9
- Terminal-Bench HardERNIE 4.5 300B A47B by 5.30.86.1+5.3
ReasoningERNIE 4.5 300B A47B
- GPQA DiamondERNIE 4.5 300B A47B by 43.737.481.1+43.7
- Humanity's Last Examtie4.13.3tie
- CritPttie00tie
FactsERNIE 4.5 300B A47B
- AA-Omniscience · Non-hallucinationERNIE 4.5 300B A47B by 13.619.533.1+13.6
- AA-Omniscience · AccuracyERNIE 4.5 300B A47B by 1.517.619.1+1.5
Following instructionsERNIE 4.5 300B A47B
- IFBenchERNIE 4.5 300B A47B by 336.139.1+3
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)Claude 3 Haiku by 21.121.10+21.1
- AA-OmniscienceERNIE 4.5 300B A47B by 13.5-48.6-35.1+13.5
- Artificial Analysis Coding IndexERNIE 4.5 300B A47B by 7.86.714.5+7.8
- AA Agentic IndexClaude 3 Haiku by 770+7
- AA IntelligenceERNIE 4.5 300B A47B by 1.95.67.5+1.9
Questions people ask
Which is better, Claude 3 Haiku or ERNIE 4.5 300B A47B?
ERNIE 4.5 300B A47B wins four of the five areas where both have results: coding, reasoning, facts and following instructions. Claude 3 Haiku wins long documents.
Which is better for coding?
ERNIE 4.5 300B A47B. It wins 2 of the 2 coding tests both models report; Claude 3 Haiku wins none.
Which is cheaper?
Claude 3 Haiku costs $0.25 per million input tokens and $1.25 per million output tokens; ERNIE 4.5 300B A47B costs $0.28 and $1.10. That makes ERNIE 4.5 300B A47B about 8% cheaper for the same work.
How do you compare the two?
We use the 14 benchmark tests both models have published scores on. The verdict counts the 9 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.