Claude 3.5 Haiku vs MiniCPM-V 4.6 1.3B
Wins 6 of 7 areas
Coding · Agents · Facts · Images and charts · Long documents · Following instructions
Wins 0 of 7 areas
—
Claude 3.5 Haiku is the stronger all-rounder.
Scores updated · 16 tests both models report · How we compare
Where each one wins
Tests won in each of the seven 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 3.5 Haiku3 of 3 tests
- FactsGetting facts right instead of making them up20Claude 3.5 Haiku2 of 2 tests
- AgentsCarrying out multi-step tasks on its own10Claude 3.5 Haiku1 of 2 tests · 1 tie
- Images and chartsUnderstanding pictures, charts and video10Claude 3.5 Haiku1 of 1 test
- Long documentsFinding answers in very long texts10Claude 3.5 Haiku1 of 1 test
- Following instructionsDoing exactly what it is asked10Claude 3.5 Haiku1 of 1 test
- ReasoningHard problems that need careful thinking11Even1 each · 1 tie
Images and charts, 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 Claude 3.5 Haiku pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+55points ahead
- Code for real scientific research problemsSciCode+25.3points ahead
- Reasons across sets of long documentsAA-LCR+20.3points ahead
Where MiniCPM-V 4.6 1.3B pulls ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+1.5points ahead
Every test, side by side
All 16 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude 3.5 Haiku
- SciCodeClaude 3.5 Haiku by 25.327.42.1+25.3
- Terminal-Bench 2.1Claude 3.5 Haiku by 10.110.10+10.1
- Terminal-Bench HardClaude 3.5 Haiku by 2.32.30+2.3
AgentsClaude 3.5 Haiku
- τ-Bench V3 · BankingClaude 3.5 Haiku by 1.55.84.3+1.5
- GDPValtie00tie
ReasoningEven
- GPQA DiamondClaude 3.5 Haiku by 10.340.830.5+10.3
- Humanity's Last ExamMiniCPM-V 4.6 1.3B by 1.53.65.1+1.5
- CritPttie00tie
FactsClaude 3.5 Haiku
- AA-Omniscience · Non-hallucinationClaude 3.5 Haiku by 5558.93.9+55
- AA-Omniscience · AccuracyClaude 3.5 Haiku by 6.513.26.7+6.5
Images and chartsClaude 3.5 Haiku
- MMMU-ProClaude 3.5 Haiku by 7.745.637.9+7.7
Following instructionsClaude 3.5 Haiku
- IFBenchClaude 3.5 Haiku by 16.142.826.7+16.1
Other results3 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)MiniCPM-V 4.6 1.3B by 63.124.687.7+63.1
- AA-OmniscienceClaude 3.5 Haiku by 60.4-22.5-82.9+60.4
- AA IntelligenceClaude 3.5 Haiku by 3.28.95.7+3.2
Questions people ask
Which is better, Claude 3.5 Haiku or MiniCPM-V 4.6 1.3B?
Claude 3.5 Haiku wins six of the seven areas where both have results: coding, agents, facts, images and charts, long documents and following instructions. MiniCPM-V 4.6 1.3B wins none. They are level on reasoning.
Which is better for coding?
Claude 3.5 Haiku. It wins 3 of the 3 coding tests both models report; MiniCPM-V 4.6 1.3B wins none.
How do you compare the two?
We use the 16 benchmark tests both models have published scores on. The verdict counts the 13 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 3 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.