Claude 3.5 Haiku vs Llama 3.2 Instruct 11B (Vision)
Wins 5 of 6 areas
Coding · Facts · Images and charts · Long documents · Following instructions
Wins 0 of 6 areas
—
Claude 3.5 Haiku is the stronger all-rounder.
Scores updated · 21 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 software20Claude 3.5 Haiku2 of 2 tests
- FactsGetting facts right instead of making them up20Claude 3.5 Haiku2 of 2 tests
- 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.
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 3.5 Haiku pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+40.8points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+18.7points ahead
- Harder college exam questions with imagesMMMU-Pro+16.3points ahead
Where Llama 3.2 Instruct 11B (Vision) pulls ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+1.9points ahead
Every test, side by side
All 21 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 16.227.411.2+16.2
- Terminal-Bench HardClaude 3.5 Haiku by 1.52.30.8+1.5
ReasoningEven
- GPQA DiamondClaude 3.5 Haiku by 18.740.822.1+18.7
- Humanity's Last ExamLlama 3.2 Instruct 11B (Vision) by 1.93.65.5+1.9
- CritPttie00tie
FactsClaude 3.5 Haiku
- AA-Omniscience · Non-hallucinationClaude 3.5 Haiku by 40.858.918.1+40.8
- AA-Omniscience · AccuracyClaude 3.5 Haiku by 2.613.210.6+2.6
Images and chartsClaude 3.5 Haiku
- MMMU-ProClaude 3.5 Haiku by 16.345.629.3+16.3
Long documentsClaude 3.5 Haiku
- AA-LCRClaude 3.5 Haiku by 14.627.312.7+14.6
Following instructionsClaude 3.5 Haiku
- IFBenchClaude 3.5 Haiku by 12.442.830.4+12.4
Other results11 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 3.5 Haiku by 40.1-22.5-62.6+40.1
- MMLUClaude 3.5 Haiku by 1667.151.1+16
- MATHClaude 3.5 Haiku by 13.387.273.9+13.3
- OpenBookQAClaude 3.5 Haiku by 1385.472.4+13
- Artificial Analysis Coding IndexClaude 3.5 Haiku by 11.715.94.2+11.7
- naturalquestions_closedbookClaude 3.5 Haiku by 1134.423.4+11
- τ²-Bench Telecom (AA run)Claude 3.5 Haiku by 1024.614.6+10
- AA IntelligenceClaude 3.5 Haiku by 3.58.95.4+3.5
- AA Agentic IndexLlama 3.2 Instruct 11B (Vision) by 31.94.9+3
- GSM8Ktie81.582.3tie
- NarrativeQAtie76.375.6tie
Questions people ask
Which is better, Claude 3.5 Haiku or Llama 3.2 Instruct 11B (Vision)?
Claude 3.5 Haiku wins five of the six areas where both have results: coding, facts, images and charts, long documents and following instructions. Llama 3.2 Instruct 11B (Vision) wins none. They are level on reasoning.
Which is better for coding?
Claude 3.5 Haiku. It wins 2 of the 2 coding tests both models report; Llama 3.2 Instruct 11B (Vision) wins none.
How do you compare the two?
We use the 21 benchmark tests both models have published scores on. The verdict counts the 10 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 11 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.