Claude 3.5 Haiku vs Gemma 3 270M
Wins 4 of 5 areas
Coding · Reasoning · Long documents · Following instructions
Wins 1 of 5 areas
Facts
Claude 3.5 Haiku is the stronger all-rounder.Gemma 3 270M is better at facts.
Scores updated · 13 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 3.5 Haiku2 of 2 tests
- ReasoningHard problems that need careful thinking10Claude 3.5 Haiku1 of 3 tests · 2 ties
- 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
- FactsGetting facts right instead of making them up01Gemma 3 270M1 of 1 test
Facts, 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
- Follows unfamiliar, precisely checkable instructionsIFBench+30.7points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+18.4points ahead
Where Gemma 3 270M pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+10.7points ahead
Every test, side by side
All 13 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 27.427.40+27.4
- Terminal-Bench HardClaude 3.5 Haiku by 2.32.30+2.3
ReasoningClaude 3.5 Haiku
- GPQA DiamondClaude 3.5 Haiku by 18.440.822.4+18.4
- CritPttie00tie
- Humanity's Last Examtie3.63.6tie
FactsGemma 3 270M
- AA-Omniscience · Non-hallucinationGemma 3 270M by 10.758.969.6+10.7
Following instructionsClaude 3.5 Haiku
- IFBenchClaude 3.5 Haiku by 30.742.812.1+30.7
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.
- Artificial Analysis Coding IndexClaude 3.5 Haiku by 15.915.90+15.9
- τ²-Bench Telecom (AA run)Claude 3.5 Haiku by 15.524.69.1+15.5
- AA-OmniscienceClaude 3.5 Haiku by 6.8-22.5-29.3+6.8
- AA IntelligenceClaude 3.5 Haiku by 3.88.95.1+3.8
- AA Agentic IndexGemma 3 270M by 1.11.93+1.1
Questions people ask
Which is better, Claude 3.5 Haiku or Gemma 3 270M?
Claude 3.5 Haiku wins four of the five areas where both have results: coding, reasoning, long documents and following instructions. Gemma 3 270M wins facts.
Which is better for coding?
Claude 3.5 Haiku. It wins 2 of the 2 coding tests both models report; Gemma 3 270M wins none.
How do you compare the two?
We use the 13 benchmark tests both models have published scores on. The verdict counts the 8 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.