Claude 3.5 Haiku vs Devstral Small
Wins 1 of 6 areas
Following instructions
Wins 3 of 6 areas
Agents · Reasoning · Long documents
Devstral Small wins more areas, narrowly.Claude 3.5 Haiku is better at following instructions.
Scores updated · 15 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.
- ReasoningHard problems that need careful thinking01Devstral Small1 of 3 tests · 2 ties
- AgentsCarrying out multi-step tasks on its own01Devstral Small1 of 1 test
- Long documentsFinding answers in very long texts01Devstral Small1 of 1 test
- Following instructionsDoing exactly what it is asked10Claude 3.5 Haiku1 of 1 test
- CodingWriting and fixing software11Even1 each
- FactsGetting facts right instead of making them up11Even1 each
Agents, long documents and following instructions rest on a single test each.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Devstral Small pulls ahead
- Reasons across sets of long documentsAA-LCR+4.7points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+3.8points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+2.7points ahead
Where Claude 3.5 Haiku pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+45.3points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+11.2points ahead
- Code for real scientific research problemsSciCode+2.9points ahead
Every test, side by side
All 15 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingEven
- Terminal-Bench HardDevstral Small by 3.82.36.1+3.8
- SciCodeClaude 3.5 Haiku by 2.927.424.5+2.9
ReasoningDevstral Small
- GPQA DiamondDevstral Small by 2.640.843.4+2.6
- Humanity's Last Examtie3.64tie
- CritPttie00tie
FactsEven
- AA-Omniscience · Non-hallucinationClaude 3.5 Haiku by 45.358.913.6+45.3
- AA-Omniscience · AccuracyDevstral Small by 2.713.215.9+2.7
Following instructionsClaude 3.5 Haiku
- IFBenchClaude 3.5 Haiku by 11.242.831.6+11.2
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.
- AA-OmniscienceClaude 3.5 Haiku by 34.3-22.5-56.8+34.3
- AA Agentic IndexDevstral Small by 23.21.925.1+23.2
- τ²-Bench Telecom (AA run)Devstral Small by 13.424.638+13.4
- Artificial Analysis Coding IndexClaude 3.5 Haiku by 3.715.912.2+3.7
- AA Intelligencetie8.98.7tie
Questions people ask
Which is better, Claude 3.5 Haiku or Devstral Small?
Devstral Small wins three of the six areas where both have results: agents, reasoning and long documents. Claude 3.5 Haiku wins following instructions. They are level on coding and facts.
Which is better for coding?
Neither. They win 1 coding test each of the 2 both models report.
How do you compare the two?
We use the 15 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 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.