Claude 3.5 Haiku vs Mistral Large 2
Wins 2 of 6 areas
Long documents · Following instructions
Wins 2 of 6 areas
Coding · Reasoning
The two are evenly matched.Claude 3.5 Haiku is better at long documents and following instructions; Mistral Large 2 at coding and reasoning.
Scores updated · 22 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 software02Mistral Large 22 of 2 tests
- ReasoningHard problems that need careful thinking01Mistral Large 21 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
- AgentsCarrying out multi-step tasks on its own00Even0 each · 1 tie
- FactsGetting facts right instead of making them up11Even1 each
Agents, 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 three tests each model wins by the widest margin. Scores are out of 100.
Where Mistral Large 2 pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+7.8points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+6.7points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+3.8points ahead
Where Claude 3.5 Haiku pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+26.6points ahead
- Reasons across sets of long documentsAA-LCR+25.3points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+11.6points ahead
Every test, side by side
All 22 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingMistral Large 2
- Terminal-Bench HardMistral Large 2 by 3.82.36.1+3.8
- SciCodeMistral Large 2 by 1.827.429.2+1.8
ReasoningMistral Large 2
- GPQA DiamondMistral Large 2 by 7.840.848.6+7.8
- Humanity's Last Examtie3.63.3tie
- CritPttie00tie
FactsEven
- AA-Omniscience · Non-hallucinationClaude 3.5 Haiku by 26.658.932.3+26.6
- AA-Omniscience · AccuracyMistral Large 2 by 6.713.219.9+6.7
Following instructionsClaude 3.5 Haiku
- IFBenchClaude 3.5 Haiku by 11.642.831.2+11.6
Other results12 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.
- MATHClaude 3.5 Haiku by 19.587.267.7+19.5
- AA-OmniscienceClaude 3.5 Haiku by 11.9-22.5-34.4+11.9
- GSM8KMistral Large 2 by 11.581.593+11.5
- naturalquestions_closedbookMistral Large 2 by 10.934.445.3+10.9
- AA Agentic IndexMistral Large 2 by 8.31.910.2+8.3
- OpenBookQAMistral Large 2 by 7.885.493.2+7.8
- τ²-Bench Telecom (AA run)Mistral Large 2 by 6.124.630.7+6.1
- MMLUMistral Large 2 by 5.467.172.5+5.4
- HumanEvalMistral Large 2 by 3.988.192+3.9
- Artificial Analysis Coding IndexClaude 3.5 Haiku by 2.115.913.8+2.1
- NarrativeQAMistral Large 2 by 1.676.377.9+1.6
- AA IntelligenceClaude 3.5 Haiku by 1.38.97.6+1.3
Questions people ask
Which is better, Claude 3.5 Haiku or Mistral Large 2?
Claude 3.5 Haiku and Mistral Large 2 each win two of the six areas where both have results. Claude 3.5 Haiku wins long documents and following instructions; Mistral Large 2 wins coding and reasoning. They are level on agents and facts.
Which is better for coding?
Mistral Large 2. It wins 2 of the 2 coding tests both models report; Claude 3.5 Haiku wins none.
How do you compare the two?
We use the 22 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 12 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.