Llama 3.1 Instruct 405B vs Mistral Large 2
Wins 4 of 6 areas
Reasoning · Facts · Long documents · Following instructions
Wins 0 of 6 areas
—
Llama 3.1 Instruct 405B is the stronger all-rounder.
Scores updated · 25 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.
- FactsGetting facts right instead of making them up20Llama 3.1 Instruct 405B2 of 2 tests
- ReasoningHard problems that need careful thinking10Llama 3.1 Instruct 405B1 of 4 tests · 3 ties
- Long documentsFinding answers in very long texts10Llama 3.1 Instruct 405B1 of 1 test
- Following instructionsDoing exactly what it is asked10Llama 3.1 Instruct 405B1 of 1 test
- CodingWriting and fixing software00Even0 each · 2 ties
- AgentsCarrying out multi-step tasks on its own00Even0 each · 1 tie
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 tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Llama 3.1 Instruct 405B pulls ahead
- Reasons across sets of long documentsAA-LCR+23.3points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+15.3points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+7.8points ahead
Where Mistral Large 2 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 25 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningLlama 3.1 Instruct 405B
- GPQA DiamondLlama 3.1 Instruct 405B by 2.951.548.6+2.9
- Humanity's Last Examtie43.3tie
- SimpleBenchtie2322.5tie
- CritPttie00tie
FactsLlama 3.1 Instruct 405B
- AA-Omniscience · Non-hallucinationLlama 3.1 Instruct 405B by 15.347.632.3+15.3
- AA-Omniscience · AccuracyLlama 3.1 Instruct 405B by 3.323.219.9+3.3
Long documentsLlama 3.1 Instruct 405B
- AA-LCRLlama 3.1 Instruct 405B by 23.325.32+23.3
Following instructionsLlama 3.1 Instruct 405B
- IFBenchLlama 3.1 Instruct 405B by 7.83931.2+7.8
Other results14 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.
- AIR-Bench 2024Llama 3.1 Instruct 405B by 23.358.635.3+23.3
- AA-OmniscienceLlama 3.1 Instruct 405B by 17.3-17.1-34.4+17.3
- MMLULlama 3.1 Instruct 405B by 16.188.672.5+16.1
- τ²-Bench Telecom (AA run)Mistral Large 2 by 11.71930.7+11.7
- MATHLlama 3.1 Instruct 405B by 6.173.867.7+6.1
- AA Agentic IndexMistral Large 2 by 3.96.310.2+3.9
- GSM8KLlama 3.1 Instruct 405B by 3.896.893+3.8
- HumanEvalMistral Large 2 by 38992+3
- NarrativeQAMistral Large 2 by 374.977.9+3
- OpenBookQAtie9493.2tie
- Artificial Analysis Coding Indextie14.513.8tie
- AA Intelligencetie7.37.6tie
- naturalquestions_closedbooktie45.645.3tie
- MT-Benchtie8.58.6tie
Questions people ask
Which is better, Llama 3.1 Instruct 405B or Mistral Large 2?
Llama 3.1 Instruct 405B wins four of the six areas where both have results: reasoning, facts, long documents and following instructions. Mistral Large 2 wins none. They are level on coding and agents.
Which is better for coding?
Neither. All 2 coding tests both models report are ties.
How do you compare the two?
We use the 25 benchmark tests both models have published scores on. The verdict counts the 11 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 14 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.