Granite 3.3 8B Instruct vs Llama 3.1 70B Instruct
Wins 0 of 6 areas
—
Wins 5 of 6 areas
Coding · Reasoning · Facts · Long documents · Following instructions
Llama 3.1 70B Instruct is the stronger all-rounder.Granite 3.3 8B Instruct is cheaper.
Scores updated · 28 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 software02Llama 3.1 70B Instruct2 of 2 tests
- FactsGetting facts right instead of making them up02Llama 3.1 70B Instruct2 of 2 tests
- ReasoningHard problems that need careful thinking01Llama 3.1 70B Instruct1 of 3 tests · 2 ties
- Long documentsFinding answers in very long texts01Llama 3.1 70B Instruct1 of 1 test
- Following instructionsDoing exactly what it is asked01Llama 3.1 70B Instruct1 of 1 test
- 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.
Granite 3.3 8B Instruct costs 75% less for the same work.
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 70B Instruct pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+18points ahead
- Code for real scientific research problemsSciCode+16.6points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+12points ahead
Where Granite 3.3 8B Instruct pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 28 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingLlama 3.1 70B Instruct
- SciCodeLlama 3.1 70B Instruct by 16.610.126.7+16.6
- Terminal-Bench HardLlama 3.1 70B Instruct by 303+3
ReasoningLlama 3.1 70B Instruct
- GPQA DiamondLlama 3.1 70B Instruct by 7.133.840.9+7.1
- Humanity's Last Examtie4.24.5tie
- CritPttie00tie
FactsLlama 3.1 70B Instruct
- AA-Omniscience · Non-hallucinationLlama 3.1 70B Instruct by 183.821.8+18
- AA-Omniscience · AccuracyLlama 3.1 70B Instruct by 109.719.7+10
Long documentsLlama 3.1 70B Instruct
- AA-LCRLlama 3.1 70B Instruct by 4.73.38+4.7
Following instructionsLlama 3.1 70B Instruct
- IFBenchLlama 3.1 70B Instruct by 1222.434.4+12
Other results18 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 2024Granite 3.3 8B Instruct by 4082.542.5+40
- HarmBenchGranite 3.3 8B Instruct by 34.381.246.9+34.3
- AA-OmniscienceLlama 3.1 70B Instruct by 34.2-77.3-43.1+34.2
- AlpacaEval-2.0Granite 3.3 8B Instruct by 28.462.734.3+28.4
- MMLULlama 3.1 70B Instruct by 20.565.586+20.5
- DROPLlama 3.1 70B Instruct by 20.259.479.6+20.2
- GSM8KLlama 3.1 70B Instruct by 12.980.993.8+12.9
- IFEvalLlama 3.1 70B Instruct by 12.774.887.5+12.7
- BBHLlama 3.1 70B Instruct by 12.569.181.6+12.5
- HumanEvalGranite 3.3 8B Instruct by 9.289.780.5+9.2
- Artificial Analysis Coding IndexLlama 3.1 70B Instruct by 7.53.410.9+7.5
- anthropic_red_teamGranite 3.3 8B Instruct by 5.999.193.2+5.9
- simple_safety_testsGranite 3.3 8B Instruct by 597.592.5+5
- τ²-Bench Telecom (AA run)Llama 3.1 70B Instruct by 4.710.515.2+4.7
- XSTestLlama 3.1 70B Instruct by 3.890.794.5+3.8
- Arena HardGranite 3.3 8B Instruct by 1.957.655.7+1.9
- AA IntelligenceLlama 3.1 70B Instruct by 1.74.96.6+1.7
- AA Agentic IndexLlama 3.1 70B Instruct by 1.63.55.1+1.6
Questions people ask
Which is better, Granite 3.3 8B Instruct or Llama 3.1 70B Instruct?
Llama 3.1 70B Instruct wins five of the six areas where both have results: coding, reasoning, facts, long documents and following instructions. Granite 3.3 8B Instruct wins none, but costs 75% less. They are level on agents.
Which is better for coding?
Llama 3.1 70B Instruct. It wins 2 of the 2 coding tests both models report; Granite 3.3 8B Instruct wins none.
Which is cheaper?
Granite 3.3 8B Instruct costs $0.03 per million input tokens and $0.25 per million output tokens; Llama 3.1 70B Instruct costs $0.56 and $0.56. That makes Granite 3.3 8B Instruct about 75% cheaper for the same work.
How do you compare the two?
We use the 28 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 18 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.