DeepSeek-V3 vs Llama 3 Instruct 70B
Wins 5 of 5 areas
Coding · Reasoning · Facts · Long documents · Following instructions
Wins 0 of 5 areas
—
DeepSeek-V3 is the stronger all-rounder.
Scores updated · 19 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 software20DeepSeek-V32 of 2 tests
- FactsGetting facts right instead of making them up20DeepSeek-V32 of 2 tests
- ReasoningHard problems that need careful thinking10DeepSeek-V31 of 3 tests · 2 ties
- Long documentsFinding answers in very long texts10DeepSeek-V31 of 1 test
- Following instructionsDoing exactly what it is asked10DeepSeek-V31 of 1 test
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.
DeepSeek-V3 costs 66% 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 DeepSeek-V3 pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+27.6points ahead
- Code for real scientific research problemsSciCode+20.1points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+14.4points ahead
Where Llama 3 Instruct 70B pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 19 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingDeepSeek-V3
- SciCodeDeepSeek-V3 by 20.13918.9+20.1
- Terminal-Bench HardDeepSeek-V3 by 14.415.20.8+14.4
ReasoningDeepSeek-V3
- GPQA DiamondDeepSeek-V3 by 27.665.537.9+27.6
- Humanity's Last Examtie4.74.5tie
- CritPttie00tie
FactsDeepSeek-V3
- AA-Omniscience · AccuracyDeepSeek-V3 by 7.825.417.7+7.8
- AA-Omniscience · Non-hallucinationDeepSeek-V3 by 1.614.112.5+1.6
Following instructionsDeepSeek-V3
- IFBenchDeepSeek-V3 by 3.94137.1+3.9
Other results10 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.
- τ²-Bench Telecom (AA run)DeepSeek-V3 by 47.147.10+47.1
- AIR-Bench 2024Llama 3 Instruct 70B by 23.840.864.6+23.8
- Artificial Analysis Coding IndexDeepSeek-V3 by 16.2236.8+16.2
- HarmBenchLlama 3 Instruct 70B by 14.349.764+14.3
- AA-OmniscienceDeepSeek-V3 by 13.6-40.7-54.3+13.6
- bbqDeepSeek-V3 by 5.796.791+5.7
- AA IntelligenceDeepSeek-V3 by 4.29.75.5+4.2
- simple_safety_testsLlama 3 Instruct 70B by 3.795.399+3.7
- anthropic_red_teamtie97.196.7tie
- XSTesttie97.196.8tie
Questions people ask
Which is better, DeepSeek-V3 or Llama 3 Instruct 70B?
DeepSeek-V3 wins all five areas where both have results: coding, reasoning, facts, long documents and following instructions. Llama 3 Instruct 70B wins none.
Which is better for coding?
DeepSeek-V3. It wins 2 of the 2 coding tests both models report; Llama 3 Instruct 70B wins none.
Which is cheaper?
DeepSeek-V3 costs $0.24 per million input tokens and $0.90 per million output tokens; Llama 3 Instruct 70B costs $0.65 and $2.75. That makes DeepSeek-V3 about 66% cheaper for the same work.
How do you compare the two?
We use the 19 benchmark tests both models have published scores on. The verdict counts the 9 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 10 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.