DeepSeek-V3 vs Llama 3.1 Nemotron Instruct 70B
Wins 4 of 6 areas
Coding · Reasoning · Long documents · Following instructions
Wins 0 of 6 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 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 software20DeepSeek-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
- 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 tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where DeepSeek-V3 pulls ahead
- Reasons across sets of long documentsAA-LCR+32.4points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+19points ahead
- Code for real scientific research problemsSciCode+15.7points ahead
Where Llama 3.1 Nemotron Instruct 70B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+14.6points ahead
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 15.73923.3+15.7
- Terminal-Bench HardDeepSeek-V3 by 10.715.24.5+10.7
ReasoningDeepSeek-V3
- GPQA DiamondDeepSeek-V3 by 1965.546.5+19
- Humanity's Last Examtie4.74.2tie
- CritPttie00tie
FactsEven
- AA-Omniscience · Non-hallucinationLlama 3.1 Nemotron Instruct 70B by 14.614.128.7+14.6
- AA-Omniscience · AccuracyDeepSeek-V3 by 7.725.417.8+7.7
Following instructionsDeepSeek-V3
- IFBenchDeepSeek-V3 by 10.34130.7+10.3
Other results9 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.
- ARC-ChallengeDeepSeek-V3 by 26.195.369.2+26.1
- τ²-Bench Telecom (AA run)DeepSeek-V3 by 2447.123.1+24
- Artificial Analysis Coding IndexDeepSeek-V3 by 12.22310.8+12.2
- Arena HardDeepSeek-V3 by 6.491.485+6.4
- HellaSwagDeepSeek-V3 by 3.388.985.6+3.3
- AA IntelligenceDeepSeek-V3 by 2.89.76.9+2.8
- GSM8KDeepSeek-V3 by 2.69491.4+2.6
- WinoGrandetie84.984.5tie
- AA-Omnisciencetie-40.7-40.8tie
Questions people ask
Which is better, DeepSeek-V3 or Llama 3.1 Nemotron Instruct 70B?
DeepSeek-V3 wins four of the six areas where both have results: coding, reasoning, long documents and following instructions. Llama 3.1 Nemotron Instruct 70B wins none. They are level on agents and facts.
Which is better for coding?
DeepSeek-V3. It wins 2 of the 2 coding tests both models report; Llama 3.1 Nemotron Instruct 70B wins none.
How do you compare the two?
We use the 19 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 9 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.