DeepSeek-R1-Distill-Llama-8B vs Llama 3.1 Instruct 405B
Wins 0 of 4 areas
—
Wins 4 of 4 areas
Coding · Reasoning · Long documents · Following instructions
Llama 3.1 Instruct 405B is the stronger all-rounder.
Scores updated · 14 tests both models report · How we compare
Where each one wins
Tests won in each of the four 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.
- ReasoningHard problems that need careful thinking01Llama 3.1 Instruct 405B1 of 2 tests · 1 tie
- CodingWriting and fixing software01Llama 3.1 Instruct 405B1 of 1 test
- Long documentsFinding answers in very long texts01Llama 3.1 Instruct 405B1 of 1 test
- Following instructionsDoing exactly what it is asked01Llama 3.1 Instruct 405B1 of 1 test
Coding, 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
- Follows unfamiliar, precisely checkable instructionsIFBench+21.4points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+21.3points ahead
- Code for real scientific research problemsSciCode+18points ahead
Where DeepSeek-R1-Distill-Llama-8B pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 14 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 21.330.251.5+21.3
- Humanity's Last Examtie4.24tie
Long documentsLlama 3.1 Instruct 405B
- AA-LCRLlama 3.1 Instruct 405B by 25.3025.3+25.3
Following instructionsLlama 3.1 Instruct 405B
- IFBenchLlama 3.1 Instruct 405B by 21.417.639+21.4
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.
- Arena HardLlama 3.1 Instruct 405B by 52.117.269.3+52.1
- DROPLlama 3.1 Instruct 405B by 35.149.784.8+35.1
- AIME 2024DeepSeek-R1-Distill-Llama-8B by 27.150.423.3+27.1
- GSM8KLlama 3.1 Instruct 405B by 24.672.296.8+24.6
- HumanEvalLlama 3.1 Instruct 405B by 21.567.589+21.5
- AlpacaEval-2.0Llama 3.1 Instruct 405B by 17.421.939.3+17.4
- MATH-500 (EM)DeepSeek-R1-Distill-Llama-8B by 15.389.173.8+15.3
- LiveCodeBenchDeepSeek-R1-Distill-Llama-8B by 11.939.627.7+11.9
- AA Intelligencetie6.57.3tie
Questions people ask
Which is better, DeepSeek-R1-Distill-Llama-8B or Llama 3.1 Instruct 405B?
Llama 3.1 Instruct 405B wins all four areas where both have results: coding, reasoning, long documents and following instructions. DeepSeek-R1-Distill-Llama-8B wins none.
Which is better for coding?
Llama 3.1 Instruct 405B. It wins the one coding test both models report.
How do you compare the two?
We use the 14 benchmark tests both models have published scores on. The verdict counts the 5 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.