DeepSeek-R1-Distill-Llama-8B vs DeepSeek-R1-Distill-Qwen-7B
Wins 0 of 1 area
—
Wins 1 of 1 area
Reasoning
DeepSeek-R1-Distill-Qwen-7B is the stronger all-rounder.DeepSeek-R1-Distill-Llama-8B is cheaper.
Scores updated · 15 tests both models report · How we compare
Where each one wins
Tests won in each of the one area 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.
Reasoning rests on a single test.
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-R1-Distill-Llama-8B costs 67% 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-R1-Distill-Qwen-7B pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+18.9points 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 15 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningDeepSeek-R1-Distill-Qwen-7B
- GPQA DiamondDeepSeek-R1-Distill-Qwen-7B by 18.930.249.1+18.9
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.
- HumanEval+DeepSeek-R1-Distill-Qwen-7B by 15.562.978.4+15.5
- HumanEvalDeepSeek-R1-Distill-Qwen-7B by 12.467.579.9+12.4
- Arena HardDeepSeek-R1-Distill-Llama-8B by 6.817.210.4+6.8
- AlpacaEval-2.0DeepSeek-R1-Distill-Llama-8B by 6.521.915.3+6.5
- GSM8KDeepSeek-R1-Distill-Qwen-7B by 6.372.278.5+6.3
- AIME 2024DeepSeek-R1-Distill-Qwen-7B by 5.150.455.5+5.1
- MATH-500 (EM)DeepSeek-R1-Distill-Qwen-7B by 3.789.192.8+3.7
- PopQADeepSeek-R1-Distill-Llama-8B by 3.413.39.9+3.4
- DROPDeepSeek-R1-Distill-Qwen-7B by 2.149.751.8+2.1
- LiveCodeBenchDeepSeek-R1-Distill-Llama-8B by 239.637.6+2
- Codeforces (Rating)DeepSeek-R1-Distill-Llama-8B by 16 rating points12051189+16 rating
- AttaQtie42.942.5tie
- TruthfulQAtie47.447.1tie
- BigBenchHardtie67.467.4tie
Questions people ask
Which is better, DeepSeek-R1-Distill-Llama-8B or DeepSeek-R1-Distill-Qwen-7B?
DeepSeek-R1-Distill-Qwen-7B wins the one area where both have results: reasoning. DeepSeek-R1-Distill-Llama-8B wins none, but costs 67% less.
Which is cheaper?
DeepSeek-R1-Distill-Llama-8B costs $0.05 per million input tokens and $0.05 per million output tokens; DeepSeek-R1-Distill-Qwen-7B costs $0.15 and $0.15. That makes DeepSeek-R1-Distill-Llama-8B about 67% cheaper for the same work.
How do you compare the two?
We use the 15 benchmark tests both models have published scores on. The verdict counts the 1 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.