Scores updated · 12 tests both models report · How we compare
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$0.05 to read · $0.05 to writePrice from nscale
Granite 3.1 8B InstructNo current price is tracked.
Every test, side by side
All 12 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results12 tests
- AIME 2024DeepSeek-R1-Distill-Llama-8B by 48.450.42+48.4
- AttaQGranite 3.1 8B Instruct by 42.842.985.7+42.8
- MATH-500 (EM)DeepSeek-R1-Distill-Llama-8B by 40.489.148.7+40.4
- HumanEval+Granite 3.1 8B Instruct by 22.962.985.8+22.9
- HumanEvalGranite 3.1 8B Instruct by 22.167.589.6+22.1
- Arena HardGranite 3.1 8B Instruct by 20.417.237.6+20.4
- TruthfulQAGranite 3.1 8B Instruct by 18.447.465.8+18.4
- PopQAGranite 3.1 8B Instruct by 15.413.328.7+15.4
- DROPGranite 3.1 8B Instruct by 8.949.758.6+8.9
- AlpacaEval-2.0Granite 3.1 8B Instruct by 8.421.930.3+8.4
- GSM8KGranite 3.1 8B Instruct by 772.279.2+7
- BigBenchHardGranite 3.1 8B Instruct by 2.567.469.9+2.5
Questions people ask
How do you compare the two?
We use the 12 benchmark tests both models have published scores on. None of them is in the eight capability areas we count, so this page lists them without a verdict. Each score is the one shown on the model's own page.