Llama 3.3 70B Instruct vs Nova Micro
Wins 4 of 6 areas
Coding · Facts · Long documents · Following instructions
Wins 0 of 6 areas
—
Llama 3.3 70B Instruct is the stronger all-rounder.Nova Micro is cheaper.
Scores updated · 26 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 software20Llama 3.3 70B Instruct2 of 2 tests
- FactsGetting facts right instead of making them up21Llama 3.3 70B Instruct2 of 3 tests
- Long documentsFinding answers in very long texts10Llama 3.3 70B Instruct1 of 1 test
- Following instructionsDoing exactly what it is asked10Llama 3.3 70B Instruct1 of 1 test
- AgentsCarrying out multi-step tasks on its own00Even0 each · 1 tie
- ReasoningHard problems that need careful thinking11Even1 each · 1 tie
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.
Nova Micro costs 88% 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 Llama 3.3 70B Instruct pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+17.7points ahead
- Code for real scientific research problemsSciCode+16.6points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+14points ahead
Where Nova Micro pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+25.1points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+1points ahead
Every test, side by side
All 26 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingLlama 3.3 70B Instruct
- SciCodeLlama 3.3 70B Instruct by 16.6269.4+16.6
- Terminal-Bench HardLlama 3.3 70B Instruct by 1.531.5+1.5
ReasoningEven
- GPQA DiamondLlama 3.3 70B Instruct by 1449.835.8+14
- Humanity's Last ExamNova Micro by 13.64.6+1
- CritPttie00tie
FactsLlama 3.3 70B Instruct
- AA-Omniscience · Non-hallucinationNova Micro by 25.19.834.9+25.1
- AA-Omniscience · AccuracyLlama 3.3 70B Instruct by 918.910+9
- Vectara HHEM hallucination ratelower is betterLlama 3.3 70B Instruct by 1.44.15.5+1.4
Long documentsLlama 3.3 70B Instruct
- AA-LCRLlama 3.3 70B Instruct by 2.715.713+2.7
Following instructionsLlama 3.3 70B Instruct
- IFBenchLlama 3.3 70B Instruct by 17.747.129.4+17.7
Other results15 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.
- vectara_avg_summary_lengthNova Micro by 35.464.6100+35.4
- MMLULlama 3.3 70B Instruct by 228664+22
- naturalquestions_closedbookLlama 3.3 70B Instruct by 14.643.128.5+14.6
- τ²-Bench Telecom (AA run)Llama 3.3 70B Instruct by 12.626.614+12.6
- DROPLlama 3.3 70B Instruct by 10.990.279.3+10.9
- Artificial Analysis Coding IndexLlama 3.3 70B Instruct by 7.811.94.1+7.8
- HumanEvalLlama 3.3 70B Instruct by 7.388.481.1+7.3
- AA-OmniscienceNova Micro by 5.7-54.2-48.5+5.7
- IFEvalLlama 3.3 70B Instruct by 4.992.187.2+4.9
- NarrativeQALlama 3.3 70B Instruct by 4.779.174.4+4.7
- OpenBookQALlama 3.3 70B Instruct by 492.888.8+4
- GSM8KLlama 3.3 70B Instruct by 1.994.292.3+1.9
- AA IntelligenceLlama 3.3 70B Instruct by 1.87.75.9+1.8
- vectara_factual_consistencyLlama 3.3 70B Instruct by 1.495.994.5+1.4
- vectara_answer_ratetie99.5100tie
Questions people ask
Which is better, Llama 3.3 70B Instruct or Nova Micro?
Llama 3.3 70B Instruct wins four of the six areas where both have results: coding, facts, long documents and following instructions. Nova Micro wins none, but costs 88% less. They are level on agents and reasoning.
Which is better for coding?
Llama 3.3 70B Instruct. It wins 2 of the 2 coding tests both models report; Nova Micro wins none.
Which is cheaper?
Llama 3.3 70B Instruct costs $0.71 per million input tokens and $0.72 per million output tokens; Nova Micro costs $0.04 and $0.14. That makes Nova Micro about 88% cheaper for the same work.
How do you compare the two?
We use the 26 benchmark tests both models have published scores on. The verdict counts the 11 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 15 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.