Nova Micro vs Nova Pro
Wins 0 of 6 areas
—
Wins 3 of 6 areas
Coding · Long documents · Following instructions
Nova Pro wins more areas, narrowly.Nova Micro is cheaper.
Scores updated · 30 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 software02Nova Pro2 of 2 tests
- Long documentsFinding answers in very long texts01Nova Pro1 of 1 test
- Following instructionsDoing exactly what it is asked01Nova Pro1 of 1 test
- AgentsCarrying out multi-step tasks on its own00Even0 each · 1 tie
- ReasoningHard problems that need careful thinking11Even1 each · 1 tie
- FactsGetting facts right instead of making them up11Even1 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 96% 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 Nova Pro pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+14.1points ahead
- Code for real scientific research problemsSciCode+11.4points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+8.7points ahead
Where Nova Micro pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+12.6points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+1.4points ahead
Every test, side by side
All 30 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingNova Pro
- SciCodeNova Pro by 11.49.420.8+11.4
- Terminal-Bench HardNova Pro by 4.61.56.1+4.6
ReasoningEven
- GPQA DiamondNova Pro by 14.135.849.9+14.1
- Humanity's Last ExamNova Micro by 1.44.63.2+1.4
- CritPttie00tie
FactsEven
- AA-Omniscience · Non-hallucinationNova Micro by 12.634.922.3+12.6
- AA-Omniscience · AccuracyNova Pro by 6.91016.9+6.9
- Vectara HHEM hallucination ratelower is bettertie5.55.1tie
Other results19 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 33.810066.2+33.8
- BFCLv4Nova Pro by 12.256.268.4+12.2
- naturalquestions_closedbookNova Pro by 1228.540.5+12
- MMLUNova Pro by 11.86475.8+11.8
- HumanEvalNova Pro by 7.981.189+7.9
- BBHNova Pro by 7.479.586.9+7.4
- OpenBookQANova Pro by 7.288.896+7.2
- Artificial Analysis Coding IndexNova Pro by 6.94.111+6.9
- DROPNova Pro by 6.179.385.4+6.1
- IFEvalNova Pro by 4.987.292.1+4.9
- NarrativeQANova Pro by 4.774.479.1+4.7
- ARC-ChallengeNova Pro by 4.690.294.8+4.6
- GSM8KNova Pro by 2.592.394.8+2.5
- AA IntelligenceNova Pro by 1.15.97+1.1
- AA-Omnisciencetie-48.5-47.7tie
- vectara_answer_ratetie10099.3tie
- vectara_factual_consistencytie94.594.9tie
- AA Agentic Indextie4.74.7tie
- τ²-Bench Telecom (AA run)tie1414tie
Questions people ask
Which is better, Nova Micro or Nova Pro?
Nova Pro wins three of the six areas where both have results: coding, long documents and following instructions. Nova Micro wins none, but costs 96% less. They are level on agents, reasoning and facts.
Which is better for coding?
Nova Pro. It wins 2 of the 2 coding tests both models report; Nova Micro wins none.
Which is cheaper?
Nova Micro costs $0.04 per million input tokens and $0.14 per million output tokens; Nova Pro costs $0.80 and $3.20. That makes Nova Micro about 96% cheaper for the same work.
How do you compare the two?
We use the 30 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 19 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.