Gemma 3 27B vs Nova Pro
Wins 1 of 7 areas
Images and charts
Wins 3 of 7 areas
Facts · Long documents · Following instructions
Nova Pro wins more areas, narrowly.Gemma 3 27B is cheaper and better at images and charts.
Scores updated · 29 tests both models report · How we compare
Where each one wins
Tests won in each of the seven 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.
- FactsGetting facts right instead of making them up03Nova Pro3 of 3 tests
- Long documentsFinding answers in very long texts01Nova Pro1 of 1 test
- Following instructionsDoing exactly what it is asked01Nova Pro1 of 1 test
- Images and chartsUnderstanding pictures, charts and video20Gemma 3 27B2 of 2 tests
- CodingWriting and fixing software11Even1 each
- 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.
Gemma 3 27B costs 94% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Nova Pro pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+14.4points ahead
- Reasons across sets of long documentsAA-LCR+13.7points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+7.1points ahead
Every test, side by side
All 29 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingEven
- SciCodeGemma 3 27B by 2.523.320.8+2.5
- Terminal-Bench HardNova Pro by 2.33.86.1+2.3
ReasoningEven
- GPQA DiamondNova Pro by 7.142.849.9+7.1
- Humanity's Last ExamGemma 3 27B by 1.24.43.2+1.2
- CritPttie00tie
FactsNova Pro
- AA-Omniscience · Non-hallucinationNova Pro by 14.47.922.3+14.4
- AA-Omniscience · AccuracyNova Pro by 3.912.916.9+3.9
- Vectara HHEM hallucination ratelower is betterNova Pro by 2.37.45.1+2.3
Images and chartsGemma 3 27B
Other results16 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_lengthGemma 3 27B by 30.296.466.2+30.2
- AA-OmniscienceNova Pro by 19.5-67.2-47.7+19.5
- TextVQANova Pro by 16.465.181.5+16.4
- ChartQANova Pro by 11.27889.2+11.2
- DocVQANova Pro by 6.986.693.5+6.9
- MATHGemma 3 27B by 6.98982.1+6.9
- τ²-Bench Telecom (AA run)Nova Pro by 3.510.514+3.5
- vectara_factual_consistencyNova Pro by 2.392.694.9+2.3
- AA IntelligenceNova Pro by 2.14.97+2.1
- IFEvalNova Pro by 1.790.492.1+1.7
- HumanEvalNova Pro by 1.287.889+1.2
- GSM8KGemma 3 27B by 1.195.994.8+1.1
- MMLUGemma 3 27B by 1.176.975.8+1.1
- Artificial Analysis Coding Indextie10.111tie
- BBHtie87.686.9tie
- vectara_answer_ratetie98.899.3tie
Questions people ask
Which is better, Gemma 3 27B or Nova Pro?
Nova Pro wins three of the seven areas where both have results: facts, long documents and following instructions. Gemma 3 27B wins images and charts, and costs 94% less. They are level on coding, agents and reasoning.
Which is better for coding?
Neither. They win 1 coding test each of the 2 both models report.
Which is cheaper?
Gemma 3 27B costs $0.08 per million input tokens and $0.16 per million output tokens; Nova Pro costs $0.80 and $3.20. That makes Gemma 3 27B about 94% cheaper for the same work.
How do you compare the two?
We use the 29 benchmark tests both models have published scores on. The verdict counts the 13 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 16 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.