Gemma 3 12B vs Nova Lite
Wins 3 of 7 areas
Coding · Images and charts · Following instructions
Wins 2 of 7 areas
Reasoning · Long documents
Gemma 3 12B wins more areas, narrowly.Nova Lite is better at reasoning.
Scores updated · 27 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.
- CodingWriting and fixing software10Gemma 3 12B1 of 2 tests · 1 tie
- Images and chartsUnderstanding pictures, charts and video10Gemma 3 12B1 of 2 tests · 1 tie
- Following instructionsDoing exactly what it is asked10Gemma 3 12B1 of 1 test
- ReasoningHard problems that need careful thinking01Nova Lite1 of 3 tests · 2 ties
- Long documentsFinding answers in very long texts01Nova Lite1 of 1 test
- AgentsCarrying out multi-step tasks on its own00Even0 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.
Gemma 3 12B costs 33% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Gemma 3 12B pulls ahead
Where Nova Lite pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+39.8points ahead
- Reasons across sets of long documentsAA-LCR+10.7points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+8.4points ahead
Every test, side by side
All 27 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemma 3 12B
- SciCodeGemma 3 12B by 2.516.413.9+2.5
- Terminal-Bench Hardtie0.80.8tie
ReasoningNova Lite
- GPQA DiamondNova Lite by 8.434.943.3+8.4
- Humanity's Last Examtie4.24.3tie
- CritPttie00tie
FactsEven
- AA-Omniscience · Non-hallucinationNova Lite by 39.82.642.4+39.8
- Vectara HHEM hallucination ratelower is betterGemma 3 12B by 1.74.46.1+1.7
- AA-Omniscience · Accuracytie10.39.8tie
Images and chartsGemma 3 12B
Following instructionsGemma 3 12B
- IFBenchGemma 3 12B by 2.636.734.1+2.6
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.
- AA-OmniscienceNova Lite by 34.9-77.1-42.2+34.9
- TextVQANova Lite by 12.567.780.2+12.5
- ChartQANova Lite by 11.175.786.8+11.1
- τ²-Bench Telecom (AA run)Nova Lite by 6.710.817.5+6.7
- DocVQANova Lite by 5.387.192.4+5.3
- BBHGemma 3 12B by 3.385.782.4+3.3
- AA IntelligenceNova Lite by 2.93.86.7+2.9
- vectara_answer_rateNova Lite by 2.597.499.9+2.5
- vectara_avg_summary_lengthNova Lite by 2.189.791.8+2.1
- vectara_factual_consistencyGemma 3 12B by 1.795.693.9+1.7
- IFEvaltie88.989.7tie
- Artificial Analysis Coding Indextie5.85.1tie
- GSM8Ktie94.494.5tie
- HumanEvaltie85.485.4tie
Questions people ask
Which is better, Gemma 3 12B or Nova Lite?
Gemma 3 12B wins three of the seven areas where both have results: coding, images and charts and following instructions. Nova Lite wins reasoning and long documents. They are level on agents and facts.
Which is better for coding?
Gemma 3 12B. It wins 1 of the 2 coding tests both models report; Nova Lite wins none, and 1 is a tie.
Which is cheaper?
Gemma 3 12B costs $0.05 per million input tokens and $0.15 per million output tokens; Nova Lite costs $0.06 and $0.24. That makes Gemma 3 12B about 33% cheaper for the same work.
How do you compare the two?
We use the 27 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 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.