Gemini 3.1 Flash Lite Preview vs Nova 2.0 Lite
Wins 7 of 7 areas
Coding · Agents · Reasoning · Facts · Images and charts · Long documents · Following instructions
Wins 0 of 7 areas
—
Gemini 3.1 Flash Lite Preview is the stronger all-rounder.
Scores updated · 22 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 software30Gemini 3.1 Flash Lite Preview3 of 3 tests
- ReasoningHard problems that need careful thinking20Gemini 3.1 Flash Lite Preview2 of 3 tests · 1 tie
- FactsGetting facts right instead of making them up21Gemini 3.1 Flash Lite Preview2 of 3 tests
- AgentsCarrying out multi-step tasks on its own10Gemini 3.1 Flash Lite Preview1 of 2 tests · 1 tie
- Images and chartsUnderstanding pictures, charts and video10Gemini 3.1 Flash Lite Preview1 of 1 test
- Long documentsFinding answers in very long texts10Gemini 3.1 Flash Lite Preview1 of 1 test
- Following instructionsDoing exactly what it is asked10Gemini 3.1 Flash Lite Preview1 of 1 test
Images and charts, 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.
Gemini 3.1 Flash Lite Preview costs 38% 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 Gemini 3.1 Flash Lite Preview pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+17.3points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+15points ahead
- Reasons across sets of long documentsAA-LCR+14points ahead
Where Nova 2.0 Lite pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 22 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 3.1 Flash Lite Preview
- Terminal-Bench 2.1Gemini 3.1 Flash Lite Preview by 1531.116.1+15
- Terminal-Bench HardGemini 3.1 Flash Lite Preview by 7.524.216.7+7.5
- SciCodeGemini 3.1 Flash Lite Preview by 6.543.436.9+6.5
AgentsGemini 3.1 Flash Lite Preview
- τ-Bench V3 · BankingGemini 3.1 Flash Lite Preview by 2.99.76.8+2.9
- GDPValtie00tie
ReasoningGemini 3.1 Flash Lite Preview
- Humanity's Last ExamGemini 3.1 Flash Lite Preview by 5.617.211.6+5.6
- GPQA DiamondGemini 3.1 Flash Lite Preview by 1.182.281.1+1.1
- CritPttie1.10.3tie
FactsGemini 3.1 Flash Lite Preview
- AA-Omniscience · AccuracyGemini 3.1 Flash Lite Preview by 17.336.319+17.3
- AA-Omniscience · Non-hallucinationGemini 3.1 Flash Lite Preview by 8.717.38.6+8.7
- Vectara HHEM hallucination ratelower is betterNova 2.0 Lite by 3.18.25.1+3.1
Images and chartsGemini 3.1 Flash Lite Preview
- MMMU-ProGemini 3.1 Flash Lite Preview by 11.775.563.8+11.7
Long documentsGemini 3.1 Flash Lite Preview
- AA-LCRGemini 3.1 Flash Lite Preview by 1474.360.3+14
Following instructionsGemini 3.1 Flash Lite Preview
- IFBenchGemini 3.1 Flash Lite Preview by 6.577.270.7+6.5
Other results8 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.
- τ²-Bench Telecom (AA run)Nova 2.0 Lite by 41.531.372.8+41.5
- AA-OmniscienceGemini 3.1 Flash Lite Preview by 38.6-16.4-55+38.6
- vectara_avg_summary_lengthNova 2.0 Lite by 31.562.694.1+31.5
- Artificial Analysis Coding IndexGemini 3.1 Flash Lite Preview by 11.734.723+11.7
- vectara_factual_consistencyNova 2.0 Lite by 3.191.894.9+3.1
- AA IntelligenceGemini 3.1 Flash Lite Preview by 2.215.613.4+2.2
- AA Agentic Indextie3.23.1tie
- vectara_answer_ratetie99.699.6tie
Questions people ask
Which is better, Gemini 3.1 Flash Lite Preview or Nova 2.0 Lite?
Gemini 3.1 Flash Lite Preview wins all seven areas where both have results: coding, agents, reasoning, facts, images and charts, long documents and following instructions. Nova 2.0 Lite wins none.
Which is better for coding?
Gemini 3.1 Flash Lite Preview. It wins 3 of the 3 coding tests both models report; Nova 2.0 Lite wins none.
Which is cheaper?
Gemini 3.1 Flash Lite Preview costs $0.25 per million input tokens and $1.50 per million output tokens; Nova 2.0 Lite costs $0.30 and $2.50. That makes Gemini 3.1 Flash Lite Preview about 38% cheaper for the same work.
How do you compare the two?
We use the 22 benchmark tests both models have published scores on. The verdict counts the 14 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 8 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.