Compare / Nova Pro 1.0 vs Gemini 3.1 Flash Lite Preview

Nova Pro 1.0 vs Gemini 3.1 Flash Lite Preview

Which is cheaper, which is more capable, and which does better at each kind of work, from 15 results on 3 sources that measured both models.

Nova Pro 1.0
Amazon · profile
Gemini 3.1 Flash Lite Preview
Google · profile
Results compared
15
Shared sources
3

Nova Pro 1.0 or Gemini 3.1 Flash Lite Preview? The short answer

  • Gemini 3.1 Flash Lite Preview is cheaper: $0.56 against $1.40 per million tokens, 2.5 times less.
  • Gemini 3.1 Flash Lite Preview scores higher on the Artificial Analysis Intelligence Index: 15.6 against 7.0.
  • On our business benchmarks, Nova Pro 1.0 ranks higher for sticking to the facts.
  • On our business benchmarks, Gemini 3.1 Flash Lite Preview ranks higher for agents and tool use, reasoning and knowledge and writing.

At a glance

Nova Pro 1.0Gemini 3.1 Flash Lite Preview
Price per million tokens$0.80 in · $3.20 out$0.25 in · $1.50 out
Blended (3 in : 1 out)$1.40$0.56
Cheapest host, blended$1.40 (Amazon Bedrock)$0.28 (Google AI Studio)
Intelligence Index7.015.6
Spring Prompt overall––
Output speed, tokens a second––
Context window300,000 tokens1,048,576 tokens
WeightsClosedClosed
Developer based inthe USthe US

Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.

Which is better for what

Each model's rank among models available today, for each kind of work, from our own benchmarks and licensed sources. The better rank is in green.

Use caseNova Pro 1.0Gemini 3.1 Flash Lite Preview
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 152 of 161 93 of 161
Reasoning and knowledgeHard questions across science, maths and general knowledge 186 of 195 99 of 195
WritingWhat people prefer in blind comparisons, and judged writing quality 173 of 187 78 of 187
Sticking to the factsSummarising without inventing things, and factual answers 11 of 153 73 of 153

Every shared result

BenchmarkMetricNova Pro 1.0Gemini 3.1 Flash Lite Preview
Arena (formerly LMArena)reportedBusiness, management and financeArena rating 1,2791,421
Arena (formerly LMArena)reportedCreative writingArena rating 1,2371,413
Arena (formerly LMArena)reportedExpert promptsArena rating 1,2731,443
Arena (formerly LMArena)reportedInstruction followingArena rating 1,2771,407
Arena (formerly LMArena)reportedOverallArena rating 1,2901,433
Arena (formerly LMArena)reportedWriting, literature and languageArena rating 1,2741,420
Artificial AnalysisreportedArtificial Analysis Intelligence Indexindex score 7.0015.6
Artificial AnalysisreportedGPQA Diamond% of questions 49.9%82.2%
Artificial AnalysisreportedHumanity's Last Exam% of questions 3.2%17.2%
Artificial AnalysisreportedIFBench% of instructions 38.1%77.2%
Artificial AnalysisreportedLong-context reasoning (AA-LCR)% of questions 21.0%74.3%
Artificial AnalysisreportedTerminal-Bench Hard% of tasks 6.1%24.2%
Artificial AnalysisreportedΤ²-bench telecom% of tasks 14.0%31.3%
Vectara Hallucination LeaderboardreportedAnswer rate% of documents 99.3%99.6%
Vectara Hallucination LeaderboardreportedHallucination rate% of summaries 5.1%8.2%

Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.

Quick answers

Is Nova Pro 1.0 better than Gemini 3.1 Flash Lite Preview?

It depends on the task. Among models available today, on our benchmarks and licensed sources, Nova Pro 1.0 ranks higher for sticking to the facts; Gemini 3.1 Flash Lite Preview ranks higher for agents and tool use, reasoning and knowledge and writing.

Which is cheaper, Nova Pro 1.0 or Gemini 3.1 Flash Lite Preview?

Gemini 3.1 Flash Lite Preview costs $0.56 per million tokens (three input to one output), against $1.40 for Nova Pro 1.0.

Run Nova Pro 1.0 and Gemini 3.1 Flash Lite Preview on your own prompt

Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.