Compare / Nova 2 Lite vs Nova Micro 1.0

Nova 2 Lite vs Nova Micro 1.0

Which is cheaper, which is more capable, and which does better at each kind of work, from 25 results on 4 sources that measured both models.

AmazonNova 2 Lite Released 29 Oct 2025 · $0.30 in · $2.50 out
AmazonNova Micro 1.0 Released 3 Dec 2024 · $0.035 in · $0.14 out
Nova 2 Lite wins 201 too close to callNova Micro 1.0 wins 4

Of the 25 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 16 November 2026 (catalogue release 2026-11-16-49bdfa045dee).

Nova 2 Lite or Nova Micro 1.0? The short answer

Pick Nova 2 Lite if quality matters most: it scores higher (Intelligence Index 13.4 against 5.9). Pick Nova Micro 1.0 if cost matters more: it costs 14 times less per token.

  • Nova Micro 1.0 is cheaper: $0.061 against $0.85 per million tokens, 14 times less.
  • Nova 2 Lite scores higher on the Artificial Analysis Intelligence Index: 13.4 against 5.9.
  • Nova 2 Lite is newer: released 29 Oct 2025, against 3 Dec 2024 for Nova Micro 1.0.
  • On third-party benchmarks, on the results both models have: Nova 2 Lite does better for agents and tool use, reasoning and knowledge, writing and sticking to the facts.

Head to head

13.4
Intelligence Index
5.9
$0.85
Price per million tokens, blendedlower is better
$0.061
233
Output speed, tokens a second
260
1,000,000
Context window, tokens
128,000

Every fact side by side

Nova 2 LiteNova Micro 1.0
Price per million tokens$0.30 in · $2.50 out$0.035 in · $0.14 out
Blended (3 in : 1 out)$0.85$0.061
Cheapest host, blended$0.85 (Amazon Bedrock)$0.061 (Amazon Bedrock)
Intelligence Index13.45.9
Spring Prompt overall––
Output speed, tokens a second233260
Context window1,000,000 tokens128,000 tokens
Released29 Oct 2025 (newer)3 Dec 2024
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 the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.

Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 131 of 159 152 of 159
Reasoning and knowledgeHard questions across science, maths and general knowledge 117 of 187 175 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 154 of 169 166 of 169
Sticking to the factsSummarising without inventing things, and factual answers 70 of 139 19 of 139

Every shared result

Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.

MeasureNova 2 LiteNova Micro 1.0
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 214 · 295 of 387 measured 1,335 1,241
Business, management and finance · TextArena rating, higher is better 186 · 292 of 380 measured 1,351 1,233
Creative writing · TextArena rating, higher is better 248 · 297 of 385 measured 1,269 1,198
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 143 · 237 of 249 measured 13.4high reasoning 5.9
GPQA Diamond% of questions, higher is better 106 · 223 of 232 measured 81.1%high reasoning 35.8%
Humanity's Last Exam% of questions, higher is better 150 · 206 of 250 measured 11.6%high reasoning 4.6%
Berkeley Function Calling Leaderboard (BFCL) V4 reported by Berkeley Function Calling Leaderboard (BFCL) V4 · 3 results
Overall accuracy · BFCL% correct, higher is better 58 · 69 of 81 measured 27.1%bfcl fc 22.3%bfcl fc
Irrelevance detection · BFCL% correct, higher is better 40 · 61 of 81 measured 82.1%bfcl fc 70.7%bfcl fc
Memory · BFCL% correct, higher is better 73 · 73 of 81 measured 2.4%bfcl fc 2.4%bfcl fc
Vectara Hallucination Leaderboard reported by Vectara Hallucination Leaderboard · 2 results
Hallucination rate · Vectara% of summaries, lower is better 10 · 18 of 104 measured 5.1% 5.5%
Answer rate · Vectara% of documents, higher is better 45 · 1 of 104 measured 99.6% 100.0%
Show all 25 results (14 more)
MeasureNova 2 LiteNova Micro 1.0
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Expert prompts · TextArena rating, higher is better 192 · 278 of 338 measured 1,352 1,244
Instruction following · TextArena rating, higher is better 199 · 300 of 387 measured 1,327 1,215
Writing, literature and language · TextArena rating, higher is better 235 · 296 of 386 measured 1,298 1,223
Artificial Analysis reported by Artificial Analysis · 6 results
IFBench% of instructions, higher is better 50 · 184 of 195 measured 70.7%high reasoning 29.4%
Long-context reasoning (AA-LCR)% of questions, higher is better 147 · 221 of 241 measured 60.3%high reasoning 13.0%
Output speedtokens per second, higher is better 12 · 7 of 78 measured 233no reasoning 260
Terminal-Bench Hard% of tasks, higher is better 100 · 175 of 190 measured 17.4%medium reasoning 1.5%
Time to first answer tokenseconds, lower is better 19 · 8 of 78 measured 0.73no reasoning 0.55
τ²-bench telecom% of tasks, higher is better 76 · 180 of 193 measured 75.7%medium reasoning 14.0%
Berkeley Function Calling Leaderboard (BFCL) V4 reported by Berkeley Function Calling Leaderboard (BFCL) V4 · 5 results
Multi-turn tasks · BFCL% correct, higher is better 71 · 73 of 81 measured 2.1%bfcl fc 1.4%bfcl fc
Relevance detection · BFCL% correct, higher is better 49 · 36 of 81 measured 75.0%bfcl fc 81.3%bfcl fc
Single-turn calls (curated) · BFCL% correct, higher is better 27 · 65 of 81 measured 87.0%bfcl fc 74.1%bfcl fc
Single-turn calls (user-contributed) · BFCL% correct, higher is better 7 · 59 of 81 measured 80.8%bfcl fc 66.3%bfcl fc
Web search · BFCL% correct, higher is better 42 · 53 of 81 measured 5.0%bfcl fc 1.5%bfcl fc

Quick answers

Is Nova 2 Lite better than Nova Micro 1.0?

Pick Nova 2 Lite if quality matters most: it scores higher (Intelligence Index 13.4 against 5.9). Pick Nova Micro 1.0 if cost matters more: it costs 14 times less per token.

Which is cheaper, Nova 2 Lite or Nova Micro 1.0?

Nova Micro 1.0 is cheaper: $0.061 against $0.85 per million tokens, 14 times less.

Which is faster, Nova 2 Lite or Nova Micro 1.0?

Nova Micro 1.0 writes about 260 tokens a second on its usual API, against 233 for Nova 2 Lite (Artificial Analysis).

Which is better for agents and tool use, Nova 2 Lite or Nova Micro 1.0?

Nova 2 Lite ranks 131 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 152 for Nova Micro 1.0.

Which is better for reasoning and knowledge, Nova 2 Lite or Nova Micro 1.0?

Nova 2 Lite ranks 117 of 187 models on sale for hard questions across science, maths and general knowledge, against 175 for Nova Micro 1.0.

Which is better for writing, Nova 2 Lite or Nova Micro 1.0?

Nova 2 Lite ranks 154 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 166 for Nova Micro 1.0.

Which is better for sticking to the facts, Nova 2 Lite or Nova Micro 1.0?

Nova Micro 1.0 ranks 19 of 139 models on sale for summarising without inventing things, and factual answers, against 70 for Nova 2 Lite.

Which has the bigger context window, Nova 2 Lite or Nova Micro 1.0?

Nova 2 Lite: 1,000,000 tokens, against 128,000 for Nova Micro 1.0.

Run Nova 2 Lite and Nova Micro 1.0 on your own prompt.

Benchmarks aren't your task. Test both side by side on your prompt, with every answer checked against your rules and the cost of each one.