Compare / Nova Micro 1.0 vs Gemma 3 4B

Nova Micro 1.0 vs Gemma 3 4B

Which is cheaper, which is more capable, and which does better at each kind of work, from 23 results on 4 sources that measured both models.

AmazonNova Micro 1.0 Released 3 Dec 2024 · $0.035 in · $0.14 out
GoogleGemma 3 4B Released 11 Mar 2025 · $0.040 in · $0.050 out
Nova Micro 1.0 wins 141 too close to callGemma 3 4B wins 8

Of the 23 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). See also Amazon vs Google, every model from both labs.

Nova Micro 1.0 or Gemma 3 4B? The short answer

They score about the same, so pick Gemma 3 4B: it costs 31% less per token.

  • Gemma 3 4B is cheaper: $0.042 against $0.061 per million tokens, 31% less.
  • Nova Micro 1.0 scores higher on the Artificial Analysis Intelligence Index: 5.9 against 4.8.
  • Gemma 3 4B is newer: released 11 Mar 2025, against 3 Dec 2024 for Nova Micro 1.0.
  • On third-party benchmarks, on the results both models have: Nova Micro 1.0 does better for agents and tool use, reasoning and knowledge and sticking to the facts; Gemma 3 4B for writing.

Head to head

5.9
Intelligence Index
4.8
$0.061
Price per million tokens, blendedlower is better
$0.042
128,000
Context window, tokens
131,072

Every fact side by side

Nova Micro 1.0Gemma 3 4B
Price per million tokens$0.035 in · $0.14 out$0.040 in · $0.050 out
Blended (3 in : 1 out)$0.061$0.042
Cheapest host, blended$0.061 (Amazon Bedrock)$0.042 (Parasail, BF16)
Intelligence Index5.94.8
Spring Prompt overall––
Output speed, tokens a second260–
Context window128,000 tokens131,072 tokens
Released3 Dec 202411 Mar 2025 (newer)
WeightsClosedOpen
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 152 of 159 158 of 159
Reasoning and knowledgeHard questions across science, maths and general knowledge 175 of 187 181 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 166 of 169 157 of 169
Sticking to the factsSummarising without inventing things, and factual answers 19 of 139 32 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 Micro 1.0Gemma 3 4B
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 295 · 255 of 387 measured 1,241 1,303
Business, management and finance · TextArena rating, higher is better 292 · 208 of 380 measured 1,233 1,330
Creative writing · TextArena rating, higher is better 297 · 243 of 385 measured 1,198 1,275
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 237 · 246 of 249 measured 5.9 4.8
GPQA Diamond% of questions, higher is better 223 · 227 of 232 measured 35.8% 29.1%
Humanity's Last Exam% of questions, higher is better 206 · 194 of 250 measured 4.6% 5.3%
Berkeley Function Calling Leaderboard (BFCL) V4 reported by Berkeley Function Calling Leaderboard (BFCL) V4 · 3 results
Overall accuracy · BFCL% correct, higher is better 69 · 74 of 81 measured 22.3%bfcl fc 19.6%bfcl prompt
Irrelevance detection · BFCL% correct, higher is better 61 · 71 of 81 measured 70.7%bfcl fc 53.9%bfcl prompt
Memory · BFCL% correct, higher is better 73 · 53 of 81 measured 2.4%bfcl fc 8.6%bfcl prompt
Vectara Hallucination Leaderboard reported by Vectara Hallucination Leaderboard · 2 results
Hallucination rate · Vectara% of summaries, lower is better 18 · 28 of 104 measured 5.5% 6.4%
Answer rate · Vectara% of documents, higher is better 1 · 103 of 104 measured 100.0% 67.3%
Show all 23 results (12 more)
MeasureNova Micro 1.0Gemma 3 4B
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Expert prompts · TextArena rating, higher is better 278 · 270 of 338 measured 1,244 1,260
Instruction following · TextArena rating, higher is better 300 · 270 of 387 measured 1,215 1,267
Writing, literature and language · TextArena rating, higher is better 296 · 237 of 386 measured 1,223 1,298
Artificial Analysis reported by Artificial Analysis · 4 results
IFBench% of instructions, higher is better 184 · 187 of 195 measured 29.4% 28.3%
Long-context reasoning (AA-LCR)% of questions, higher is better 221 · 226 of 241 measured 13.0% 6.7%
Terminal-Bench Hard% of tasks, higher is better 175 · 180 of 190 measured 1.5% 0.8%
τ²-bench telecom% of tasks, higher is better 180 · 187 of 193 measured 14.0% 5.0%
Berkeley Function Calling Leaderboard (BFCL) V4 reported by Berkeley Function Calling Leaderboard (BFCL) V4 · 5 results
Multi-turn tasks · BFCL% correct, higher is better 73 · 75 of 81 measured 1.4%bfcl fc 0.4%bfcl prompt
Relevance detection · BFCL% correct, higher is better 36 · 1 of 81 measured 81.3%bfcl fc 100.0%bfcl prompt
Single-turn calls (curated) · BFCL% correct, higher is better 65 · 74 of 81 measured 74.1%bfcl fc 61.1%bfcl prompt
Single-turn calls (user-contributed) · BFCL% correct, higher is better 59 · 64 of 81 measured 66.3%bfcl fc 60.8%bfcl prompt
Web search · BFCL% correct, higher is better 53 · 56 of 81 measured 1.5%bfcl fc 1.0%bfcl prompt

Quick answers

Is Nova Micro 1.0 better than Gemma 3 4B?

They score about the same, so pick Gemma 3 4B: it costs 31% less per token.

Which is cheaper, Nova Micro 1.0 or Gemma 3 4B?

Gemma 3 4B is cheaper: $0.042 against $0.061 per million tokens, 31% less.

Which is better for agents and tool use, Nova Micro 1.0 or Gemma 3 4B?

Nova Micro 1.0 ranks 152 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 158 for Gemma 3 4B.

Which is better for reasoning and knowledge, Nova Micro 1.0 or Gemma 3 4B?

Nova Micro 1.0 ranks 175 of 187 models on sale for hard questions across science, maths and general knowledge, against 181 for Gemma 3 4B.

Which is better for writing, Nova Micro 1.0 or Gemma 3 4B?

Gemma 3 4B ranks 157 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 Micro 1.0 or Gemma 3 4B?

Nova Micro 1.0 ranks 19 of 139 models on sale for summarising without inventing things, and factual answers, against 32 for Gemma 3 4B.

Which has the bigger context window, Nova Micro 1.0 or Gemma 3 4B?

Gemma 3 4B: 131,072 tokens, against 128,000 for Nova Micro 1.0.

Run Nova Micro 1.0 and Gemma 3 4B 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.