Compare / Nova Micro 1.0 vs Phi-4

Nova Micro 1.0 vs Phi-4

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 Micro 1.0 Released 3 Dec 2024 · $0.035 in · $0.14 out
MicrosoftPhi-4 Released 12 Dec 2024 · $0.070 in · $0.14 out
Nova Micro 1.0 wins 105 too close to callPhi-4 wins 10

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 Micro 1.0 or Phi-4? The short answer

They score about the same, so pick Nova Micro 1.0: it costs 30% less per token.

  • Nova Micro 1.0 is cheaper: $0.061 against $0.088 per million tokens, 30% less.
  • They score about the same on the Artificial Analysis Intelligence Index (5.9 and 5.9).
  • Nova Micro 1.0 writes faster: 260 tokens a second against 45.
  • Phi-4 is newer: released 12 Dec 2024, against 3 Dec 2024 for Nova Micro 1.0.
  • On third-party benchmarks, on the results both models have: Phi-4 does better for agents and tool use, writing and sticking to the facts.

Head to head

5.9
Intelligence Index
5.9
$0.061
Price per million tokens, blendedlower is better
$0.088
260
Output speed, tokens a second
45
128,000
Context window, tokens
16,384

Every fact side by side

Nova Micro 1.0Phi-4
Price per million tokens$0.035 in · $0.14 out$0.070 in · $0.14 out
Blended (3 in : 1 out)$0.061$0.088
Cheapest host, blended$0.061 (Amazon Bedrock)–
Intelligence Index5.95.9
Spring Prompt overall––
Output speed, tokens a second26045
Context window128,000 tokens16,384 tokens
Released3 Dec 202412 Dec 2024 (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 159 115 of 159
Reasoning and knowledgeHard questions across science, maths and general knowledge 175 of 187 169 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 166 of 169 161 of 169
Sticking to the factsSummarising without inventing things, and factual answers 19 of 139 4 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 1.0Phi-4
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 295 · 291 of 387 measured 1,241 1,256
Business, management and finance · TextArena rating, higher is better 292 · 282 of 380 measured 1,233 1,256
Creative writing · TextArena rating, higher is better 297 · 290 of 385 measured 1,198 1,210
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 237 · 237 of 249 measured 5.9 5.9
GPQA Diamond% of questions, higher is better 223 · 191 of 232 measured 35.8% 57.5%
Humanity's Last Exam% of questions, higher is better 206 · 229 of 250 measured 4.6% 3.8%
Berkeley Function Calling Leaderboard (BFCL) V4 reported by Berkeley Function Calling Leaderboard (BFCL) V4 · 3 results
Overall accuracy · BFCL% correct, higher is better 69 · 51 of 81 measured 22.3%bfcl fc 28.8%bfcl prompt
Irrelevance detection · BFCL% correct, higher is better 61 · 16 of 81 measured 70.7%bfcl fc 87.6%bfcl prompt
Memory · BFCL% correct, higher is better 73 · 24 of 81 measured 2.4%bfcl fc 24.7%bfcl prompt
Vectara Hallucination Leaderboard reported by Vectara Hallucination Leaderboard · 2 results
Hallucination rate · Vectara% of summaries, lower is better 18 · 4 of 104 measured 5.5% 3.7%
Answer rate · Vectara% of documents, higher is better 1 · 100 of 104 measured 100.0% 80.7%
Show all 25 results (14 more)
MeasureNova Micro 1.0Phi-4
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Expert prompts · TextArena rating, higher is better 278 · 261 of 338 measured 1,244 1,268
Instruction following · TextArena rating, higher is better 300 · 285 of 387 measured 1,215 1,245
Writing, literature and language · TextArena rating, higher is better 296 · 290 of 386 measured 1,223 1,229
Artificial Analysis reported by Artificial Analysis · 6 results
IFBench% of instructions, higher is better 184 · 192 of 195 measured 29.4% 23.5%
Long-context reasoning (AA-LCR)% of questions, higher is better 221 · 230 of 241 measured 13.0% 0.0%
Output speedtokens per second, higher is better 7 · 72 of 78 measured 260 45.1
Terminal-Bench Hard% of tasks, higher is better 175 · 162 of 190 measured 1.5% 3.8%
Time to first answer tokenseconds, lower is better 8 · 27 of 78 measured 0.55 1.03
τ²-bench telecom% of tasks, higher is better 180 · 188 of 193 measured 14.0% 0.0%
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 · 64 of 81 measured 1.4%bfcl fc 3.9%bfcl prompt
Relevance detection · BFCL% correct, higher is better 36 · 74 of 81 measured 81.3%bfcl fc 50.0%bfcl prompt
Single-turn calls (curated) · BFCL% correct, higher is better 65 · 69 of 81 measured 74.1%bfcl fc 69.6%bfcl prompt
Single-turn calls (user-contributed) · BFCL% correct, higher is better 59 · 66 of 81 measured 66.3%bfcl fc 60.7%bfcl prompt
Web search · BFCL% correct, higher is better 53 · 44 of 81 measured 1.5%bfcl fc 4.5%bfcl prompt

Quick answers

Is Nova Micro 1.0 better than Phi-4?

They score about the same, so pick Nova Micro 1.0: it costs 30% less per token.

Which is cheaper, Nova Micro 1.0 or Phi-4?

Nova Micro 1.0 is cheaper: $0.061 against $0.088 per million tokens, 30% less.

Which is faster, Nova Micro 1.0 or Phi-4?

Nova Micro 1.0 writes about 260 tokens a second on its usual API, against 45 for Phi-4 (Artificial Analysis).

Which is better for agents and tool use, Nova Micro 1.0 or Phi-4?

Phi-4 ranks 115 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 Micro 1.0 or Phi-4?

Phi-4 ranks 169 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 Micro 1.0 or Phi-4?

Phi-4 ranks 161 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 Phi-4?

Phi-4 ranks 4 of 139 models on sale for summarising without inventing things, and factual answers, against 19 for Nova Micro 1.0.

Which has the bigger context window, Nova Micro 1.0 or Phi-4?

Nova Micro 1.0: 128,000 tokens, against 16,384 for Phi-4.

Run Nova Micro 1.0 and Phi-4 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.