Compare / Nova Micro 1.0 vs Llama 3.3 70B Instruct
Nova Micro 1.0 vs Llama 3.3 70B Instruct
Which is cheaper, which is more capable, and which does better at each kind of work, from 23 results on 3 sources that measured both models.
Nova Micro 1.0 or Llama 3.3 70B Instruct? The short answer
- Nova Micro 1.0 is cheaper: $0.061 against $0.64 per million tokens, 10 times less.
- Llama 3.3 70B Instruct scores higher on the Artificial Analysis Intelligence Index: 7.7 against 5.9.
- Nova Micro 1.0 writes faster: 256 tokens a second against 80.
- On our business benchmarks, Llama 3.3 70B Instruct ranks higher for agents and tool use, reasoning and knowledge and writing.
At a glance
| Nova Micro 1.0 | Llama 3.3 70B Instruct | |
|---|---|---|
| Price per million tokens | $0.035 in · $0.14 out | $0.59 in · $0.79 out |
| Blended (3 in : 1 out) | $0.061 | $0.64 |
| Cheapest host, blended | $0.061 (Amazon Bedrock) | $0.16 (DeepInfra, FP8) |
| Intelligence Index | 5.9 | 7.7 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | 256 | 80 |
| Context window | 128,000 tokens | 131,072 tokens |
| Weights | Closed | Open |
| Developer based in | the US | the 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 case | Nova Micro 1.0 | Llama 3.3 70B Instruct |
|---|---|---|
| Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls | 156 of 161 | 127 of 161 |
| Reasoning and knowledgeHard questions across science, maths and general knowledge | 181 of 195 | 174 of 195 |
| WritingWhat people prefer in blind comparisons, and judged writing quality | 184 of 187 | 165 of 187 |
| Sticking to the factsSummarising without inventing things, and factual answers | 20 of 153 | not measured |
Every shared result
| Benchmark | Metric | Nova Micro 1.0 | Llama 3.3 70B Instruct |
|---|---|---|---|
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,233 | 1,304 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,197 | 1,285 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,244 | 1,298 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,215 | 1,293 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,241 | 1,318 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,223 | 1,292 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 5.90 | 7.70 |
| Artificial Analysisreported | GPQA Diamond% of questions | 35.8% | 49.8% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 4.6% | 3.6% |
| Artificial Analysisreported | IFBench% of instructions | 29.4% | 47.1% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 13.0% | 15.7% |
| Artificial Analysisreported | Output speedtokens per second | 256 | 80.5 |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 1.5% | 3.0% |
| Artificial Analysisreported | Time to first answer tokenseconds | 0.58 | 0.64 |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 14.0% | 26.6% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Irrelevance detection% correct | 70.7% | 53.5% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Memory% correct | 2.4% | 8.2% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Multi-turn tasks% correct | 1.4% | 21.5% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Overall accuracy% correct | 22.3% | 31.9% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Relevance detection% correct | 81.2% | 100.0% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (curated)% correct | 74.1% | 88.0% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Single-turn calls (user-contributed)% correct | 66.3% | 76.6% |
| Berkeley Function Calling Leaderboard (BFCL) V4reported | Web search% correct | 1.5% | 10.0% |
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 Micro 1.0 better than Llama 3.3 70B Instruct?
It depends on the task. Among models available today, on our benchmarks and licensed sources, Llama 3.3 70B Instruct ranks higher for agents and tool use, reasoning and knowledge and writing.
Which is cheaper, Nova Micro 1.0 or Llama 3.3 70B Instruct?
Nova Micro 1.0 costs $0.061 per million tokens (three input to one output), against $0.64 for Llama 3.3 70B Instruct.
Which is faster, Nova Micro 1.0 or Llama 3.3 70B Instruct?
Nova Micro 1.0 writes about 256 tokens a second on its usual API, against 80 for Llama 3.3 70B Instruct (Artificial Analysis).
Run Nova Micro 1.0 and Llama 3.3 70B Instruct on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.