Compare / Llama 3.3 70B Instruct vs Mistral Small 3
Llama 3.3 70B Instruct vs Mistral Small 3
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.
Llama 3.3 70B Instruct or Mistral Small 3? The short answer
- Mistral Small 3 is cheaper: $0.058 against $0.64 per million tokens, 11 times less.
- Llama 3.3 70B Instruct scores higher on the Artificial Analysis Intelligence Index: 7.7 against 6.7.
- On our business benchmarks, Llama 3.3 70B Instruct ranks higher for reasoning and knowledge.
- On our business benchmarks, Mistral Small 3 ranks higher for writing.
At a glance
| Llama 3.3 70B Instruct | Mistral Small 3 | |
|---|---|---|
| Price per million tokens | $0.59 in · $0.79 out | $0.050 in · $0.080 out |
| Blended (3 in : 1 out) | $0.64 | $0.058 |
| Cheapest host, blended | $0.16 (DeepInfra, FP8) | – |
| Intelligence Index | 7.7 | 6.7 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | 80 | – |
| Context window | 131,072 tokens | 32,768 tokens |
| Weights | Open | Open |
| Developer based in | the US | France |
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 | Llama 3.3 70B Instruct | Mistral Small 3 |
|---|---|---|
| Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls | 127 of 161 | not measured |
| Reasoning and knowledgeHard questions across science, maths and general knowledge | 174 of 195 | 190 of 195 |
| WritingWhat people prefer in blind comparisons, and judged writing quality | 165 of 187 | 155 of 187 |
| Sticking to the factsSummarising without inventing things, and factual answers | not measured | 11 of 153 |
Every shared result
| Benchmark | Metric | Llama 3.3 70B Instruct | Mistral Small 3 |
|---|---|---|---|
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,304 | 1,259 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,285 | 1,227 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,298 | 1,259 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,293 | 1,255 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,318 | 1,274 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,292 | 1,248 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 7.70 | 6.70 |
| Artificial Analysisreported | GPQA Diamond% of questions | 49.8% | 46.2% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 3.6% | 3.8% |
| Artificial Analysisreported | IFBench% of instructions | 47.1% | 26.4% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 15.7% | 0.0% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 26.6% | 19.6% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 10.0% | 8.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.37 | 0.35 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 26.2 | 33.9 |
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 Llama 3.3 70B Instruct better than Mistral Small 3?
It depends on the task. Among models available today, on our benchmarks and licensed sources, Llama 3.3 70B Instruct ranks higher for reasoning and knowledge; Mistral Small 3 ranks higher for writing.
Which is cheaper, Llama 3.3 70B Instruct or Mistral Small 3?
Mistral Small 3 costs $0.058 per million tokens (three input to one output), against $0.64 for Llama 3.3 70B Instruct.
Run Llama 3.3 70B Instruct and Mistral Small 3 on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.