Compare / Nova Lite 1.0 vs Mistral Large 3 2512
Nova Lite 1.0 vs Mistral Large 3 2512
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.
Nova Lite 1.0 or Mistral Large 3 2512? The short answer
- Nova Lite 1.0 is cheaper: $0.10 against $0.75 per million tokens, 7.1 times less.
- Mistral Large 3 2512 scores higher on the Artificial Analysis Intelligence Index: 9.3 against 6.7.
- On our business benchmarks, Nova Lite 1.0 ranks higher for sticking to the facts.
- On our business benchmarks, Mistral Large 3 2512 ranks higher for reasoning and knowledge and writing.
At a glance
| Nova Lite 1.0 | Mistral Large 3 2512 | |
|---|---|---|
| Price per million tokens | $0.060 in · $0.24 out | $0.50 in · $1.50 out |
| Blended (3 in : 1 out) | $0.10 | $0.75 |
| Cheapest host, blended | $0.10 (Amazon Bedrock) | $0.75 (Mistral) |
| Intelligence Index | 6.7 | 9.3 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | – | 80 |
| Context window | 300,000 tokens | 262,144 tokens |
| Weights | Closed | Closed |
| 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 | Nova Lite 1.0 | Mistral Large 3 2512 |
|---|---|---|
| Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls | not measured | 131 of 161 |
| Reasoning and knowledgeHard questions across science, maths and general knowledge | 177 of 195 | 155 of 195 |
| WritingWhat people prefer in blind comparisons, and judged writing quality | 181 of 187 | 97 of 187 |
| Sticking to the factsSummarising without inventing things, and factual answers | 25 of 153 | 120 of 153 |
Every shared result
| Benchmark | Metric | Nova Lite 1.0 | Mistral Large 3 2512 |
|---|---|---|---|
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,269 | 1,409 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,221 | 1,373 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,262 | 1,428 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,244 | 1,400 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,260 | 1,413 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,240 | 1,388 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 6.70 | 9.30 |
| Artificial Analysisreported | GPQA Diamond% of questions | 43.3% | 68.0% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 4.3% | 4.2% |
| Artificial Analysisreported | IFBench% of instructions | 34.1% | 36.2% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 19.0% | 36.0% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 0.8% | 15.9% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 17.5% | 24.6% |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 99.9% | 98.8% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 6.1% | 14.5% |
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 Lite 1.0 better than Mistral Large 3 2512?
It depends on the task. Among models available today, on our benchmarks and licensed sources, Nova Lite 1.0 ranks higher for sticking to the facts; Mistral Large 3 2512 ranks higher for reasoning and knowledge and writing.
Which is cheaper, Nova Lite 1.0 or Mistral Large 3 2512?
Nova Lite 1.0 costs $0.10 per million tokens (three input to one output), against $0.75 for Mistral Large 3 2512.
Run Nova Lite 1.0 and Mistral Large 3 2512 on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.