Compare / Nova 2 Lite vs Ministral 3 8B 2512
Nova 2 Lite vs Ministral 3 8B 2512
Which is cheaper, which is more capable, and which does better at each kind of work, from 16 results on 3 sources that measured both models.
Nova 2 Lite or Ministral 3 8B 2512? The short answer
- Ministral 3 8B 2512 is cheaper: $0.15 against $0.85 per million tokens, 5.7 times less.
- Nova 2 Lite scores higher on the Artificial Analysis Intelligence Index: 13.4 against 5.5.
- Nova 2 Lite writes faster: 210 tokens a second against 103.
- On our business benchmarks, Nova 2 Lite ranks higher for agents and tool use, reasoning and knowledge and sticking to the facts.
- On our business benchmarks, Ministral 3 8B 2512 ranks higher for writing.
At a glance
| Nova 2 Lite | Ministral 3 8B 2512 | |
|---|---|---|
| Price per million tokens | $0.30 in · $2.50 out | $0.15 in · $0.15 out |
| Blended (3 in : 1 out) | $0.85 | $0.15 |
| Cheapest host, blended | $0.85 (Amazon Bedrock) | $0.15 (Mistral) |
| Intelligence Index | 13.4 | 5.5 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | 210 | 103 |
| Context window | 1,000,000 tokens | 262,144 tokens |
| Weights | Closed | 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 | Nova 2 Lite | Ministral 3 8B 2512 |
|---|---|---|
| Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls | 130 of 161 | 150 of 161 |
| Reasoning and knowledgeHard questions across science, maths and general knowledge | 112 of 195 | 184 of 195 |
| WritingWhat people prefer in blind comparisons, and judged writing quality | 168 of 187 | 156 of 187 |
| Sticking to the factsSummarising without inventing things, and factual answers | 76 of 153 | 147 of 153 |
Every shared result
| Benchmark | Metric | Nova 2 Lite | Ministral 3 8B 2512 |
|---|---|---|---|
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 23.0 | 9.70 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 13.4 | 5.50 |
| Artificial Analysisreported | GPQA Diamond% of questions | 81.1% | 47.1% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 11.6% | 4.3% |
| Artificial Analysisreported | IFBench% of instructions | 70.7% | 29.1% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 60.3% | 25.7% |
| Artificial Analysisreported | Output speedtokens per second | 210 | 103 |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 16.1% | 4.1% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 17.4% | 4.5% |
| Artificial Analysisreported | Time to first answer tokenseconds | 0.83 | 0.48 |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 75.7% | 26.6% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 45.0% | 23.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.35 | 0.33 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 23.5 | 28.8 |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 99.6% | 99.1% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 5.1% | 21.7% |
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 2 Lite better than Ministral 3 8B 2512?
It depends on the task. Among models available today, on our benchmarks and licensed sources, Nova 2 Lite ranks higher for agents and tool use, reasoning and knowledge and sticking to the facts; Ministral 3 8B 2512 ranks higher for writing.
Which is cheaper, Nova 2 Lite or Ministral 3 8B 2512?
Ministral 3 8B 2512 costs $0.15 per million tokens (three input to one output), against $0.85 for Nova 2 Lite.
Which is faster, Nova 2 Lite or Ministral 3 8B 2512?
Nova 2 Lite writes about 210 tokens a second on its usual API, against 103 for Ministral 3 8B 2512 (Artificial Analysis).
Run Nova 2 Lite and Ministral 3 8B 2512 on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.