Compare / Ministral 3 14B 2512 vs GPT-4.1
Ministral 3 14B 2512 vs GPT-4.1
Which is cheaper, which is more capable, and which does better at each kind of work, from 12 results on 3 sources that measured both models.
Ministral 3 14B 2512 or GPT-4.1? The short answer
- Ministral 3 14B 2512 is cheaper: $0.20 against $3.50 per million tokens, 18 times less.
- GPT-4.1 scores higher on the Artificial Analysis Intelligence Index: 12.7 against 6.0.
- On our business benchmarks, GPT-4.1 ranks higher for agents and tool use, reasoning and knowledge, writing and sticking to the facts.
At a glance
| Ministral 3 14B 2512 | GPT-4.1 | |
|---|---|---|
| Price per million tokens | $0.20 in · $0.20 out | $2.00 in · $8.00 out |
| Blended (3 in : 1 out) | $0.20 | $3.50 |
| Cheapest host, blended | $0.20 (Mistral) | $3.50 (Azure) |
| Intelligence Index | 6.0 | 12.7 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | 91 | – |
| Context window | 262,144 tokens | 1,047,576 tokens |
| Weights | Open | Closed |
| Developer based in | France | 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 | Ministral 3 14B 2512 | GPT-4.1 |
|---|---|---|
| Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls | 128 of 161 | 40 of 161 |
| Reasoning and knowledgeHard questions across science, maths and general knowledge | 167 of 195 | 148 of 195 |
| WritingWhat people prefer in blind comparisons, and judged writing quality | 143 of 187 | 54 of 187 |
| Sticking to the factsSummarising without inventing things, and factual answers | 146 of 153 | 92 of 153 |
Every shared result
| Benchmark | Metric | Ministral 3 14B 2512 | GPT-4.1 |
|---|---|---|---|
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 6.00 | 12.7 |
| Artificial Analysisreported | GPQA Diamond% of questions | 57.2% | 66.6% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 4.6% | 4.2% |
| Artificial Analysisreported | IFBench% of instructions | 32.0% | 43.0% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 26.3% | 68.3% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 4.5% | 13.6% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 27.2% | 47.1% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 24.0% | 6.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.32 | 0.33 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 31.4 | 67.5 |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 99.6% | 99.9% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 19.4% | 5.6% |
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 Ministral 3 14B 2512 better than GPT-4.1?
It depends on the task. Among models available today, on our benchmarks and licensed sources, GPT-4.1 ranks higher for agents and tool use, reasoning and knowledge, writing and sticking to the facts.
Which is cheaper, Ministral 3 14B 2512 or GPT-4.1?
Ministral 3 14B 2512 costs $0.20 per million tokens (three input to one output), against $3.50 for GPT-4.1.
Run Ministral 3 14B 2512 and GPT-4.1 on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.