Compare / Llama 4 Maverick vs Mistral Large 3 2512
Llama 4 Maverick vs Mistral Large 3 2512
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.
Llama 4 Maverick or Mistral Large 3 2512? The short answer
- Llama 4 Maverick is cheaper: $0.42 against $0.75 per million tokens, 45% less.
- They score about the same on the Artificial Analysis Intelligence Index (10.0 and 9.3).
- Mistral Large 3 2512 writes faster: 80 tokens a second against 42.
- On our business benchmarks, Llama 4 Maverick ranks higher for reasoning and knowledge.
- On our business benchmarks, Mistral Large 3 2512 ranks higher for agents and tool use and writing.
At a glance
| Llama 4 Maverick | Mistral Large 3 2512 | |
|---|---|---|
| Price per million tokens | $0.27 in · $0.85 out | $0.50 in · $1.50 out |
| Blended (3 in : 1 out) | $0.42 | $0.75 |
| Cheapest host, blended | $0.30 (DigitalOcean) | $0.75 (Mistral) |
| Intelligence Index | 10.0 | 9.3 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | 42 | 80 |
| Context window | 1,048,576 tokens | 262,144 tokens |
| Weights | Open | 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 | Llama 4 Maverick | Mistral Large 3 2512 |
|---|---|---|
| Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls | 141 of 161 | 131 of 161 |
| Reasoning and knowledgeHard questions across science, maths and general knowledge | 146 of 195 | 155 of 195 |
| WritingWhat people prefer in blind comparisons, and judged writing quality | 166 of 187 | 97 of 187 |
| Sticking to the factsSummarising without inventing things, and factual answers | not measured | 120 of 153 |
Every shared result
| Benchmark | Metric | Llama 4 Maverick | Mistral Large 3 2512 |
|---|---|---|---|
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,317 | 1,409 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,307 | 1,373 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,326 | 1,428 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,314 | 1,400 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,327 | 1,413 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,312 | 1,388 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 16.3 | 20.1 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 10.0 | 9.30 |
| Artificial Analysisreported | GPQA Diamond% of questions | 67.1% | 68.0% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 4.9% | 4.2% |
| Artificial Analysisreported | IFBench% of instructions | 43.0% | 36.2% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 50.0% | 36.0% |
| Artificial Analysisreported | Output speedtokens per second | 42.4 | 80.3 |
| Artificial Analysisreported | SciCode% of problems | 31.7% | 36.6% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 7.9% | 12.0% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 0.0% | 0.0% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 6.8% | 15.9% |
| Artificial Analysisreported | Time to first answer tokenseconds | 0.64 | 0.69 |
| Artificial Analysisreported | Τ-bench banking% of tasks | 3.7% | 5.8% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 17.8% | 24.6% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 13.0% | 15.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.37 | 0.38 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 24.0 | 41.6 |
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 Llama 4 Maverick better than Mistral Large 3 2512?
It depends on the task. Among models available today, on our benchmarks and licensed sources, Llama 4 Maverick ranks higher for reasoning and knowledge; Mistral Large 3 2512 ranks higher for agents and tool use and writing.
Which is cheaper, Llama 4 Maverick or Mistral Large 3 2512?
Llama 4 Maverick costs $0.42 per million tokens (three input to one output), against $0.75 for Mistral Large 3 2512.
Which is faster, Llama 4 Maverick or Mistral Large 3 2512?
Mistral Large 3 2512 writes about 80 tokens a second on its usual API, against 42 for Llama 4 Maverick (Artificial Analysis).
Run Llama 4 Maverick 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.