Compare / Mistral Large 3 2512 vs GPT-4o (2024-05-13)
Mistral Large 3 2512 vs GPT-4o (2024-05-13)
Which is cheaper, which is more capable, and which does better at each kind of work, from 13 results on 3 sources that measured both models.
Mistral Large 3 2512 or GPT-4o (2024-05-13)? The short answer
- Mistral Large 3 2512 is cheaper: $0.75 against $7.50 per million tokens, 10 times less.
- Mistral Large 3 2512 scores higher on the Artificial Analysis Intelligence Index: 9.3 against 7.3.
- On our business benchmarks, Mistral Large 3 2512 ranks higher for reasoning and knowledge.
- On our business benchmarks, GPT-4o (2024-05-13) ranks higher for writing.
At a glance
| Mistral Large 3 2512 | GPT-4o (2024-05-13) | |
|---|---|---|
| Price per million tokens | $0.50 in · $1.50 out | $5.00 in · $15.00 out |
| Blended (3 in : 1 out) | $0.75 | $7.50 |
| Cheapest host, blended | $0.75 (Mistral) | $7.50 (Azure) |
| Intelligence Index | 9.3 | 7.3 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | 80 | – |
| Context window | 262,144 tokens | 128,000 tokens |
| Weights | Closed | 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 | Mistral Large 3 2512 | GPT-4o (2024-05-13) |
|---|---|---|
| Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls | 131 of 161 | not measured |
| Reasoning and knowledgeHard questions across science, maths and general knowledge | 155 of 195 | 182 of 195 |
| WritingWhat people prefer in blind comparisons, and judged writing quality | 97 of 187 | 88 of 187 |
| Sticking to the factsSummarising without inventing things, and factual answers | 120 of 153 | not measured |
Every shared result
| Benchmark | Metric | Mistral Large 3 2512 | GPT-4o (2024-05-13) |
|---|---|---|---|
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,409 | 1,322 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,373 | 1,338 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,428 | 1,311 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,400 | 1,326 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,413 | 1,346 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,388 | 1,345 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 20.1 | 24.2 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 9.30 | 7.30 |
| Artificial Analysisreported | GPQA Diamond% of questions | 68.0% | 52.6% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 4.2% | 1.8% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 15.0% | 12.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.38 | 0.33 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 41.6 | 63.4 |
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 Mistral Large 3 2512 better than GPT-4o (2024-05-13)?
It depends on the task. Among models available today, on our benchmarks and licensed sources, Mistral Large 3 2512 ranks higher for reasoning and knowledge; GPT-4o (2024-05-13) ranks higher for writing.
Which is cheaper, Mistral Large 3 2512 or GPT-4o (2024-05-13)?
Mistral Large 3 2512 costs $0.75 per million tokens (three input to one output), against $7.50 for GPT-4o (2024-05-13).
Run Mistral Large 3 2512 and GPT-4o (2024-05-13) on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.