Compare / Mistral Large 4 vs GPT-5.4 mini
Mistral Large 4 vs GPT-5.4 mini
Which is cheaper, which is more capable, and which does better at each kind of work, from 10 results on 2 sources that measured both models.
Results as of 8 October 2026 (catalogue release 2026-10-08-4199ce0620fe).
Mistral Large 4 or GPT-5.4 mini? The short answer
Pick Mistral Large 4: it scores higher (Intelligence Index 38.4 against 24.1) at about the same price.
- They cost about the same: $2.06 and $1.69 per million tokens (three input to one output).
- Mistral Large 4 scores higher on the Artificial Analysis Intelligence Index: 38.4 against 24.1.
- Mistral Large 4 is newer: released 6 Oct 2026, against 17 Mar 2026 for GPT-5.4 mini.
- On third-party benchmarks, on the results both models have: Mistral Large 4 does better for agents and tool use and reasoning and knowledge.
At a glance
| Mistral Large 4 | GPT-5.4 mini | |
|---|---|---|
| Price per million tokens | $1.36 in · $4.18 out | $0.75 in · $4.50 out |
| Blended (3 in : 1 out) | $2.06 | $1.69 |
| Cheapest host, blended | – | $1.69 (Azure) |
| Cached input, per million | – | $0.075 cached input |
| Intelligence Index | 38.4 | 24.1 |
| Spring Prompt overall | 37 | – |
| Output speed, tokens a second | 106 | – |
| Context window | 524,288 tokens | 400,000 tokens |
| Released | 6 Oct 2026 (newer) | 17 Mar 2026 |
| 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 4 | GPT-5.4 mini |
|---|---|---|
| Product listingsTurning a sparse product feed and photos into listings that can go live | 18 of 20 | not measured |
| Decks from an analysisTurning a finished analysis into a deck you could present as it is | 19 of 19 | not measured |
| User surveysPlanning a user survey and reading its results without being misled | 4 of 8 | not measured |
| Marketing planningPlanning a year of ad spend without overspending | 10 of 19 | not measured |
| Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls | 21 of 164 | 56 of 164 |
| Reasoning and knowledgeHard questions across science, maths and general knowledge | 44 of 198 | 71 of 198 |
| WritingWhat people prefer in blind comparisons, and judged writing quality | not measured | 58 of 188 |
| Sticking to the factsSummarising without inventing things, and factual answers | not measured | 66 of 152 |
| Speed under pressureGood decisions against a real clock (fast chess) | 13 of 22 | 12 of 22 |
From our research
Every shared result
Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.
| Measure | Mistral Large 4 | GPT-5.4 mini |
|---|---|---|
| BulletBench measured by Spring Prompt · 3 results | ||
| Ladder Elo · Lightning 10+1ladder Elo, higher is better | 249 | 571no reasoning |
| Cost per game · Lightning 10+1US dollars, lower is better | $0.0117 | $0.0136no reasoning |
| Games lost on time · Lightning 10+1% of games, lower is better | 58.3% | 0.0%no reasoning |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better | 38.4 | 24.1xhigh reasoning |
| Humanity's Last Exam% of questions, higher is better | 35.0% | 28.1%xhigh reasoning |
| Terminal-Bench 4.0% of tasks, higher is better | 26.8% | 2.0%xhigh reasoning |
Show all 10 results (4 more)
| Measure | Mistral Large 4 | GPT-5.4 mini |
|---|---|---|
| BulletBench measured by Spring Prompt · 2 results | ||
| Invalid moves · Lightning 10+1% of moves, lower is better | 1.8% | 0.0%no reasoning |
| Median move time · Lightning 10+1milliseconds, lower is better | 0.8 s | 0.9 sno reasoning |
| Artificial Analysis reported by Artificial Analysis · 2 results | ||
| Long-context reasoning (AA-LCR)% of questions, higher is better | 81.3% | 77.0%xhigh reasoning |
| SciCode% of problems, higher is better | 54.2% | 52.1%xhigh reasoning |
Quick answers
Is Mistral Large 4 better than GPT-5.4 mini?
Pick Mistral Large 4: it scores higher (Intelligence Index 38.4 against 24.1) at about the same price.
Which is cheaper, Mistral Large 4 or GPT-5.4 mini?
They cost about the same: $2.06 and $1.69 per million tokens (three input to one output).
Run Mistral Large 4 and GPT-5.4 mini on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.