Compare / Mistral Large 4 vs Mistral Small 4
Mistral Large 4 vs Mistral Small 4
Which is cheaper, which is more capable, and which does better at each kind of work, from 12 results on 2 sources that measured both models.
Of the 12 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.
Results as of 19 November 2026 (catalogue release 2026-11-19-3608133e8331).
Mistral Large 4 or Mistral Small 4? The short answer
Pick Mistral Large 4 if quality matters most: it scores higher (Intelligence Index 38.4 against 11.3). Pick Mistral Small 4 if cost matters more: it costs 7.9 times less per token. Mistral Small 4 is also faster.
- Mistral Small 4 is cheaper: $0.26 against $2.06 per million tokens, 7.9 times less.
- Mistral Large 4 scores higher on the Artificial Analysis Intelligence Index: 38.4 against 11.3.
- Mistral Small 4 writes faster: 176 tokens a second against 60.
- Mistral Large 4 is newer: released 6 Oct 2026, against 16 Mar 2026 for Mistral Small 4.
- On third-party benchmarks, on the results both models have: Mistral Large 4 does better for agents and tool use and reasoning and knowledge.
Head to head
Every fact side by side
| Mistral Large 4 | Mistral Small 4 | |
|---|---|---|
| Price per million tokens | $1.36 in · $4.18 out | $0.15 in · $0.60 out |
| Blended (3 in : 1 out) | $2.06 | $0.26 |
| Cheapest host, blended | $1.05 (Mistral) | $0.26 (Mistral) |
| Cached input, per million | – | $0.015 cached input |
| Intelligence Index | 38.4 | 11.3 |
| Spring Prompt overall | 24 | – |
| Output speed, tokens a second | 60 | 176 |
| Context window | 1,048,576 tokens | 262,144 tokens |
| Released | 6 Oct 2026 (newer) | 16 Mar 2026 |
| Weights | Open | Open |
| Developer based in | France | 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 the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.
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. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. 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 | Mistral Small 4 |
|---|---|---|
| BulletBench measured by Spring Prompt · 3 results | ||
| Ladder Elo · Lightning 10+1ladder Elo, higher is better 39 · 15 of 45 measured | 249 | 571no reasoning |
| Cost per game · Lightning 10+1US dollars, lower is better 40 · 31 of 45 measured | $0.0117 | $0.0041no reasoning |
| Games lost on time · Lightning 10+1% of games, lower is better 36 · 1 of 45 measured | 58.3% | 0.0%no reasoning |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better 36 · 164 of 249 measured | 38.4 | 11.3 |
| Humanity's Last Exam% of questions, higher is better 65 · 164 of 250 measured | 35.0% | 9.9% |
| Terminal-Bench 4.0% of tasks, higher is better 26 · 72 of 120 measured | 24.7% | 0.0% |
Show all 12 results (6 more)
| Measure | Mistral Large 4 | Mistral Small 4 |
|---|---|---|
| BulletBench measured by Spring Prompt · 2 results | ||
| Invalid moves · Lightning 10+1% of moves, lower is better 43 · 42 of 45 measured | 1.8% | 1.0%no reasoning |
| Median move time · Lightning 10+1milliseconds, lower is better 30 · 14 of 45 measured | 0.8 s | 0.6 sno reasoning |
| Artificial Analysis reported by Artificial Analysis · 4 results | ||
| Long-context reasoning (AA-LCR)% of questions, higher is better 32 · 165 of 241 measured | 81.3% | 49.7% |
| Output speedtokens per second, higher is better 61 · 19 of 78 measured | 60.2 | 176 |
| SciCode% of problems, higher is better 34 · 91 of 121 measured | 54.2% | 38.8% |
| Time to first answer tokenseconds, lower is better 68 · 9 of 78 measured | 33.9 | 0.57no reasoning |
Compare them with other models
Quick answers
Is Mistral Large 4 better than Mistral Small 4?
Pick Mistral Large 4 if quality matters most: it scores higher (Intelligence Index 38.4 against 11.3). Pick Mistral Small 4 if cost matters more: it costs 7.9 times less per token. Mistral Small 4 is also faster.
Which is cheaper, Mistral Large 4 or Mistral Small 4?
Mistral Small 4 is cheaper: $0.26 against $2.06 per million tokens, 7.9 times less.
Which is faster, Mistral Large 4 or Mistral Small 4?
Mistral Small 4 writes about 176 tokens a second on its usual API, against 60 for Mistral Large 4 (Artificial Analysis).
Which is better for agents and tool use, Mistral Large 4 or Mistral Small 4?
Mistral Large 4 ranks 37 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 133 for Mistral Small 4.
Which is better for reasoning and knowledge, Mistral Large 4 or Mistral Small 4?
Mistral Large 4 ranks 54 of 187 models on sale for hard questions across science, maths and general knowledge, against 127 for Mistral Small 4.
Which is better for speed under pressure, Mistral Large 4 or Mistral Small 4?
Mistral Small 4 ranks 15 of 38 models on sale for good decisions against a real clock (fast chess), against 27 for Mistral Large 4.
Which has the bigger context window, Mistral Large 4 or Mistral Small 4?
Mistral Large 4: 1,048,576 tokens, against 262,144 for Mistral Small 4.
Run Mistral Large 4 and Mistral Small 4 on your own prompt.
Benchmarks aren't your task. Test both side by side on your prompt, with every answer checked against your rules and the cost of each one.