Compare / Mistral Small 4 vs GPT-6 Luna
Mistral Small 4 vs GPT-6 Luna
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.
Results as of 8 October 2026 (catalogue release 2026-10-08-4199ce0620fe).
Mistral Small 4 or GPT-6 Luna? The short answer
Pick GPT-6 Luna: it scores higher (Intelligence Index 38.1 against 11.3) and costs less.
- GPT-6 Luna is cheaper to run: $0.002 against $0.004 per game of bullet chess on BulletBench (2.4 times less).
- GPT-6 Luna scores higher on the Artificial Analysis Intelligence Index: 38.1 against 11.3.
- GPT-6 Luna is newer: released 22 Sep 2026, against 16 Mar 2026 for Mistral Small 4.
- On third-party benchmarks, on the results both models have: GPT-6 Luna does better for agents and tool use and reasoning and knowledge.
At a glance
| Mistral Small 4 | GPT-6 Luna | |
|---|---|---|
| Price per million tokens | $0.15 in · $0.60 out | $0.10 in · $0.50 out |
| Blended (3 in : 1 out) | $0.26 | $0.20 |
| Cheapest host, blended | $0.26 (Mistral) | $0.20 (Azure) |
| Cost per game of bullet chess (BulletBench) | $0.004 | $0.002 |
| Cached input, per million | $0.015 cached input | $0.010 cached input |
| Intelligence Index | 11.3 | 38.1 |
| Spring Prompt overall | – | 40 |
| Output speed, tokens a second | 164 | 127 |
| Context window | 262,144 tokens | 1,050,000 tokens |
| Released | 16 Mar 2026 | 22 Sep 2026 (newer) |
| 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 | Mistral Small 4 | GPT-6 Luna |
|---|---|---|
| Product listingsTurning a sparse product feed and photos into listings that can go live | not measured | 5 of 20 |
| Decks from an analysisTurning a finished analysis into a deck you could present as it is | not measured | 7 of 19 |
| Marketing planningPlanning a year of ad spend without overspending | not measured | 3 of 19 |
| Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls | 132 of 164 | 43 of 164 |
| Professional workReal tasks from banking, consulting and law, business documents and freelance projects | not measured | 25 of 51 |
| Reasoning and knowledgeHard questions across science, maths and general knowledge | 131 of 198 | 40 of 198 |
| WritingWhat people prefer in blind comparisons, and judged writing quality | 116 of 188 | 60 of 188 |
| Sticking to the factsSummarising without inventing things, and factual answers | not measured | 94 of 152 |
| Speed under pressureGood decisions against a real clock (fast chess) | 9 of 22 | 17 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 Small 4 | GPT-6 Luna |
|---|---|---|
| BulletBench measured by Spring Prompt · 3 results | ||
| Cost per game · Bullet 60sUS dollars, lower is better | $0.0039no reasoning | $0.0016no reasoning |
| Ladder Elo · Bullet 60sladder Elo, higher is better | 367no reasoning | 249no reasoning |
| Games lost on time · Bullet 60s% of games, lower is better | 25.0%no reasoning | 50.0%no reasoning |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better | 11.3 | 38.1max reasoning |
| Humanity's Last Exam% of questions, higher is better | 9.9% | 38.5%max reasoning |
| Terminal-Bench 4.0% of tasks, higher is better | 0.0% | 12.6%max reasoning |
Show all 12 results (6 more)
| Measure | Mistral Small 4 | GPT-6 Luna |
|---|---|---|
| BulletBench measured by Spring Prompt · 2 results | ||
| Invalid moves · Bullet 60s% of moves, lower is better | 0.6%no reasoning | 0.0%no reasoning |
| Median move time · Bullet 60smilliseconds, lower is better | 0.6 sno reasoning | 1.5 sno reasoning |
| Artificial Analysis reported by Artificial Analysis · 4 results | ||
| Long-context reasoning (AA-LCR)% of questions, higher is better | 49.7% | 83.3%max reasoning |
| Output speedtokens per second, higher is better | 164 | 127max reasoning |
| SciCode% of problems, higher is better | 38.8% | 54.6%max reasoning |
| Time to first answer tokenseconds, lower is better | 0.47no reasoning | 0.82no reasoning |
Quick answers
Is Mistral Small 4 better than GPT-6 Luna?
Pick GPT-6 Luna: it scores higher (Intelligence Index 38.1 against 11.3) and costs less.
Which is cheaper, Mistral Small 4 or GPT-6 Luna?
GPT-6 Luna is cheaper to run: $0.002 against $0.004 per game of bullet chess on BulletBench (2.4 times less).
Which is faster, Mistral Small 4 or GPT-6 Luna?
Mistral Small 4 writes about 164 tokens a second on its usual API, against 127 for GPT-6 Luna (Artificial Analysis).
Run Mistral Small 4 and GPT-6 Luna on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.