Compare / Mistral Medium 3 vs Mistral Medium 3.5
Mistral Medium 3 vs Mistral Medium 3.5
Which is cheaper, which is more capable, and which does better at each kind of work, from 16 results on 3 sources that measured both models.
Of the 16 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 Medium 3 or Mistral Medium 3.5? The short answer
Pick Mistral Medium 3.5 if quality matters most: it scores higher (Intelligence Index 14.2 against 9.0). Pick Mistral Medium 3 if cost matters more: it costs 3.8 times less per token.
- Mistral Medium 3 is cheaper: $0.80 against $3.00 per million tokens, 3.8 times less.
- Mistral Medium 3.5 scores higher on the Artificial Analysis Intelligence Index: 14.2 against 9.0.
- Mistral Medium 3.5 is newer: released 28 Apr 2026, against 7 May 2025 for Mistral Medium 3.
- On third-party benchmarks, on the results both models have: Mistral Medium 3.5 does better for reasoning and knowledge and writing.
Head to head
Every fact side by side
| Mistral Medium 3 | Mistral Medium 3.5 | |
|---|---|---|
| Price per million tokens | $0.40 in · $2.00 out | $1.50 in · $7.50 out |
| Blended (3 in : 1 out) | $0.80 | $3.00 |
| Cheapest host, blended | $0.80 (Mistral) | $3.00 (Mistral) |
| Cached input, per million | – | $0.15 cached input |
| Intelligence Index | 9.0 | 14.2 |
| Spring Prompt overall | – | 15 |
| Output speed, tokens a second | – | 157 |
| Context window | 131,072 tokens | 262,144 tokens |
| Released | 7 May 2025 | 28 Apr 2026 (newer) |
| Weights | Closed | Closed |
| 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 Medium 3 | Mistral Medium 3.5 |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Overall · TextArena rating, higher is better 155 · 99 of 387 measured | 1,388 | 1,427 |
| Business, management and finance · TextArena rating, higher is better 154 · 98 of 380 measured | 1,387 | 1,430 |
| Creative writing · TextArena rating, higher is better 138 · 95 of 385 measured | 1,364 | 1,400 |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better 189 · 139 of 249 measured | 9.0 | 14.2 |
| GPQA Diamond% of questions, higher is better 189 · 140 of 232 measured | 57.8% | 74.8% |
| Humanity's Last Exam% of questions, higher is better 225 · 139 of 250 measured | 4.1% | 13.8% |
| UGI Leaderboard reported by UGI Leaderboard · 3 results | ||
| Writing score · UGIscore out of 100, higher is better 136 · 86 of 230 measured | 32.6 | 45.5no reasoning |
| Requested-length error · UGI% off the requested word count, lower is better 111 · 91 of 230 measured | 20.0% | 18.0%no reasoning |
| Style adherence · UGIscore from 0 to 1, higher is better 93 · 108 of 230 measured | 0.35 | 0.35no reasoning |
Show all 16 results (7 more)
| Measure | Mistral Medium 3 | Mistral Medium 3.5 |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Expert prompts · TextArena rating, higher is better 175 · 119 of 338 measured | 1,379 | 1,435 |
| Instruction following · TextArena rating, higher is better 166 · 92 of 387 measured | 1,366 | 1,422 |
| Writing, literature and language · TextArena rating, higher is better 145 · 100 of 386 measured | 1,371 | 1,405 |
| Artificial Analysis reported by Artificial Analysis · 4 results | ||
| IFBench% of instructions, higher is better 139 · 59 of 195 measured | 39.3% | 68.8% |
| Long-context reasoning (AA-LCR)% of questions, higher is better 193 · 120 of 241 measured | 31.3% | 69.3% |
| Terminal-Bench Hard% of tasks, higher is better 162 · 57 of 190 measured | 3.8% | 33.3% |
| τ²-bench telecom% of tasks, higher is better 156 · 25 of 193 measured | 24.3% | 94.2% |
Compare them with other models
Quick answers
Is Mistral Medium 3 better than Mistral Medium 3.5?
Pick Mistral Medium 3.5 if quality matters most: it scores higher (Intelligence Index 14.2 against 9.0). Pick Mistral Medium 3 if cost matters more: it costs 3.8 times less per token.
Which is cheaper, Mistral Medium 3 or Mistral Medium 3.5?
Mistral Medium 3 is cheaper: $0.80 against $3.00 per million tokens, 3.8 times less.
Which is better for agents and tool use, Mistral Medium 3 or Mistral Medium 3.5?
Mistral Medium 3 ranks 83 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 100 for Mistral Medium 3.5.
Which is better for reasoning and knowledge, Mistral Medium 3 or Mistral Medium 3.5?
Mistral Medium 3.5 ranks 123 of 187 models on sale for hard questions across science, maths and general knowledge, against 153 for Mistral Medium 3.
Which is better for writing, Mistral Medium 3 or Mistral Medium 3.5?
Mistral Medium 3.5 ranks 85 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 121 for Mistral Medium 3.
Which has the bigger context window, Mistral Medium 3 or Mistral Medium 3.5?
Mistral Medium 3.5: 262,144 tokens, against 131,072 for Mistral Medium 3.
Run Mistral Medium 3 and Mistral Medium 3.5 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.