Compare / head-to-head
Mistral Large 3vsMistral Medium 3.5
Mistral Large 3 leads 1 of 1 shared benchmark. Mistral Large 3 is 4.5x cheaper per token. Both offer a 256K-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
1 – 0
Mistral Large 3 leads
Cheaper per token
Mistral Large 3
4.5x cheaper, input + output
Larger context
Tie
both 256K tokens
Provider uptime (30d)
100%
Mistral AI
Mistral Large 3
Mistral AI · released 2025-12-02
textvision
Mistral Medium 3.5
Mistral AI · released 2026-04-28
textvision
Quality
Benchmark matrix
1 shared · 0 only Mistral Large 3 · 2 only Mistral Medium 3.5| Benchmark | Mistral Large 3 | Mistral Medium 3.5 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 1 | ||||
| LMArena Elo | 1427 ↗ | 1420.6 ↗ | +6.4 | Mistral Large 3 |
| Only Mistral Large 3 reports · 0 | ||||
| Mistral Large 3 reports nothing Mistral Medium 3.5 does not. | ||||
| Only Mistral Medium 3.5 reports · 2 | ||||
| SWE-bench Verified | not reported | 77.6% ↗ | — | — |
| Tau3 Telecom | not reported | 91.4 ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Mistral Large 3 minus Mistral Medium 3.5 in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | Mistral Large 3 | Mistral Medium 3.5 | Edge |
|---|---|---|---|
| Context window | 256K tokens | 256K tokens | Tie |
| Max output | — | — | — |
| Input price / 1M | $0.5 ↗ | $1.5 ↗ | Mistral Large 3 |
| Output price / 1M | $1.5 ↗ | $7.5 ↗ | Mistral Large 3 |
| Cached input / 1M | $0.05 ↗ | $0.15 ↗ | Mistral Large 3 |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $2 | $9 | Mistral Large 3 |
| Modalities | text · vision | text · vision | Tie |
| Released | 2025-12-02 | 2026-04-28 | — |
| Cited benchmark scores | 1 | 3 | — |
Reliability
Mistral AI status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Mistral Large 3 vs …
Models sharing the most benchmarksMore matchups
Mistral Medium 3.5 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Mistral Large 3 and Mistral Medium 3.5 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.