Mistral Large 3.5 Benchmarks, Pricing & Rankings
Mistral AI · 2026-07-15 · Open · Current
Snapshot 2026-10-14 · updated weekly
Mistral Large 3.5 ranks #26 of 42 on the AMR leaderboard.
Mistral Large 3.5 benchmark scores
| GPQA Diamond | 80.7% | |
| MMLU-Pro | 78.9% | |
| SWE-Bench Verified | 57.6% | |
| AIME 2025 | 78.9% | |
| LiveCodeBench v6 | 68.9% | |
| Arena Elo | 1365 |
Mistral Large 3.5 price, speed & context
Input price
$0.80
per 1M tokens
Output price
$2.40
per 1M tokens
Speed
132
tok/s
Context
256K
tokens
About Mistral Large 3.5
Mistral Large 3.5 keeps the European open flagship seat with strong function calling and EU-hosted inference options.
Models around Mistral Large 3.5 in the rankings
Mistral Large 3.5 FAQ
Where does Mistral Large 3.5 rank?
Mistral Large 3.5 ranks #26 of 42 tracked AI models on the AMR aggregate as of October 2026, with an aggregate score of 82.3. Its strongest dimension is GPQA Diamond at 80.7%.
How much does Mistral Large 3.5 cost?
Mistral Large 3.5 costs $0.80 per million input tokens and $2.40 per million output tokens on the standard API. At a typical 1:3 input/output agent workload, that blends to roughly $2.00 per million tokens.
What is the Mistral Large 3.5 context window?
Mistral Large 3.5 supports a 256K token context window and generates at a median 132 output tokens per second. That context fits roughly 171 standard documents in a single prompt.
Is Mistral Large 3.5 open source?
Yes — Mistral Large 3.5 ships open weights that you can download and self-host or serve through any compatible inference provider.
What is better than Mistral Large 3.5?
Gemini 3.8 Flash ranks one place higher at #25 with an AMR score of 82.7. Mistral Large 3.5 still wins 5 of the tracked dimensions head-to-head — check the comparison table to see exactly which.