74.8%
GPQA Diamond (AA run)
Models / Mistral
Mistral Medium · Released 2026-04-29
Listed on Artificial Analysis with API pricing $1.5/$7.5 per 1M tokens. Benchmark rows sync from the AA snapshot — see the ledger on this page.
Frontier model tracked on Artificial Analysis. Use the benchmark ledger below for sourced scores; we do not infer numbers beyond published rows.
Family profile
Best published score in each covered benchmark family.
4 tested benchmark families
Where Mistral Medium 3.5 places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.
| Benchmark | Family | Rank | Score | Source | Date |
|---|---|---|---|---|---|
| AA output speed | Performance | #33/ 219 | Artificial Analysis | 2026-11-20 | |
| Terminal-Bench | Agentic | #75/ 167 | 51 | Artificial Analysis | 2026-09-28 |
| SciCode | Coding | #82/ 97 | 40 | Artificial Analysis | 2026-09-28 |
| AA-LCR | Long context | #130/ 184 | 69 | Artificial Analysis | 2026-09-28 |
| Humanity's Last Exam | Reasoning | #149/ 186 | 14 | Artificial Analysis | 2026-09-28 |
| GPQA Diamond | Reasoning | #155/ 184 | 75 | Artificial Analysis | 2026-09-28 |
The three highest-scoring models with pages in each capability family. Where Mistral Medium 3.5 shows up, it's highlighted.
Benchmark rows added to the public ledger for Mistral Medium 3.5 in the last 120 days. Older rows live in the full table below.
| Benchmark | Family | Score | Source | Days ago |
|---|---|---|---|---|
| AA output speed | Performance | 171 t/s | Artificial Analysis | 2 |
| AA-LCR | Long context | 69.33% | Artificial Analysis | 55 |
| GPQA Diamond | Reasoning | 74.8% | Artificial Analysis | 55 |
| Humanity's Last Exam | Reasoning | 13.8% | Artificial Analysis | 55 |
| SciCode | Coding | 40.2% | Artificial Analysis | 55 |
| Terminal-Bench | Agentic | 50.56% | Artificial Analysis | 55 |
A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.
Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.
Every catalog benchmark for Mistral Medium 3.5. Scores link to the original source; gaps mean no public row exists yet.
6 of 13 catalog benchmarks have a sourced row for Mistral Medium 3.5.
74.8%
GPQA Diamond (AA run)
13.8%
HLE (AA run)
40.2%
SciCode (AA run)
50.56%
Terminal-Bench v2.1 (AA run)
69.33%
AA-LCR (AA run)
171 t/s
Output tokens/s (5-day average across workloads, default provider)
Permanent URL
Every format below points at version 3, published 20 Nov 2026. That URL shows exactly this record for as long as VerdictPal exists, so your reference needs no access date.
VerdictPal Editorial Desk. (2026, November 20). Mistral Medium 3.5: VerdictPal model page (Version 3). VerdictPal. https://verdictpal.com/models/mistral-medium-3-5/v/3
APA 7, web page with a group author. Paste into your reference list.
Permanent URL https://verdictpal.com/models/mistral-medium-3-5/v/3
Every answer below is assembled from the dated fields on this page. Nothing is written separately for search.
Mistral Medium 3.5 is a Mistral model: Listed on Artificial Analysis with API pricing $1.5/$7.5 per 1M tokens. Benchmark rows sync from the AA snapshot — see the ledger on this page.
Frontier model tracked on Artificial Analysis. Use the benchmark ledger below for sourced scores; we do not infer numbers beyond published rows.
Mistral Medium 3.5 lists $1.5 input and $7.5 output per 1M tokens. Pricing last checked 2026-08-01.
Mistral Medium 3.5 does not publish a context window on the sources checked for this page.
Mistral Medium 3.5 carries Solid status on the model atlas.
Model alerts · Weekly digest
One email when a model lands in the atlas or gets new benchmark scores, and a Monday digest of what changed for research tools and models. Built from the same sourced data as this page.
See what changed recently →