BenchLeader

Mistral Medium 3.1

Quality#183 of 333
48.3Index
Below the median
−1.7 on the median
Price#118 of 249
$0.800per 1M tokens
Cheaper than most
0.9× the median
Speed#106 of 215
78tokens/s
Above the median
1.0× the median

55 cheaper ranked models score higher: DeepSeek V4.1 Flash 1017 (59.2, $0.525), DeepSeek V4.1 Flash (59.0, $0.518), GPT-5.6 Luna (58.5, $0.450) and 52 more.

As of 8 Nov 2026, Mistral Medium 3.1 by Mistral AI scores 48.3 on the BenchLeader Index (593 ranked configurations), with its best results in reasoning (58) and weakest in agents & tools (38). API pricing: $0.400 per 1M input tokens and $2.00 per 1M output tokens ($0.800 blended at 3:1), list price on 8 Nov 2026. It streams about 78 tokens/s (OpenRouter). Released 12 Aug 2025.

Key facts (as of 8 Nov 2026)

  • Mistral Medium 3.1 API pricing: $0.400 per 1M input tokens and $2.00 per 1M output tokens ($0.800 blended at 3:1) (list price, 8 Nov 2026).
  • Mistral Medium 3.1 streams about 78 tokens/s (OpenRouter, 8 Nov 2026).
  • Mistral Medium 3.1 was released on 12 Aug 2025 (Mistral AI).

In detail. Mistral Medium 3.1 is a Mistral AI proprietary model, released 12 Aug 2025. Its best configuration ranks #373 of 593 on the BenchLeader Index at 48.3 ±5.5, in the lower half. The ± is the point: 273 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in reasoning (58) and lowest in agents & tools (38). At $0.800 per million tokens blended it is mid-priced. Output speed of 78 tokens per second puts it faster than most, with a first token in 0.7 s. Last measured 6 Nov 2026.

Blended price
$0.800/M
$0.400 in · $2.00 out
via models.dev
Output speed
78 tok/s
OpenRouter traffic, 7-day median; not yet measured by Artificial Analysis
First answer
0.66 s
Context
262k
via models.dev
Full answer
–
Cost per task
–
Tokens per task
–
Released
12 Aug 2025
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Overall index48
  2. Reasoning58
  3. Coding42
  4. Agents & tools38
  5. Maths57
  6. Instruction following43
  7. Human preference58
  8. Multimodal42
  9. Long context45

Get an email when Mistral AI ships a new model

And once when it gets ranked, plus the weekly review on Mondays.

Choose providers and emails

Versions

Mistral AI has shipped 4 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.

ModelReleasedIndexRank
Mistral Medium 3.528 Apr 202646.6#416
Mistral Medium 3.1this page12 Aug 202548.3#373
Mistral Medium 37 May 202544.3#458
Mistral Medium 231211 Dec 2023––

How its index has moved

10 Sep 2026 to 29 Oct 2026
424854

The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.

Benchmark results

See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

Benchmarknot statedSourceTrend
Arena Hard Prompts1427#147Arena (LMArena)
GPQA Diamond (AA)not in index58.8%#391Artificial Analysis
Humanity's Last Exam (AA)not in index4.7%#495Artificial Analysis
CritPtnot in index0.0%#329Artificial Analysis
LMCAnot in index19.1%#162Epoch AI Benchmarking Hub
DTBenchnot in index67.5%#166Epoch AI Benchmarking Hub

Coding

Agents & tools

Maths

Benchmarknot statedSourceTrend
Arena Maths1395#160Arena (LMArena)

Instruction following

Benchmarknot statedSourceTrend
IFBench39.8%#267Artificial Analysis
Arena Instruction Followingnot in index1395#152Arena (LMArena)

Human preference

Benchmarknot statedSourceTrend
Arena Text1408#149Arena (LMArena)
Arena Creative Writingnot in index1378#143Arena (LMArena)
Arena Multi-turnnot in index1406#150Arena (LMArena)
Arena Longer Queriesnot in index1408#154Arena (LMArena)

Multimodal

Benchmarknot statedSourceTrend
Arena Vision1172#107Arena (LMArena)
MMMU-Pro54.2%#242Artificial Analysis

Long context

Benchmarknot statedSourceTrend
AA-LCR v1.142.7%#362Artificial Analysis
MLCRnot in index2.8%#162Artificial Analysis

Composite

Benchmarknot statedSourceTrend
AA Intelligence Index v4.3.2not in index9.2#417Artificial Analysis
AA Progress Index v1not in index192.8#446Artificial Analysis

API pricing: where to run it

Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.

ProviderSpeedFirst tokenInput $/MOutput $/MContextQuantisation
Mistral133 tok/s0.87 s$0.440$2.20131k–
Mistral75 tok/s0.69 s$0.400$2.00131k–

What a task costs

Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.

WorkloadTokens in / outCostWith cachingTime
Chat reply400 / 300$0.0008–4.5 s
Summarize a 30-page report12,000 / 600$0.0060–8.4 s
Code edit6,000 / 1,500$0.0054–19.9 s
Agentic coding session60,000 / 4,000$0.032–51.9 s
Structured extraction2,000 / 200$0.0012–3.2 s

More from Mistral AI

New this month

See also

Embed or cite

Show where Mistral Medium 3.1 ranks on a model card or README. The badge redraws itself with every daily update, carries the data date and links back to this page. To see ranks like this on OpenRouter and Hugging Face model pages, get the Chrome extension.

[![Mistral Medium 3.1 on BenchLeader: #180 overall](https://www.benchleader.com/badge/mistral-medium-3-1.svg)](https://www.benchleader.com/models/mistral-medium-3-1)

Cite this

The ranking changes daily, so a reference carries the data date. APA style:

BenchLeader. (2026, November 8). Mistral Medium 3.1 on the BenchLeader Index (method v1.4) [Data set]. Retrieved November 8, 2026, from https://www.benchleader.com/models/mistral-medium-3-1

BibTeX:

@misc{benchleader_mistral_medium_3_1_20261108,
  author       = {{BenchLeader}},
  title        = {{Mistral Medium 3.1 on the BenchLeader Index (method v1.4)}},
  year         = {2026},
  month        = nov,
  howpublished = {\url{https://www.benchleader.com/models/mistral-medium-3-1}},
  note         = {Data as of 2026-11-08}
}

Every badge style, the embeddable top-10 widget and how to cite the Index

Questions people ask

What are Mistral Medium 3.1's benchmark scores?
As of 8 Nov 2026, Mistral Medium 3.1 scores 48.3 ±5.5 on the BenchLeader Index, strongest in reasoning (58) and weakest in agents & tools (38). That rests on independent benchmark results only, and every score on this page links to its publisher.
How does Mistral Medium 3.1 rank?
Mistral Medium 3.1 is #373 of 593 ranked configurations on 8 Nov 2026. 273 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 69.4.
How much does Mistral Medium 3.1 cost per 1M tokens?
As of 8 Nov 2026, Mistral Medium 3.1 costs $0.400 per 1M input tokens and $2.00 per 1M output tokens, $0.800 blended (three input tokens per output token).
When was Mistral Medium 3.1 released?
Mistral AI released Mistral Medium 3.1 on 12 Aug 2025.

Data as of 8 Nov 2026. Compare with another model.

Cite as: BenchLeader, “Mistral Medium 3.1: benchmarks, pricing, speed and rank”, data as of 8 Nov 2026, https://www.benchleader.com/models/mistral-medium-3-1.