Thoughts on AI, technology, and the future we're building.

New posts every week

HomeAll PostsAI NewsAI Basics
Timelines
ChatGPTOpenAI release historyAnthropic ClaudeClaude release historyGoogle GeminiGemini release history
Benchmarks
OverviewFull model trackerValue RankingsPerformance for the moneyCoding RankingsSWE-bench and code signalsAgent RankingsTool and workflow signalsReasoning RankingsKnowledge and reasoningLong ContextDocument and retrieval signalsLab ComparisonsProvider-level rankings
CategoriesAboutContact

Subscribe to Newsletter

Practical AI news, tips, tricks, tool analysis, sent straight to your inbox.

No spam. Unsubscribe anytime.

Practical explainers, tool notes, and systems thinking for people turning new AI capability into useful work.

Explore

  • All Posts
  • Categories
  • About
  • Contact

Categories

  • AI News
  • AI Basics
  • ChatGPT
  • Anthropic
  • AI Tools
  • AI Video
  • AI Images
  • Courses

Connect

LinkedInTwitterRSS

© 2026. All rights reserved.

Benchmark suiteLatest source data: Jun 5, 2026Checked: June 10, 2026

Mistral Medium 3.5.

A model-level benchmark profile for Mistral Medium 3.5, combining Arena category ranks, suite indexes, commercial price and speed data, SWE-bench status, and lab context.

Mistral lab page

Lab

Mistral

Open weights

Coverage

67%

6 of 9 tracked signals

Best Arena rank

#58

Vision Arena

Best suite

#65

Value / 52

OverviewFull public trackerValuePerformance for the moneyCodingCode and SWE-bench signalsAgentsTool and workflow readinessReasoningKnowledge and reasoning signalsContextDocument and retrieval signalsLabsProvider comparisons

Model profile

Benchmark signal map.

This view treats missing values as coverage gaps, then puts every available score, rank, cost, and speed signal into the same visual hierarchy.

Analyst view

Mistral Medium 3.5 is strongest on value.

67% coverage

Its best composite result is rank #65 in the value view, with a 52 value index. The strongest raw Arena signal is Vision Arena at rank #58 with 3,861 public votes.

Best current lane

Value

#65 / 52 value index

Strongest raw signal

Vision

#58, 1198 score

Commercial posture

$3.00

0.56s first token / 118 tok/s

Coverage gaps

Search ArenaDocument ArenaSWE-bench

Profile completeness

6 of 9 signals matched

67%

Arena categories

3/5

Vision, Code, Text

Commercial match

Live

Mistral Medium 3.5

SWE-bench

Not listed

No confident software benchmark row

Raw identifier

mistral-medium-3.5

Open weights

Performance cockpit

Public benchmark scores

Arena rows show score, public rank, confidence interval, vote count, and publish date. Missing rows stay visible as coverage gaps.

Text Arena

Arena category

1,425#78

1416-1433 CI

6,089 votes

Jun 4, 2026

Arena public leaderboard dataset

WebDev Arena

Arena category

1,269#69

1249-1288 CI

1,260 votes

Jun 5, 2026

Arena public leaderboard dataset

Vision Arena

Arena category

1,198#58

1186-1209 CI

3,861 votes

Jun 5, 2026

Arena public leaderboard dataset

Search Arena

Arena category

Not listed

No confident public Arena row for this category.

Coverage gap

Document Arena

Arena category

Not listed

No confident public Arena row for this category.

Coverage gap

SWE-bench Verified

Software issue resolution

Not listed

No confident SWE-bench row matched to this model.

Coverage gap

Cost and speed

Commercial profile

Price, latency, and throughput are only shown when a confident commercial source row is matched.

Blended price

$3.00

USD / 1M tokens

Input price

$1.50

USD / 1M input tokens

Output price

$7.50

USD / 1M output tokens

Latency

0.56s

Median time to first token

Output speed

118 tok/s

Median generation speed

Matched source row

Mistral Medium 3.5

Suite position

Composite ranks by benchmark lens.

These views combine available public signals into purpose-specific indexes. A missing card means the model lacks enough source coverage for that lens.

Value

Quality, price, latency, and output speed

#6552

value index

blended / 1M tokens$3.00
time to first token0.56s
output speed118 tok/s

Coding

Code Arena, SWE-bench, and output speed

#7033

coding index

Code Arena rank #691,269
No confident matchNot listed
output speed118 tok/s

Agents

Search, documents, code, and latency

#9064

agent proxy

Search ArenaNot listed
Docs ArenaNot listed
latency0.56s

Reasoning

Text, documents, vision, and mode signal

#10424

reasoning proxy

Text Arena rank #781,425
Docs ArenaNot listed
Vision Arena rank #581,198

Long context

Document, search, and text benchmark proxy

#9911

context proxy

Docs ArenaNot listed
Search ArenaNot listed
Text Arena rank #781,425

Lab context

Nearby Mistral profiles.

Same-lab models make it easier to see whether this profile is a flagship, value play, specialist, or lower-coverage row.

Full lab

Mistral Large 3

mistral-large-3

Open weights

Best rank

#77

Coverage

56%

Mistral Medium 2508

mistral-medium-2508

Proprietary

Best rank

#78

Coverage

11%

Mistral Medium 2505

mistral-medium-2505

Proprietary

Best rank

#80

Coverage

11%

Devstral 2

devstral-2

Open weights

Best rank

#81

Coverage

33%

Devstral Medium 2507

devstral-medium-2507

Proprietary

Best rank

#85

Coverage

11%

Mistral Small 2506

mistral-small-2506

Open weights

Best rank

#87

Coverage

11%

Mistral Small 3.1 24b Instruct 2503

mistral-small-3.1-24b-instruct-2503

Open weights

Best rank

#90

Coverage

11%