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 10, 2026Checked: June 14, 2026

Microsoft benchmarks.

A lab-level profile for Microsoft, covering tracked models, category leaders, open/proprietary mix, speed, value, source coverage, and portfolio depth.

All labs

Lab rank

#27

By available Arena average

Models tracked

8

6 open-weight models

Portfolio coverage

15%

Average matched benchmark signals

Fastest model

0.49s

Phi 4

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

Lab profile

Portfolio shape, leaders, and model coverage.

The lab page now starts with the portfolio read, then drills into category leaders, value rankings, and model-level coverage rather than repeating source panels.

Portfolio read

Microsoft has 8 tracked benchmark profiles.

Lab #27

The portfolio combines 2 proprietary models and 6 open-weight models. Its average available Arena rank is 315.6, with a best category rank of #270. Average profile coverage is 15%, so model-level gaps remain visible in the cards below.

Best Arena model

Phi 4

Best category rank #270

Highest coverage

Phi 4

44% matched signals

Fastest response

Phi 4

0.49s first token

Access mix

Open versus proprietary

Proprietary

2 / 25%

Open weights

6 / 75%

Value leader

Phi 4

Category leaders

Best model by benchmark lens.

Each card shows the highest-ranked model from this lab in a composite benchmark suite, with the global rank and index left intact.

Value

Quality, price, latency, and speed

Phi 4

#9365

value index

Coding

Code Arena, SWE-bench, and output speed

Phi 4

#1231

coding index

Agents

Search, document, code, and latency

Phi 4

#5100

agent proxy

Reasoning

Text, document, vision, and mode signals

Phi 4

#24453

reasoning proxy

Context

Document, search, and text proxy

Phi 4

#26953

context proxy

Microsoft value ranking table

Models from this lab with both quality and commercial price matches.

Top 1 of 1

RankModelIndexPriceLatencySpeedQualitySources
#93
Phi 4

phi-4

MicrosoftOpen weights
65value index
$0.219blended / 1M tokens
0.49stime to first token
41 tok/soutput speed
53quality signal
ArenaArtificial Analysis
#93
Phi 4

phi-4

MicrosoftOpen weights
65value index
Price
$0.219blended / 1M tokens
Latency
0.49stime to first token
Speed
41 tok/soutput speed
Quality
53quality signal
ArenaArtificial Analysis

Model portfolio

Microsoft model coverage map.

Every tracked model keeps its best Arena rank, coverage score, commercial metrics, and suite placement visible in one scannable grid.

Phi 4

phi-4

Open weights

Coverage

44%

Best Arena

#270

Text

Value

#93

value index

Coding

#123

coding index

Latency

0.49s

41 tok/s

$0.219

Phi 3 Medium 4K Instruct

phi-3-medium-4k-instruct

Open weights

Coverage

11%

Best Arena

#298

Text

Value

Not listed

No price match

Coding

Not listed

No coding index

Latency

Not listed

Not listed

Not listed

Wizardlm 70b

wizardlm-70b

Proprietary

Coverage

11%

Best Arena

#303

Text

Value

Not listed

No price match

Coding

Not listed

No coding index

Latency

Not listed

Not listed

Not listed

Phi 3 Small 8K Instruct

phi-3-small-8k-instruct

Open weights

Coverage

11%

Best Arena

#316

Text

Value

Not listed

No price match

Coding

Not listed

No coding index

Latency

Not listed

Not listed

Not listed

Wizardlm 13b

wizardlm-13b

Proprietary

Coverage

11%

Best Arena

#328

Text

Value

Not listed

No price match

Coding

Not listed

No coding index

Latency

Not listed

Not listed

Not listed

Phi 3 Mini 4K Instruct June 2024

phi-3-mini-4k-instruct-june-2024

Open weights

Coverage

11%

Best Arena

#331

Text

Value

Not listed

No price match

Coding

Not listed

No coding index

Latency

Not listed

Not listed

Not listed

Phi 3 Mini 128K Instruct

phi-3-mini-128k-instruct

Open weights

Coverage

11%

Best Arena

#339

Text

Value

Not listed

No price match

Coding

Not listed

No coding index

Latency

Not listed

Not listed

Not listed

Phi 3 Mini 4K Instruct

phi-3-mini-4k-instruct

Open weights

Coverage

11%

Best Arena

#340

Text

Value

Not listed

No price match

Coding

Not listed

No coding index

Latency

Not listed

Not listed

Not listed