Skytells
HomeModelsCLIChangelog
  • Home
  • Models
  • CLI
  • Changelog
Skytells

Addressing the world's greatest challenges with AI. Enterprise research, foundation models, and infrastructure trusted by organizations worldwide since 2012.

Get Started

  • Console
  • Learn
  • Documentation
  • API Reference
  • Pricing
  • ModelsNew

Platform

  • Cloud AgentsNew
  • AI Solutions
  • Infrastructure
  • Edge Network
  • Trust Center
  • CLI

Resources

  • Blog
  • Changelog
  • AI Leaderboard
  • Research
  • Status

Company

  • About
  • Careers
  • Legal
  • Privacy Policy

© 2012–2026 Skytells, Inc. All rights reserved.

Live rankings

AI Model Leaderboard

Every major AI model ranked across benchmark quality, inference speed, agentic capability, programming aptitude, and cost efficiency — updated continuously from published evaluation data.

Explore full leaderboardBrowse model catalog

334

Tracked models

29

Providers

286

Benchmarked

29.3

Avg. index

OverallBenchmarksInferenceAgenticProgrammingValue / Price

334 models

RankModelProviderScoreBenchmarksInferenceAgenticProgrammingValuePrice
241

Qwen2.5 VL 72B Instruct

qwen2.5-vl-72b

multimodalvisionmulti-input reasoning
AAlibaba Cloud / Qwen Team

14.6

overall

22.70.05.20.00.0N/A
242

Phi 4

phi-4

textinference
MMicrosoft

14.4

overall

14.40.00.00.00.0N/A
243

Qwen2.5 14B Instruct

qwen-2.5-14b-instruct

textinference
AAlibaba Cloud / Qwen Team

13.4

overall

13.40.00.00.00.0N/A
244

Qwen3.5-2B

qwen3.5-2b

multimodalvisionmulti-input reasoning
AAlibaba Cloud / Qwen Team

13.2

overall

13.20.00.00.00.0N/A
245

Mistral Small 3 24B Instruct

mistral-small-24b-instruct-2501

textinference
Mistral AI

13.0

overall

13.00.00.00.00.0N/A
246

Mistral Small 3.1 24B Base

mistral-small-3.1-24b-base-2503

multimodalvisionmulti-input reasoning
Mistral AI

12.9

overall

12.90.00.00.00.0
247

Nova Lite

nova-lite

multimodalvisionmulti-input reasoning
AAmazon

12.9

overall

12.90.00.00.00.0N/A
248

Gemini 2.5 Flash-Lite

gemini-2.5-flash-lite

multimodalvisionmulti-input reasoning
Google

12.7

overall

20.30.00.02.90.0
249

Devstral Small 1.1

devstral-small-2507

codeprogrammingtool use
Mistral AI

12.5

overall

0.00.00.012.50.0N/A
250

Qwen2.5 VL 32B Instruct

qwen2.5-vl-32b

multimodalvisionmulti-input reasoning
AAlibaba Cloud / Qwen Team

11.2

overall

19.40.01.50.00.0N/A
251

Qwen2 72B Instruct

qwen2-72b-instruct

textinference
AAlibaba Cloud / Qwen Team

11.0

overall

11.00.00.00.00.0N/A
252

Llama 3.1 70B Instruct

llama-3.1-70b-instruct

textinference
MMeta

10.3

overall

10.30.00.00.00.0N/A
253

Gemini 1.5 Flash 8B

gemini-1.5-flash-8b

multimodalvisionmulti-input reasoning
Google

9.9

overall

9.90.00.00.00.0
254

Grok-1.5V

grok-1.5v

multimodalvisionmulti-input reasoning
xAI

9.7

overall

9.70.00.00.00.0N/A
255

Claude 3 Sonnet

claude-3-sonnet-20240229

multimodalvisionmulti-input reasoning
Anthropic

9.2

overall

9.20.00.00.00.0
256

Mistral Large 3

mistral-large-3-2509

multimodalvisionmulti-input reasoning
Mistral AI

8.8

overall

8.80.00.00.00.0
257

Gemma 3 12B

gemma-3-12b-it

multimodalvisionmulti-input reasoning
Google

8.6

overall

8.60.00.00.00.0N/A
258

Gemma 4 E2B

gemma-4-e2b-it

multimodalvisionmulti-input reasoning
Google

8.5

overall

8.50.00.00.00.0N/A
259

Nova Micro

nova-micro

textinference
AAmazon

8.4

overall

8.40.00.00.00.0N/A
260

Grok-1.5

grok-1.5

multimodalvisionmulti-input reasoning
xAI

8.2

overall

8.20.00.00.00.0N/A
241
A

Qwen2.5 VL 72B Instruct

Alibaba Cloud / Qwen Team

14.6

N/A

242
M

Phi 4

Microsoft

14.4

N/A

243
A

Qwen2.5 14B Instruct

Alibaba Cloud / Qwen Team

13.4

N/A

244

Page 13 of 17 · 334 models

PreviousNext

Want benchmark charts, model comparison, and pricing analytics?

Sign in to access the full interactive leaderboard with deep benchmark breakdowns and model comparison tools.

Open full leaderboard

Rankings are based on multi-dimensional evaluation across benchmark quality, inference efficiency, and cost-per-output. Scores are updated continuously and may differ from individual third-party benchmarks.

N/A
N/A
N/A
N/A
N/A
A

Qwen3.5-2B

Alibaba Cloud / Qwen Team

13.2

N/A

245

Mistral Small 3 24B Instruct

Mistral AI

13.0

N/A

246

Mistral Small 3.1 24B Base

Mistral AI

12.9

N/A

247
A

Nova Lite

Amazon

12.9

N/A

248

Gemini 2.5 Flash-Lite

Google

12.7

N/A

249

Devstral Small 1.1

Mistral AI

12.5

N/A

250
A

Qwen2.5 VL 32B Instruct

Alibaba Cloud / Qwen Team

11.2

N/A

251
A

Qwen2 72B Instruct

Alibaba Cloud / Qwen Team

11.0

N/A

252
M

Llama 3.1 70B Instruct

Meta

10.3

N/A

253

Gemini 1.5 Flash 8B

Google

9.9

N/A

254

Grok-1.5V

xAI

9.7

N/A

255

Claude 3 Sonnet

Anthropic

9.2

N/A

256

Mistral Large 3

Mistral AI

8.8

N/A

257

Gemma 3 12B

Google

8.6

N/A

258

Gemma 4 E2B

Google

8.5

N/A

259
A

Nova Micro

Amazon

8.4

N/A

260

Grok-1.5

xAI

8.2

N/A