Request a pilot
‹ PublicAI Index

The LLM benchmark aggregator.

Step 5

StepFun

Strongest in General intelligence (#17 of 204, on 1 of its 3 boards), weakest in Agents (#19 of 267). Above par in 4 of 4 scopes. Among the models it meets almost everywhere, it finishes behind Claude Fable 5 and GPT-6 Astra and ahead of Claude Opus 4.5 and Gemini 3.1 Pro.

§ 1 · Profile

What it is good at

Bars run from 50 — the average of the models each source lists — so right of the line is above par. The middle column is the gap to whoever leads that scope.

Core abilities57.8#18/204
General intelligence61.2#17/204
Agents62.3#19/267
Knowledge work66#17/177

§ 2 · Head to head

What it beats, and what beats it

The same models turn up scope after scope. Counted once: where both were placed, who finished higher. Bars run right for Step 5, left for the other.

UI-TARS 1.5 7Bwon 3 · lost 0
Gemma 3 4B Itwon 3 · lost 0
Command Awon 3 · lost 0
Granite 4.2 30Bwon 3 · lost 0
Qwen2.5 Vl 72B Instructwon 3 · lost 0
Nemotron 3 Superwon 3 · lost 0
Mistral Smallwon 3 · lost 0
Gemini 2.5 Flash Litewon 3 · lost 0
Gemma 4 12Bwon 3 · lost 0
Qwen3.5 9Bwon 3 · lost 0
Mistral Mediumwon 3 · lost 0
Kimi K2won 3 · lost 0
GPT-4.1won 3 · lost 0
Gemini 2.5 Flashwon 3 · lost 0
GPT-5.2won 3 · lost 0
GPT-5 Nanowon 3 · lost 0
O4 Miniwon 3 · lost 0
O3won 3 · lost 0
Qwen3 235B A22B Instructwon 3 · lost 0
Grok 4won 3 · lost 0
Qwen3.6 27Bwon 4 · lost 0
Grok 4.3won 4 · lost 0
Gemini 3.5 Flash Litewon 4 · lost 0
GPT-5.4 Miniwon 4 · lost 0
GPT-5.4 Nanowon 4 · lost 0
Kimi K2.7 Codewon 4 · lost 0
Nemotron 3 Ultra 550B A55Bwon 4 · lost 0
Qwen3.6 Pluswon 4 · lost 0
K2 Horizon 0.9Bwon 4 · lost 0
Ministral 3 3Bwon 4 · lost 0
Ministral 3 8Bwon 4 · lost 0
Kimi K2.6won 4 · lost 0
Grok Build 0.1won 4 · lost 0
Ministral 3 14Bwon 4 · lost 0
Celeris 1won 4 · lost 0
GPT-4o Miniwon 4 · lost 0
Mistral Small 4won 4 · lost 0
Qwen3 Coder Nextwon 4 · lost 0
Granite 4.2 3Bwon 4 · lost 0
North Mini Codewon 4 · lost 0
GPT-4.1 Nanowon 4 · lost 0
Mistral Medium 3.5won 4 · lost 0
Granite 4.2 8Bwon 4 · lost 0
Trinity Largewon 4 · lost 0
Gemma 3 27B Itwon 4 · lost 0
MiniMax M3won 4 · lost 0
MiniCPM5 2Bwon 4 · lost 0
Mercury 2.5won 4 · lost 0
Mistral Large 3won 4 · lost 0
GPT-6 Lunawon 4 · lost 0
Nemotron 3.5 Lightningwon 4 · lost 0
Command A+won 4 · lost 0
Llama 4 Scout Instructwon 4 · lost 0
GPT OSS 20Bwon 4 · lost 0
GPT-5.6 Lunawon 4 · lost 0
K2 Horizon 3.7Bwon 4 · lost 0
Qwen3.5 122B A10Bwon 4 · lost 0
Ring 2.6.1Twon 4 · lost 0
Claude Haiku 4.5won 4 · lost 0
Muse Glimmerwon 4 · lost 0
Qwen3.6 35B A3Bwon 4 · lost 0
LongCat 2.0won 4 · lost 0
Inklingwon 4 · lost 0
GPT OSS 120Bwon 4 · lost 0
GLM-5.2won 4 · lost 0
Claude Sonnet 4.6won 4 · lost 0
GLM-4.6won 4 · lost 0
K2 Horizon 7Bwon 4 · lost 0
Muse Spark 1.1won 4 · lost 0
GPT-4.1 Miniwon 4 · lost 0
Qwen3 32Bwon 4 · lost 0
Qwen3 14Bwon 4 · lost 0
Ling 3.0 Flash Finwon 4 · lost 0
Nemotron 3 Ultrawon 4 · lost 0
Claude Sonnet 5won 4 · lost 0
Ling 3.0 Flash VLwon 4 · lost 0
K2 Horizon MoVA 36B A4Bwon 4 · lost 0
Qwen3.7 Pluswon 4 · lost 0
Hy3won 4 · lost 0
DeepSeek V3.2won 4 · lost 0
DeepSeek V3won 4 · lost 0
Apodex 1.1won 4 · lost 0
Mimo V2.5 Prowon 4 · lost 0
GPT-5.5 Instantwon 4 · lost 0
Gemini 3.6 Flashwon 4 · lost 0
Qwen3 30B A3B Thinkingwon 4 · lost 0
DeepSeek V4 Flashwon 4 · lost 0
Llama 4 Maverick Instructwon 4 · lost 0
Qwen3.7 Maxwon 4 · lost 0
DeepSeek V3.1 Terminuswon 4 · lost 0
Claude Sonnet 4.5won 4 · lost 0
Gemini 3.5 Flashwon 4 · lost 0
K2 Horizon 375B A23Bwon 4 · lost 0
Qwen3.8 27Bwon 4 · lost 0
Qwen3.5 397B A17Bwon 4 · lost 0
Gemma 4 31Bwon 4 · lost 0
Qwen3 Next 80B A3B Thinkingwon 4 · lost 0
Gemini 3.1 Flash Litewon 4 · lost 0
DeepSeek V4 Prowon 4 · lost 0
Muse Spark 1.2won 4 · lost 0
Claude Opus 4.7won 4 · lost 0
GPT-5.6 Terrawon 4 · lost 0
DeepSeek R1won 4 · lost 0
DeepSeek V4 Flash Visionwon 4 · lost 0
Gemini 2.5 Prowon 4 · lost 0
GPT-5 Miniwon 4 · lost 0
Gemini 3.8 Flashwon 4 · lost 0
GPT-5.4won 4 · lost 0
GPT-5won 4 · lost 0
Claude Sonnet 4won 4 · lost 0
Gemini 3.7 Flashwon 4 · lost 0
Claude Opus 4.8won 3 · lost 1
Grok 4.5won 3 · lost 1
Gemini 3.1 Prowon 3 · lost 1
Claude Opus 4.5won 2 · lost 1
GLM-5.3 Flashwon 2 · lost 2
GLM-5.3won 2 · lost 2
Qwen3.8 Flash Nextwon 2 · lost 2
Claude Opus 5won 2 · lost 2
Qwen3.8 2.4T A95Bwon 2 · lost 2
Grok 4.6won 2 · lost 2
DeepSeek V4.1 Flashwon 2 · lost 2
Kimi K2.5won 2 · lost 2
GPT-6 Solwon 2 · lost 2
GPT-5.6 Solwon 2 · lost 2
GPT-5.5won 2 · lost 2
Grok 4.7won 1 · lost 3
Gemini 3 Prowon 0 · lost 3
Mimo V2.6 Prowon 0 · lost 4
Qwen3.8 Maxwon 0 · lost 4
Kimi K3won 0 · lost 4
Claude Opus 5.5won 0 · lost 4
Muse Spark 1.3won 0 · lost 4
Claude Fable 5.1won 0 · lost 4
GPT-6 Astrawon 0 · lost 4
Claude Fable 5won 0 · lost 4

§ 3 · Sources

Where the numbers come from

3 publications, 3 figures. Every one links to the page it was read from.

Artificial Analysis ↗1 measureread 2026-09-27
Artificial Analysis Intelligence Index 44
GDPval-AA ↗1 measureread 2026-09-27
GDPval-AA 1566
AA-Briefcase ↗1 measureread 2026-09-27
AA-Briefcase 1432

Badge

PublicAI Index badge for Step 5[![PublicAI Index](https://publicai.io/model-index/badge?model=step-5)](https://publicai.io/model-index/m/step-5)