Request a pilot
‹ PublicAI Index

The LLM benchmark aggregator.

Grok Build 0.1

SpaceXAI

Strongest in Instruction following (#37 of 57), weakest in Safety (#290 of 337). Above par in 3 of 19 scopes. Among the models it meets almost everywhere, it finishes behind GPT-5.5 and Claude Opus 5.5 and ahead of Command A and Qwen3.6 Plus.

§ 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.

Agents53.8#78/268
Knowledge work55.7#47/178
Coding38.8#160/165
Code generation30#77/77
Agentic coding42.7#124/157
Reasoning37.8#162/178
Reasoning39.8#113/140
Mathematics34.2#132/140
Core abilities41.6#180/204
Instruction following45.2#37/57
Data analysis45.6#42/57
Language37.2#51/57
General intelligence38.8#181/204
Safety44.8#290/337
Secure code60.2#66/274
Fairness45.5#182/300
Toxicity avoidance41.3#239/272
Jailbreak resistance32.2#248/272
Harm refusal44.1#260/300

§ 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 Grok Build 0.1, left for the other.

Qwen3.6 27Bwon 10 · lost 3
Grok 4.1 Fastwon 7 · lost 5
Grok 4.3won 11 · lost 8
Gemini 3.5 Flash Litewon 7 · lost 6
Qwen3.6 Pluswon 7 · lost 6
Command Awon 7 · lost 6
GPT-5.4 Miniwon 7 · lost 7
GPT-4o Miniwon 8 · lost 8
Claude 3.5 Haikuwon 5 · lost 7
GPT-5.4 Nanowon 5 · lost 9
GLM-4.6won 5 · lost 9
Gemma 3 27B Itwon 4 · lost 8
DeepSeek V3won 5 · lost 11
Llama 4 Scout Instructwon 4 · lost 9
O3 Miniwon 4 · lost 10
Grok 4won 4 · lost 10
GPT OSS 120Bwon 4 · lost 11
Kimi K2.7 Codewon 5 · lost 14
Gemini 3.5 Flashwon 5 · lost 14
GPT OSS 20Bwon 3 · lost 9
DeepSeek R1won 4 · lost 12
Gemini 2.5 Prowon 4 · lost 12
Gemma 4 12Bwon 3 · lost 11
Mimo V2.5 Prowon 3 · lost 11
Gemma 4 31Bwon 3 · lost 11
Kimi K2.6won 4 · lost 15
GLM-5.2won 4 · lost 15
GPT-4.1 Nanowon 3 · lost 12
Claude Haiku 4.5won 3 · lost 12
GPT-4.1 Miniwon 3 · lost 12
Claude Opus 4.6won 3 · lost 12
GPT-5 Miniwon 3 · lost 12
Claude Sonnet 4won 3 · lost 13
GPT-4owon 2 · lost 10
Claude 3.7 Sonnetwon 2 · lost 10
MiniMax M2.7won 2 · lost 10
MiniMax M3won 3 · lost 16
Gemini 3.6 Flashwon 3 · lost 16
GPT-5.1won 2 · lost 11
Gemini 2.0 Flashwon 2 · lost 11
Kimi K2won 2 · lost 12
Gemini 3.1 Prowon 2 · lost 12
DeepSeek V3.2won 2 · lost 13
Claude Sonnet 4.5won 2 · lost 13
GPT-5won 2 · lost 13
Kimi K2.5won 2 · lost 13
Claude Sonnet 4.6won 2 · lost 15
GLM-5.3 Flashwon 2 · lost 17
Inklingwon 2 · lost 17
Muse Spark 1.1won 2 · lost 17
DeepSeek V4 Flashwon 2 · lost 17
Claude Opus 4.8won 2 · lost 17
DeepSeek V4 Prowon 2 · lost 17
Claude 3.5 Sonnetwon 1 · lost 11
GLM-5.1won 1 · lost 12
Claude Opus 4.5won 1 · lost 12
GLM-5.3won 1 · lost 12
Kimi K2 Thinkingwon 1 · lost 12
Gemini 3.7 Flashwon 1 · lost 12
GPT-4.1won 1 · lost 13
Claude Opus 4won 1 · lost 13
Mimo V2.6 Prowon 1 · lost 13
Gemini 2.5 Flashwon 1 · lost 14
O3won 1 · lost 14
GPT-5.2won 1 · lost 17
GPT-6 Lunawon 1 · lost 18
GPT-5.6 Lunawon 1 · lost 18
Claude Sonnet 5won 1 · lost 18
Qwen3.7 Maxwon 1 · lost 18
Claude Opus 4.7won 1 · lost 18
GPT-5.6 Terrawon 1 · lost 18
Claude Opus 5won 1 · lost 18
Gemini 3.8 Flashwon 1 · lost 18
GPT-5.4won 1 · lost 18
GPT-6 Solwon 1 · lost 18
GPT-5 Nanowon 0 · lost 12
Qwen3.8 27Bwon 0 · lost 13
Qwen3.8 Flash Nextwon 0 · lost 13
Muse Spark 1.2won 0 · lost 13
DeepSeek V4 Flash Visionwon 0 · lost 13
DeepSeek V4.1 Flashwon 0 · lost 13
Kimi K3won 0 · lost 13
Muse Spark 1.3won 0 · lost 13
Claude Fable 5.1won 0 · lost 13
Claude Fable 5won 0 · lost 13
Qwen3 235B A22B Instructwon 0 · lost 14
GPT-6 Astrawon 0 · lost 14
O4 Miniwon 0 · lost 15
Grok 4.5won 0 · lost 19
Grok 4.6won 0 · lost 19
Grok 4.7won 0 · lost 19
Qwen3.8 Maxwon 0 · lost 19
GPT-5.6 Solwon 0 · lost 19
Claude Opus 5.5won 0 · lost 19
GPT-5.5won 0 · lost 19

§ 3 · Sources

Where the numbers come from

4 publications, 16 figures. Every one links to the page it was read from.

GDPval-AA ↗1 measureread 2026-09-26
GDPval-AA 1052
LiveBench ↗8 measuresread 2026-09-26
LiveBench 67.8LiveBench · Reasoning 76.4LiveBench · Coding 65.4LiveBench · Agentic Coding 45.8LiveBench · Mathematics 78.4LiveBench · Data Analysis 70.8LiveBench · Language 72.5LiveBench · Instruction Following 65.2
Vals.ai ↗1 measureread 2026-09-26
Vals · Vibe Code Bench 13.35% (Grok Build)
Enkrypt AI Safety Leaderboard ↗6 measuresread 2026-09-26
Enkrypt · Jailbreak risk 27.8%Enkrypt · Harmful content risk 13.3%Enkrypt · CBRN risk 46.5%Enkrypt · Toxicity risk 12.4%Enkrypt · Bias risk 84.8%Enkrypt · Insecure code risk 12.9%

Badge

PublicAI Index badge for Grok Build 0.1[![PublicAI Index](https://publicai.io/model-index/badge?model=grok-build-0-1)](https://publicai.io/model-index/m/grok-build-0-1)