Request a Pilot
‹ PublicAI Index

The LLM benchmark aggregator.

Ox Alpha

Other

Strongest in Instruction following (#53 of 62), weakest in Core abilities (#188 of 199). Above par in 3 of 8 scopes. Among the models it meets almost everywhere, it finishes behind Claude Fable 5 and GPT-6 Astra and ahead of Mistral Medium 3.5 and Command A.

§ 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.

Coding50.3#85/179
Agentic coding50.3#82/173
Reasoning43.1#153/195
Reasoning51.1#61/147
Mathematics34.6#144/152
Core abilities39.3#188/199
Instruction following36.4#53/62
Language34.2#57/62

§ 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 Ox Alpha, left for the other.

Gemma 4 31Bwon 5 · lost 0
NVIDIA Nemotron 3.5 Lightning 30B A3Bwon 7 · lost 0
Qwen3.6 27Bwon 6 · lost 1
GPT-4owon 4 · lost 1
Nemotron 3.5 Super VLwon 4 · lost 1
Smaug Nemotron 3.5won 4 · lost 1
GPT-4o miniwon 4 · lost 2
GPT-4.1 nanowon 4 · lost 2
Gemini 2.0 Flashwon 4 · lost 2
Mistral Large 3won 4 · lost 2
Llama 4 Maverick Instructwon 4 · lost 2
MiniMax M3won 5 · lost 3
Gemini 3.5 Flash-Litewon 5 · lost 3
Claude Haiku 4.5won 3 · lost 2
GPT-5.1won 3 · lost 2
Claude 3.5 Sonnetwon 3 · lost 2
GLM-4.7won 3 · lost 2
Muse Spark Openwon 3 · lost 2
Command Awon 3 · lost 2
Mistral Medium 3.5won 3 · lost 2
Inkling Smallwon 3 · lost 3
GPT OSS 120Bwon 3 · lost 3
GPT-4.1 miniwon 3 · lost 3
DeepSeek V3.2won 3 · lost 3
DeepSeek V3won 3 · lost 3
MiniMax M2.5won 3 · lost 3
Claude Sonnet 4.5won 3 · lost 3
Kimi K2 Thinkingwon 3 · lost 3
Grok 4 Fastwon 3 · lost 3
GPT-5 miniwon 3 · lost 3
Gemini 2.5 Prowon 3 · lost 3
GLM-5won 3 · lost 3
Kimi K2.5won 3 · lost 3
GPT-5.4 miniwon 4 · lost 4
GPT-5.4 nanowon 4 · lost 4
Qwen3.6 Pluswon 3 · lost 4
Grok Build 0.1won 3 · lost 4
Grok 4.1 Fastwon 2 · lost 3
Gemini 3 Flashwon 2 · lost 3
GLM-4.6won 2 · lost 3
Gemini 3.1 Flash-Litewon 2 · lost 3
Qwen3 Maxwon 2 · lost 3
Kimi K2.7 Codewon 3 · lost 5
Inklingwon 3 · lost 5
NVIDIA Nemotron 3 Ultra 550B A55Bwon 3 · lost 5
Beam 1.0won 2 · lost 4
GPT-4.1won 2 · lost 4
Grok 4.20won 2 · lost 4
Gemini 3 Prowon 2 · lost 4
Grok 4.3won 2 · lost 5
Kimi K2.6won 2 · lost 5
GPT-5.2 Codexwon 2 · lost 5
Claude Haiku 5.5won 2 · lost 6
GPT-5.6 Lunawon 2 · lost 6
GPT-6 Lunawon 2 · lost 6
Mistral Large 4won 2 · lost 6
GLM-5.3 Flashwon 2 · lost 6
Claude Sonnet 4.6won 2 · lost 6
GPT-5.2won 2 · lost 6
Claude Opus 4.5won 2 · lost 6
Qwen3.7 Maxwon 2 · lost 6
Gemini 3.6 Flashwon 2 · lost 6
Gemini 3.5 Flashwon 2 · lost 6
Gemini 3.1 Prowon 2 · lost 6
MiniMax M2.1won 1 · lost 4
O1won 1 · lost 4
Claude 3.7 Sonnetwon 1 · lost 4
O3 Miniwon 1 · lost 4
MiniMax M3.1 Flashwon 1 · lost 4
O3 Prowon 1 · lost 4
Step 5won 1 · lost 5
Kimi K2won 1 · lost 5
MiMo V2.6 Prowon 1 · lost 5
Qwen3 235B A22B Instructwon 1 · lost 5
Gemini 2.5 Flashwon 1 · lost 5
Grok 3 Miniwon 1 · lost 5
Grok 3won 1 · lost 5
O4 Miniwon 1 · lost 5
O3won 1 · lost 5
DeepSeek R1won 1 · lost 5
GPT-5won 1 · lost 5
Claude Sonnet 4won 1 · lost 5
Claude Opus 4won 1 · lost 5
GLM-5.2won 1 · lost 7
Qwen3.8 27Bwon 1 · lost 7
Claude Opus 4.6won 1 · lost 7
Grok 4.7won 1 · lost 7
MiMo V2.6 Flashwon 0 · lost 5
Inkling 2 Smallwon 0 · lost 5
Muse Emberwon 0 · lost 5
Muse Wonder Fullwon 0 · lost 5
GPT-6.1 Terrawon 0 · lost 5
Gemini 4 Carbonwon 0 · lost 5
Kimi K3.1 Prowon 0 · lost 6
Grok 4won 0 · lost 6
Gemini 4 Argonwon 0 · lost 6
Claude Fable 5.2won 0 · lost 6
Muse Spark 1.1won 0 · lost 7
DeepSeek V4 Flash Visionwon 0 · lost 7
Qwen3.8 Flash Nextwon 0 · lost 7
Claude Sonnet 5won 0 · lost 8
DeepSeek V4 Flashwon 0 · lost 8
DeepSeek V4 Prowon 0 · lost 8
GPT-5.6 Terrawon 0 · lost 8
Gemini 3.8 Flashwon 0 · lost 8
Claude Opus 5won 0 · lost 8
GLM-5.3won 0 · lost 8
Grok 4.6won 0 · lost 8
GPT-6 Solwon 0 · lost 8
Muse Spark 1.2won 0 · lost 8
Qwen3.8 Maxwon 0 · lost 8
Claude Sonnet 5.5won 0 · lost 8
Claude Opus 4.7won 0 · lost 8
DeepSeek V4.1 Flashwon 0 · lost 8
GPT-5.4won 0 · lost 8
Kimi K3won 0 · lost 8
GPT-5.6 Solwon 0 · lost 8
Muse Spark 1.3won 0 · lost 8
Muse Wonderwon 0 · lost 8
Grok 4.5won 0 · lost 8
Claude Opus 4.8won 0 · lost 8
Claude Opus 5.5won 0 · lost 8
Claude Fable 5.1won 0 · lost 8
Gemini 3.7 Flashwon 0 · lost 8
GPT-5.5won 0 · lost 8
GPT-6.1 Solwon 0 · lost 8
GPT-6 Astrawon 0 · lost 8
Claude Fable 5won 0 · lost 8

§ 3 · Sources

Where the numbers come from

2 publications, 9 figures. Every one links to the page it was read from.

LiveBench 1.0 ↗8 measuresread 2026-11-10
LiveBench 1.0 69.2LiveBench 1.0 · Reasoning 76.6LiveBench 1.0 · Coding 75.8LiveBench 1.0 · Agentic Coding 52.6LiveBench 1.0 · Mathematics 77.5LiveBench 1.0 · Data Analysis 75.8LiveBench 1.0 · Language 66.1LiveBench 1.0 · Instruction Following 60.3
SimpleBench ↗1 measureread 2026-11-10
SimpleBench 55.1%

Badge

PublicAI Index badge for Ox Alpha[![PublicAI Index](https://publicai.io/model-index/badge?model=ox-alpha)](https://publicai.io/model-index/m/ox-alpha)