Request a pilot
‹ PublicAI Index

The LLM benchmark aggregator.

Claude 4 Haiku

Anthropic

Strongest in General intelligence (#41 of 214, on 1 of its 3 boards), weakest in Core abilities (#43 of 225). Above par in 2 of 2 scopes. Among the models it meets almost everywhere, it finishes behind Claude Fable 5 and GPT-6 Astra and ahead of Grok 4.6 and Qwen3.8 2.4T A95B.

§ 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 abilities55.6#43/225
General intelligence58.1#41/214

§ 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 Claude 4 Haiku, left for the other.

NVIDIA-Nemotron-3.5-Lightning-30B-A3B (NVFP4)won 2 · lost 0
Claude Haiku 4.5won 2 · lost 0
Magistral Smallwon 2 · lost 0
AFM 4.5Bwon 2 · lost 0
Jamba Mini 1.7won 2 · lost 0
Magistral Mediumwon 2 · lost 0
Phi 4 Multimodal Instructwon 2 · lost 0
Spotlightwon 2 · lost 0
Mercury Coderwon 2 · lost 0
UI-TARS 1.5 7Bwon 2 · lost 0
Gemma 4 31Bwon 2 · lost 0
Mercurywon 2 · lost 0
Llama 4 Scout Instructwon 2 · lost 0
K2 Horizon 0.9Bwon 2 · lost 0
GPT-5.4 miniwon 2 · lost 0
Gemma 3 4B ITwon 2 · lost 0
Jamba Large 1.7won 2 · lost 0
NVIDIA-Nemotron-3-Ultra-550B-A55B (NVFP4)won 2 · lost 0
Nemotron 3 Nano 4Bwon 2 · lost 0
Ministral 3 3Bwon 2 · lost 0
Ministral 3 8Bwon 2 · lost 0
GPT-5.4 nanowon 2 · lost 0
Ministral 3 14Bwon 2 · lost 0
Celeris 1won 2 · lost 0
Valkyrie 49B V1won 2 · lost 0
GPT-4o miniwon 2 · lost 0
Command A (03-2025)won 2 · lost 0
Mistral Small 4won 2 · lost 0
Gemma 3n E4B ITwon 2 · lost 0
Nemotron 3 Nanowon 2 · lost 0
Qwen3 Coder Nextwon 2 · lost 0
Gemma 4 E4Bwon 2 · lost 0
Granite 4.2 3Bwon 2 · lost 0
Virtuoso Largewon 2 · lost 0
Codestralwon 2 · lost 0
North Mini Codewon 2 · lost 0
GPT-4.1 nanowon 2 · lost 0
Nemotron 3.5 Super VLwon 2 · lost 0
Mistral Medium 3.5won 2 · lost 0
Ling 3.0 Tinywon 2 · lost 0
Qwen3.5 9Bwon 2 · lost 0
Granite 4.2 8Bwon 2 · lost 0
Trinity Largewon 2 · lost 0
Claude 3 Haikuwon 2 · lost 0
Kimi K2.7 Codewon 2 · lost 0
Llama 3 70B Instructwon 2 · lost 0
Gemma 3 27B ITwon 2 · lost 0
Mistral Large 4won 2 · lost 0
MiniCPM5 2Bwon 2 · lost 0
Mercury 2.5won 2 · lost 0
Qwen2.5 Vl 72B Instructwon 2 · lost 0
Command A+won 2 · lost 0
Granite 4.2 30Bwon 2 · lost 0
Devstral Smallwon 2 · lost 0
Devstral Mediumwon 2 · lost 0
Mistral Smallwon 2 · lost 0
Phi 4 Reasoning Pluswon 2 · lost 0
Gemini 2.0 Flashwon 2 · lost 0
GPT OSS 20Bwon 2 · lost 0
MiniMax M3won 2 · lost 0
Anubis 70B V1.1won 2 · lost 0
K2 Horizon 3.7Bwon 2 · lost 0
Qwen3.5 122B A10Bwon 2 · lost 0
Llama 4 Maverick Instructwon 2 · lost 0
Mistral Small 3.2won 2 · lost 0
Gemma 3 27B It Fastwon 2 · lost 0
Gemini 2.5 Flash-Litewon 2 · lost 0
Beam 1.0won 2 · lost 0
Ring 2.6.1Twon 2 · lost 0
Muse Glimmerwon 2 · lost 0
Muse Spark Openwon 2 · lost 0
Gemini 3.5 Flash-Litewon 2 · lost 0
GPT-5.6 Lunawon 2 · lost 0
GLM-4 32Bwon 2 · lost 0
Qwen3.6 35B A3Bwon 2 · lost 0
MiniMax 01won 2 · lost 0
GLM-4.5 Airwon 2 · lost 0
GPT-6 Lunawon 2 · lost 0
LongCat 2.0won 2 · lost 0
LongCat Flash Chatwon 2 · lost 0
Inklingwon 2 · lost 0
GPT OSS 120Bwon 2 · lost 0
Nova Premierwon 2 · lost 0
Ernie 4.5 300B A47Bwon 2 · lost 0
Llama 3 405Bwon 2 · lost 0
GLM-4.6won 2 · lost 0
K2 Horizon 7Bwon 2 · lost 0
A.X K2won 2 · lost 0
Nemotron 3.5 Bolt 74B-A9Bwon 2 · lost 0
GLM-5.2won 2 · lost 0
Claude Sonnet 5won 2 · lost 0
Claude Sonnet 4.6won 2 · lost 0
GLM-4.6:exactowon 2 · lost 0
Nemotron Nano 9B V2won 2 · lost 0
Ling 3.0 Flash Finwon 2 · lost 0
GPT-4.1 miniwon 2 · lost 0
Qwen3 32Bwon 2 · lost 0
Qwen3 14Bwon 2 · lost 0
GLM-5.3 Flashwon 2 · lost 0
Qwen 3 Coderwon 2 · lost 0
Solar Mini 4won 2 · lost 0
DeepSeek V4 Flashwon 2 · lost 0
Mistral Mediumwon 2 · lost 0
Ling 3.0 Flash VLwon 2 · lost 0
K2 Horizon MoVA 36B A4Bwon 2 · lost 0
Hy3won 2 · lost 0
Qwen3.7 Pluswon 2 · lost 0
Mistral Large 3won 2 · lost 0
Step 5won 2 · lost 0
Nemotron Nano 12B V2 Vlwon 2 · lost 0
Apodex 1.1won 2 · lost 0
Inkling Smallwon 2 · lost 0
GPT-5.5 Instantwon 2 · lost 0
Kimi K2won 2 · lost 0
DeepSeek V3.2won 2 · lost 0
Cogito V2 Llama 4 Scoutwon 2 · lost 0
DeepSeek V3won 2 · lost 0
GPT-4.1won 2 · lost 0
DeepSeek R1 Distill Llama 70Bwon 2 · lost 0
Grok Code Fast 1won 2 · lost 0
Quasar 438Bwon 2 · lost 0
Solar Pro 4won 2 · lost 0
DeepSeek V3.1won 2 · lost 0
Qwen3 Next 80B A3B Instructwon 2 · lost 0
Qwen3 30B A3B Thinkingwon 2 · lost 0
Qwen3 32B Fastwon 2 · lost 0
Qwen3 235B A22B Instructwon 2 · lost 0
MiniMax M2.5won 2 · lost 0
Hermes 4 405Bwon 2 · lost 0
Qwen3.8 Flashwon 2 · lost 0
Gemini 2.5 Flashwon 2 · lost 0
DeepSeek V3.1 Terminuswon 2 · lost 0
Ling 1twon 2 · lost 0
MiniMax M2won 2 · lost 0
K2 Horizon 375B A23Bwon 2 · lost 0
GLM-4.5won 2 · lost 0
Claude Sonnet 4.5 (High, 32K, 20250929)won 2 · lost 0
Cogito V2 DeepSeek 671Bwon 2 · lost 0
Qwen3.8 27Bwon 2 · lost 0
GLM-5.3won 2 · lost 0
GLM-4.5Vwon 2 · lost 0
Qwen3.5 397B A17Bwon 2 · lost 0
Cogito V2 Llama 405Bwon 2 · lost 0
DeepSeek-V4-Pro (High, 20260813)won 2 · lost 0
Grok 3won 2 · lost 0
Grok 3 Miniwon 2 · lost 0
JT-4.1 Flash 236B A21Bwon 2 · lost 0
Muse Spark 1.2won 2 · lost 0
GPT-5 nanowon 2 · lost 0
Step 3won 2 · lost 0
Qwen Pluswon 2 · lost 0
Kimi K2 Thinkingwon 2 · lost 0
DeepSeek V4 Flash Visionwon 2 · lost 0
Maestro Reasoningwon 2 · lost 0
GPT-5.6 Terrawon 2 · lost 0
Grok 4 Fastwon 2 · lost 0
MiMo V2.6 Flashwon 2 · lost 0
Ring 1twon 2 · lost 0
Qwen3 Next 80B A3B Thinkingwon 2 · lost 0
GPT-5.4won 2 · lost 0
Gemini 3.8 Flashwon 2 · lost 0
Gemini 3.1 Flash-Litewon 2 · lost 0
O4 Miniwon 2 · lost 0
O3won 2 · lost 0
Qwen3.8 2.4T A95Bwon 2 · lost 0
Grok 4.6won 2 · lost 0
Claude Haiku 5.5won 1 · lost 1
GPT-5.2won 1 · lost 1
Claude Opus 4.5 (High, 32K, 20251101)won 1 · lost 1
Claude Opus 4.7won 1 · lost 1
MiniMax M3.1 Flashwon 1 · lost 1
Claude Opus 5won 1 · lost 1
Claude Opus 4.6won 1 · lost 1
Gemini 3.7 Flashwon 1 · lost 1
Gemini 3.1 Prowon 1 · lost 1
Qwen3.8 Flash Nextwon 1 · lost 1
Qwen3.8 Maxwon 1 · lost 1
Kimi K3won 1 · lost 1
GPT-5.6 Solwon 1 · lost 1
Muse Spark 1.3won 1 · lost 1
DeepSeek R1won 0 · lost 2
Qwen3 235B A22B Thinkingwon 0 · lost 2
Claude Sonnet 5.5won 0 · lost 2
Ling 3.1 Flashwon 0 · lost 2
MiMo V2.6 Prowon 0 · lost 2
GPT-5 miniwon 0 · lost 2
Gemini 2.5 Prowon 0 · lost 2
GPT-5 Codexwon 0 · lost 2
Claude Opus 4.8won 0 · lost 2
O3 Prowon 0 · lost 2
Qwen3 Maxwon 0 · lost 2
GPT-5won 0 · lost 2
Claude Sonnet 4won 0 · lost 2
Grok 4.5won 0 · lost 2
Grok 4won 0 · lost 2
Claude Opus 4won 0 · lost 2
GPT-6 Solwon 0 · lost 2
Grok 4.20 (Reasoning, 0309)won 0 · lost 2
GLM-5won 0 · lost 2
DeepSeek V4.1 Flashwon 0 · lost 2
Grok 4.7won 0 · lost 2
GPT-5 Prowon 0 · lost 2
Kimi K2.5won 0 · lost 2
Gemini 3 Prowon 0 · lost 2
GPT-5.5won 0 · lost 2
Claude Opus 5.5won 0 · lost 2
Muse Wonderwon 0 · lost 2
Muse Wonder Fullwon 0 · lost 2
Claude Fable 5.1won 0 · lost 2
Gemini 4 Argonwon 0 · lost 2
GPT-6.1 Solwon 0 · lost 2
GPT-6 Astrawon 0 · lost 2
Claude Fable 5won 0 · lost 2

§ 3 · Sources

Where the numbers come from

1 publication, 1 figures. Every one links to the page it was read from.

Kagi LLM Benchmark ↗1 measureread 2026-10-21
Kagi LLM Benchmark 69%

Badge

PublicAI Index badge for Claude 4 Haiku[![PublicAI Index](https://publicai.io/model-index/badge?model=claude-4-haiku)](https://publicai.io/model-index/m/claude-4-haiku)