Request a pilot
‹ PublicAI Index

The LLM benchmark aggregator.

H2o Danube3 4B Chat

H2O.ai · 4B

Strongest in Jailbreak resistance (#82 of 272), weakest in Safety (#285 of 336). Above par in 2 of 6 scopes. Among the models it meets almost everywhere, it finishes behind Claude Sonnet 5 and Claude Opus 5.5 and ahead of SmolLM 360M Instruct and DeepSeek R1 Distill Qwen 7B.

§ 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.

Safety45.1#285/336
Jailbreak resistance57.2#82/272
Toxicity avoidance50.6#196/272
Harm refusal47.1#206/299
Secure code26.2#258/274
Fairness40.2#277/299

§ 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 H2o Danube3 4B Chat, left for the other.

SmolLM 1.7B Instructwon 6 · lost 0
Smollm2 1.7B Instructwon 6 · lost 0
OLMoE 1B-7B Instructwon 5 · lost 1
Mistral Instruct v0.1 (7B)won 5 · lost 1
OLMo 7B Instruct Hfwon 5 · lost 1
H2o Danube3 500M Chatwon 5 · lost 1
Nous Hermes 2 Mixtral 8x7b Dpowon 5 · lost 1
SmolLM2 360M Instructwon 5 · lost 1
CodeLlama 7B Instruct Hfwon 5 · lost 1
Qwen2.5 0.5B Instructwon 5 · lost 1
Gemma 2B Itwon 5 · lost 1
GPT-3.5 Turbowon 5 · lost 1
RakutenAI 7B Chatwon 4 · lost 2
DBRX Instructwon 4 · lost 2
PowerMoE 3Bwon 4 · lost 2
Phi 2won 4 · lost 2
Qwen2.5 7B Instructwon 4 · lost 2
Gemma 7B Itwon 4 · lost 2
PowerLM 3Bwon 4 · lost 2
Grok 4.1 Fastwon 4 · lost 2
LFM2 350Mwon 4 · lost 2
RakutenAI 7B Instructwon 4 · lost 2
Falcon Mamba 7B Instructwon 4 · lost 2
GLM-4 9B Chatwon 4 · lost 2
Jamba Mini 1.7won 4 · lost 2
Grok 3won 4 · lost 2
Magistral Smallwon 4 · lost 2
Aya 23 8Bwon 4 · lost 2
Falcon H1 0.5B Instructwon 4 · lost 2
Grok Build 0.1won 4 · lost 2
DeepSeek R1 Distill Qwen 7Bwon 4 · lost 2
SmolLM 360M Instructwon 4 · lost 2
Qwen3 30B A3B Instructwon 3 · lost 3
Laguna Xs 2.1won 3 · lost 3
Mistral Instruct v0.3 (7B)won 3 · lost 3
Qwen2 7B Instructwon 3 · lost 3
OLMo 2 7B Instructwon 3 · lost 3
Grok 4won 3 · lost 3
Laguna S 2.1won 3 · lost 3
SEA LION V1 7B ITwon 3 · lost 3
Llama 3.1 8B Instructwon 3 · lost 3
Qwen1.5 14B Chatwon 3 · lost 3
DeepSeek R1 Distill Llama 8Bwon 3 · lost 3
Zephyr 7B Betawon 3 · lost 3
Magistral Mediumwon 3 · lost 3
Llama 3.1 Instruct Turbo (70B)won 3 · lost 3
Jamba 1.6 Miniwon 3 · lost 3
Command R7Bwon 3 · lost 3
DeepSeek V4 Flashwon 3 · lost 3
Command R Pluswon 3 · lost 3
Command Awon 3 · lost 3
Jamba Large 1.7won 3 · lost 3
Qwen3 8Bwon 3 · lost 3
DeepSeek LLM 67B Chatwon 3 · lost 3
Open Codestral Mambawon 3 · lost 3
Jamba 1.5 Miniwon 3 · lost 3
DeepSeek V3won 3 · lost 3
DeepSeek V3p1won 3 · lost 3
Gemma 4 E4Bwon 3 · lost 3
Sarvam 1won 3 · lost 3
Komodo 7B Basewon 3 · lost 3
Mistral Largewon 3 · lost 3
DeepSeek R1won 2 · lost 4
Ling 3.0 Flash VLwon 2 · lost 4
Mimo V2.6 Flashwon 2 · lost 4
Gemini 3.6 Flashwon 2 · lost 4
LFM2 700Mwon 2 · lost 4
NexusRaven V2 13Bwon 2 · lost 4
Ling 3.0 Flashwon 2 · lost 4
Open Mixtral 8x7bwon 2 · lost 4
Jamba 1.5 Largewon 2 · lost 4
Gemma 2 9B Itwon 2 · lost 4
GLM-5.2won 2 · lost 4
Gemini 3.5 Flashwon 2 · lost 4
Mistral 7B Instruct V0.2won 2 · lost 4
Nemotron 3 Ultra 550B A55Bwon 2 · lost 4
GLM-4.6won 2 · lost 4
Grok 4.3won 2 · lost 4
Mimo V2.6 Pro Ultraspeedwon 2 · lost 4
Qwen2.5 3B Instructwon 2 · lost 4
LFM2 1.2Bwon 2 · lost 4
Aya 23 35Bwon 2 · lost 4
NVIDIA Nemotron 3 Super 120B A12Bwon 2 · lost 4
MiniMax M3won 2 · lost 4
Granite 3.0 1B A400M Instructwon 2 · lost 4
Gemma 4 E2Bwon 2 · lost 4
QwQ 32Bwon 2 · lost 4
Jamba 1.6 Largewon 2 · lost 4
GLM-4.5won 2 · lost 4
Kimi K2.6won 2 · lost 4
Yi 1.5 9B Chatwon 2 · lost 4
Jamba Instructwon 2 · lost 4
Qwen3.7 Maxwon 2 · lost 4
SeaLLMs V3 7B Chatwon 2 · lost 4
Mistral Smallwon 2 · lost 4
DeepSeek Reasonerwon 2 · lost 4
DeepSeek V3.2won 2 · lost 4
Gemma 2 2B Itwon 2 · lost 4
Kimi K2.7 Codewon 2 · lost 4
Hunyuan A13B Instructwon 2 · lost 4
Fuguwon 2 · lost 4
Mimo V2.5 Prowon 2 · lost 4
Llama 3.3 Instruct Turbo (70B)won 2 · lost 4
Gemini 2.0 Flash Litewon 2 · lost 4
Dolphin 2.5 Mixtral 8x7bwon 2 · lost 4
Gemini 2.5 Prowon 2 · lost 4
GLM-5.3 Flashwon 2 · lost 4
GPT OSS 20Bwon 2 · lost 4
DeepSeek Chatwon 2 · lost 4
DeepSeek V4 Prowon 2 · lost 4
LongWriter Glm4 9Bwon 2 · lost 4
Gemini 2.5 Flashwon 2 · lost 4
Gemini 1.5 Flashwon 2 · lost 4
Sarvam 30Bwon 2 · lost 4
Kimi K2won 2 · lost 4
GPT-6 Solwon 2 · lost 4
GPT-5.6 Solwon 2 · lost 4
GPT-6 Lunawon 2 · lost 4
GPT-5.6 Lunawon 2 · lost 4
GPT OSS 120Bwon 2 · lost 4
GPT-5.5won 2 · lost 4
GPT-5.6 Terrawon 2 · lost 4
Granite 3.2 8B Instructwon 1 · lost 5
Phi-4 Mini Instructwon 1 · lost 5
Qwen2.5 7B Instruct 1Mwon 1 · lost 5
Kimi K2.5won 1 · lost 5
Qwen2.5 1.5B Instructwon 1 · lost 5
Mistral Small 24B Instructwon 1 · lost 5
Granite 3.1 2B Instructwon 1 · lost 5
Llama 4 Scout Instructwon 1 · lost 5
Llama 3.2 3B Instructwon 1 · lost 5
Gemma 4 12Bwon 1 · lost 5
Granite 3.2 2B Instructwon 1 · lost 5
Granite 3.0 3B A800M Instructwon 1 · lost 5
Gemma 3 4B Itwon 1 · lost 5
Llama 3.1 Instruct Turbo (8B)won 1 · lost 5
Gemma 4 31Bwon 1 · lost 5
Starling Lm 7B Betawon 1 · lost 5
Open Mixtral 8x22bwon 1 · lost 5
Granite 3.0 2B Instructwon 1 · lost 5
Gemini 1.5 Prowon 1 · lost 5
Gemma2 9B Cpt Sea Lionv3 Instructwon 1 · lost 5
Reflection Llama 3.1 70Bwon 1 · lost 5
Apertus 8B Instructwon 1 · lost 5
Llama 3.2 1B Instructwon 1 · lost 5
Gemma 4 26B A4Bwon 1 · lost 5
Qwen2.5 32B Instructwon 1 · lost 5
Qwen2.5 14B Instruct 1Mwon 1 · lost 5
Qwen2 VL 72Bwon 1 · lost 5
GLM-5 Turbowon 1 · lost 5
Llama 3 8B Instructwon 1 · lost 5
Qwen 2.5 Instruct Turbo (7B)won 1 · lost 5
Claude 3 Haikuwon 1 · lost 5
Qwen2.5 14B Instructwon 1 · lost 5
Qwen3 Vl 235B A22B Instructwon 1 · lost 5
Gemini 2.0 Flashwon 1 · lost 5
Phi 3 Medium 128k Instructwon 1 · lost 5
Gemma 3 27B Itwon 1 · lost 5
Qwen2 57B A14B Instructwon 1 · lost 5
GPT-5.6 Astrawon 1 · lost 5
Phi 3 Small 128k Instructwon 1 · lost 5
Kimi K2 Thinkingwon 1 · lost 5
GPT OSS Safeguard 20Bwon 1 · lost 5
Gemini 3.8 Flashwon 1 · lost 5
EAI Llama 3.1 8B Instruct SageAlignwon 1 · lost 5
Gemma 3 12B Itwon 1 · lost 5
SeaLLM 7B V2won 1 · lost 5
Apertus 70B Instructwon 1 · lost 5
Granite 4.0 H Microwon 1 · lost 5
Granite 4.0 H Tinywon 1 · lost 5
Phi 3 Small 8k Instructwon 1 · lost 5
K2 Chatwon 1 · lost 5
GPT-4.1 Nanowon 1 · lost 5
Nova Prowon 1 · lost 5
Qwen3.8 Maxwon 1 · lost 5
GLM-5.1won 1 · lost 5
Qwen3.5 35B A3Bwon 1 · lost 5
EAI SageAlign 8B LoRAwon 1 · lost 5
GPT-4.1 Miniwon 1 · lost 5
Qwen3.5 27Bwon 1 · lost 5
Qwen3.5 122B A10Bwon 1 · lost 5
GPT-4won 1 · lost 5
O4 Miniwon 1 · lost 5
Phi 3.5 MoE Instructwon 1 · lost 5
Nova Microwon 1 · lost 5
Nova Litewon 1 · lost 5
Qwen3 235B A22B Instructwon 1 · lost 5
Fugu Ultra V2won 1 · lost 5
Nova Premierwon 1 · lost 5
Granite 4.0 H Smallwon 1 · lost 5
Grok 4.5won 1 · lost 5
GPT-4.1won 1 · lost 5
Cogito 671B V2 P1won 1 · lost 5
Qwen 2.5 Instruct Turbo (72B)won 1 · lost 5
Qwen3.5 397B A17Bwon 1 · lost 5
GPT-5.1won 1 · lost 5
Claude Opus 5won 1 · lost 5
Grok 4.6won 1 · lost 5
Claude Opus 4.6won 0 · lost 4
Claude Sonnet 4.6won 0 · lost 4
WizardLM 2.8x22Bwon 0 · lost 6
IBM Granite 4.0 Microwon 0 · lost 6
Llama 3.1 Instruct Turbo (405B)won 0 · lost 6
Granite 3.1 3B A800M Instructwon 0 · lost 6
Phi 3 Medium 4k Instructwon 0 · lost 6
Granite 3.1 8B Instructwon 0 · lost 6
Smaug Llama 3 70B Instructwon 0 · lost 6
Llama 3 70B Chat HFwon 0 · lost 6
Granite 3.0 8B Instructwon 0 · lost 6
Mimo V2.6 Prowon 0 · lost 6
Llama 4 Maverick Instructwon 0 · lost 6
Llama 3 70B Instructwon 0 · lost 6
Phi 3 Mini 128k Instructwon 0 · lost 6
Phi 3.5 Mini Instructwon 0 · lost 6
Llama 3.1 Tulu 3 8B SFTwon 0 · lost 6
Phi 3 Mini 4k Instructwon 0 · lost 6
GPT-4o Miniwon 0 · lost 6
Llama 3.1 Tulu 3 8B DPOwon 0 · lost 6
Krutrim 2 Instructwon 0 · lost 6
Llama 3.1 Tulu 3 8Bwon 0 · lost 6
Qwen Maxwon 0 · lost 6
Llama 3 8B Chat Hfwon 0 · lost 6
C4ai Aya Expanse 32Bwon 0 · lost 6
C4ai Aya Expanse 8Bwon 0 · lost 6
Llama 3.2 Vision (11B)won 0 · lost 6
Llama 3.1 Nemotron 70B Instruct HFwon 0 · lost 6
Titan Text Express V1won 0 · lost 6
Internlm2 Chat 20Bwon 0 · lost 6
Qwen2.5 72B Instructwon 0 · lost 6
Llama 2 70B Chat Hfwon 0 · lost 6
Llama 2 13B Chat Hfwon 0 · lost 6
Llama 3 8B Instruct RRwon 0 · lost 6
Llama 2 7B Chat Hfwon 0 · lost 6
Claude 3.7 Sonnetwon 0 · lost 6
Sarvam 105Bwon 0 · lost 6
GPT-4owon 0 · lost 6
GPT-5.4won 0 · lost 6
Qwen2 72B Instructwon 0 · lost 6
O3 Miniwon 0 · lost 6
Claude Haiku 4.5won 0 · lost 6
Claude 3 Sonnetwon 0 · lost 6
Llama 3 8B Instruct MopeyMulewon 0 · lost 6
Llama 3.2 90B Vision Instruct Turbowon 0 · lost 6
Claude Opus 4won 0 · lost 6
Claude Opus 4.7won 0 · lost 6
Claude Sonnet 4.5won 0 · lost 6
Foundation Sec 8B Instructwon 0 · lost 6
Gemma 2 27B Itwon 0 · lost 6
O1 Miniwon 0 · lost 6
Claude Sonnet 4won 0 · lost 6
Meta SecAlign 8Bwon 0 · lost 6
Apriel 1.5 15B Thinkerwon 0 · lost 6
GPT-4 Turbowon 0 · lost 6
Mistral NeMo Minitron 8B Instructwon 0 · lost 6
O3won 0 · lost 6
GPT-5.2won 0 · lost 6
O1won 0 · lost 6
Phi 4won 0 · lost 6
GPT-5 Miniwon 0 · lost 6
MiniMax M2won 0 · lost 6
Claude 3.5 Haikuwon 0 · lost 6
GPT-5won 0 · lost 6
GPT-5 Nanowon 0 · lost 6
Claude 3 Opuswon 0 · lost 6
Muse Spark 1.1won 0 · lost 6
Claude Opus 4.8won 0 · lost 6
Inklingwon 0 · lost 6
Grok 4.7won 0 · lost 6
Claude 3.5 Sonnetwon 0 · lost 6
Hy3won 0 · lost 6
MiniMax M2.7won 0 · lost 6
Claude Opus 5.5won 0 · lost 6
Claude Sonnet 5won 0 · lost 6

§ 3 · Sources

Where the numbers come from

1 publication, 6 figures. Every one links to the page it was read from.

Enkrypt AI Safety Leaderboard ↗6 measuresread 2026-09-27
Enkrypt · Jailbreak risk 6.7%Enkrypt · Harmful content risk 56.1%Enkrypt · CBRN risk 10.3%Enkrypt · Toxicity risk 5.9%Enkrypt · Bias risk 93%Enkrypt · Insecure code risk 81.8%

Badge

PublicAI Index badge for H2o Danube3 4B Chat[![PublicAI Index](https://publicai.io/model-index/badge?model=h2o-danube3-4b-chat)](https://publicai.io/model-index/m/h2o-danube3-4b-chat)