The LLM benchmark aggregator.

IBM Granite 3.3 8B Instruct

IBM · 8B

Strongest in Factual grounding (#65 of 104), weakest in Safety (#190 of 327). Above par in 1 of 5 scopes. Among the models it meets almost everywhere, it finishes behind GPT-5 nano and Claude Sonnet 4 and ahead of Command R+ and DeepSeek R1.

§ 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.

Safety49.6−11.8#190/3272/3

Factual grounding48.3−22.4#65/1041/1

Safe-prompt compliance42.4−18#70/821/1

Harm refusal53.4−8.1#99/2901/2

Fairness45.7−24.3#175/2901/2

§ 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 IBM Granite 3.3 8B Instruct, left for the other.

SmolLM 1.7B Instructwon 3 · lost 0

H2o Danube3 500M Chatwon 3 · lost 0

SmolLM2 1.7B Instructwon 3 · lost 0

Qwen3 30B A3B Instructwon 3 · lost 0

Laguna Xs 2.1won 3 · lost 0

RakutenAI 7B Instructwon 3 · lost 0

Falcon Mamba 7B Instructwon 3 · lost 0

Nous Hermes 2 Mixtral 8x7B DPOwon 3 · lost 0

CodeLlama 7B Instructwon 3 · lost 0

Qwen2.5 0.5B Instructwon 3 · lost 0

Magistral Smallwon 3 · lost 0

Aya 23 8Bwon 3 · lost 0

Laguna S 2.1won 3 · lost 0

Grok Build 0.1won 3 · lost 0

DeepSeek R1 Distill Qwen 7Bwon 3 · lost 0

DeepSeek R1 Distill Llama 8Bwon 3 · lost 0

H2o Danube3 4B Chatwon 3 · lost 0

Ling 3.0 Flash VLwon 3 · lost 0

MiMo V2.6 Flashwon 3 · lost 0

Jamba 1.6 Miniwon 3 · lost 0

Command R7Bwon 3 · lost 0

DeepSeek V4 Flashwon 3 · lost 0

Ling 3.0 Flashwon 3 · lost 0

Jamba 1.5 Largewon 3 · lost 0

GLM-5.2won 3 · lost 0

Granite 3.2 8B Instructwon 3 · lost 0

Mistral 7B Instruct v0.2won 3 · lost 0

NVIDIA Nemotron 3 Ultra 550B A55Bwon 3 · lost 0

Grok 4.3won 3 · lost 0

Jamba 1.5 Miniwon 3 · lost 0

Qwen2.5 3B Instructwon 3 · lost 0

NVIDIA Nemotron 3 Super 120B A12Bwon 3 · lost 0

Granite 3.0 1B A400M Instructwon 3 · lost 0

QwQ 32Bwon 3 · lost 0

Gemma 4 E2Bwon 3 · lost 0

Jamba Instructwon 3 · lost 0

Yi 1.5 9B Chatwon 3 · lost 0

Gemma 4 E4Bwon 3 · lost 0

Qwen2.5 7B Instruct 1Mwon 3 · lost 0

SeaLLMs V3 7B Chatwon 3 · lost 0

Qwen2.5 1.5B Instructwon 3 · lost 0

WizardLM 2.8x22Bwon 3 · lost 0

Granite 3.1 2B Instructwon 3 · lost 0

Gemma 4 12Bwon 3 · lost 0

Granite 3.2 2B Instructwon 3 · lost 0

OLMoE 1B-7B Instructwon 4 · lost 0

DBRX Instructwon 4 · lost 0

Grok 4.1 Fastwon 4 · lost 0

OLMo 2 7B Instructwon 4 · lost 0

DeepSeek LLM 67B Chatwon 4 · lost 0

Phi-4 Mini Instructwon 4 · lost 0

IBM Granite 4.0 Microwon 4 · lost 0

Mistral Instruct v0.1 (7B)won 3 · lost 1

OLMo 2 13B Instructwon 3 · lost 1

Command Rwon 3 · lost 1

Jamba Mini 1.7won 3 · lost 1

Mixtral 8x7B Instructwon 3 · lost 1

GPT-3.5 Turbowon 3 · lost 1

Command Awon 3 · lost 1

Qwen3 8Bwon 3 · lost 1

Marin 8B Instructwon 3 · lost 1

IBM Granite 4.0 Micro (with guardian)won 3 · lost 1

GLM-4.6won 3 · lost 1

Kimi K2.6won 3 · lost 1

Palmyra Medwon 3 · lost 1

Kimi K2.5won 3 · lost 1

Llama 3.3 70B Instructwon 3 · lost 1

OLMo 7B Instructwon 2 · lost 1

RakutenAI 7B Chatwon 2 · lost 1

PowerMoE 3Bwon 2 · lost 1

Phi 2won 2 · lost 1

Gemma 7B ITwon 2 · lost 1

PowerLM 3Bwon 2 · lost 1

LFM2 350Mwon 2 · lost 1

GLM-4 9B Chatwon 2 · lost 1

SmolLM2 360M Instructwon 2 · lost 1

Qwen2 7B Instructwon 2 · lost 1

Gemma 2B ITwon 2 · lost 1

Magistral Small 1.2won 2 · lost 1

Falcon H1 0.5B Instructwon 2 · lost 1

SEA LION V1 7B ITwon 2 · lost 1

Qwen1.5 14B Chatwon 2 · lost 1

Zephyr 7B Betawon 2 · lost 1

Magistral Mediumwon 2 · lost 1

Gemini 3.6 Flashwon 2 · lost 1

LFM2 700Mwon 2 · lost 1

NexusRaven V2 13Bwon 2 · lost 1

SmolLM 360M Instructwon 2 · lost 1

Gemini 3.5 Flashwon 2 · lost 1

Mimo V2.6 Pro Ultraspeedwon 2 · lost 1

Open Codestral Mambawon 2 · lost 1

Aya 23 35Bwon 2 · lost 1

LFM2 1.2Bwon 2 · lost 1

MiniMax M3won 2 · lost 1

Jamba 1.6 Largewon 2 · lost 1

Qwen3.7 Maxwon 2 · lost 1

GLM-4.5won 2 · lost 1

Sarvam 1won 2 · lost 1

Gemma 2 2B ITwon 2 · lost 1

Llama 3.2 3B Instructwon 2 · lost 1

Kimi K2.7 Codewon 2 · lost 1

Hunyuan A13B Instructwon 2 · lost 1

Fuguwon 2 · lost 1

MiMo V2.5 Prowon 2 · lost 1

Mistral Large 4won 2 · lost 1

Granite 3.0 3B A800M Instructwon 2 · lost 1

Granite 3.0 2B Instructwon 2 · lost 1

Gemma2 9B Cpt Sea Lionv3 Instructwon 2 · lost 1

Qwen2.5 32B Instructwon 2 · lost 1

Qwen2 VL 72Bwon 2 · lost 1

GLM-5 Turbowon 2 · lost 1

Phi-3 Medium 4K Instructwon 2 · lost 1

Granite 3.1 8B Instructwon 2 · lost 1

Qwen2.5 14B Instructwon 2 · lost 1

Phi 3 Medium 128k Instructwon 2 · lost 1

Phi 3 Small 128k Instructwon 2 · lost 1

Granite 3.0 8B Instructwon 2 · lost 1

SeaLLM 7B V2won 2 · lost 1

Phi-3 Small 8K Instructwon 2 · lost 1

Phi-3 Mini 128K Instructwon 2 · lost 1

Phi 3.5 MoE Instructwon 2 · lost 1

DeepSeek R1won 3 · lost 2

Command R+won 3 · lost 2

Mistral Instruct v0.3 (7B)won 2 · lost 2

Grok 4won 2 · lost 2

Llama 3.1 70B Instructwon 2 · lost 2

Jamba Large 1.7won 2 · lost 2

Mixtral 8x22B Instructwon 2 · lost 2

DeepSeek V3.2won 2 · lost 2

DeepSeek R1 (hide reasoning)won 2 · lost 2

DeepSeek V3.1won 2 · lost 2

Gemini 2.0 Flash-Litewon 2 · lost 2

Llama 3.1 8B Instructwon 2 · lost 2

Gemma 4 31Bwon 2 · lost 2

Mercury 2won 2 · lost 2

DeepSeek V4 Prowon 2 · lost 2

Gemma 4 26B A4Bwon 2 · lost 2

Claude 3 Haikuwon 2 · lost 2

Gemma 3 12B ITwon 2 · lost 2

Qwen3.5 27Bwon 2 · lost 2

Qwen3.5 122B A10Bwon 2 · lost 2

Aya Expanse 32Bwon 2 · lost 2

Grok 3won 2 · lost 3

DeepSeek V3won 2 · lost 3

Mistral Small 3 24B Instructwon 2 · lost 3

Llama 4 Scout Instructwon 2 · lost 3

Gemini 3 Prowon 2 · lost 3

Gemma 2 9B ITwon 1 · lost 2

Komodo 7B Basewon 1 · lost 2

Starling LM 7B Betawon 1 · lost 2

Dolphin 2.5 Mixtral 8x7bwon 1 · lost 2

Reflection Llama 3.1 70Bwon 1 · lost 2

GLM-5.3 Flashwon 1 · lost 2

Apertus 8B Instructwon 1 · lost 2

Llama 3.2 1B Instructwon 1 · lost 2

LongWriter Glm4 9Bwon 1 · lost 2

Qwen2.5 14B Instruct 1Mwon 1 · lost 2

Granite 3.1 3B A800M Instructwon 1 · lost 2

Sarvam 30Bwon 1 · lost 2

Qwen3 VL 235B A22B Instructwon 1 · lost 2

Qwen2 57B A14B Instructwon 1 · lost 2

Smaug Llama 3 70B Instructwon 1 · lost 2

GPT-5.6 Astrawon 1 · lost 2

MiMo V2.6 Prowon 1 · lost 2

GPT OSS Safeguard 20Bwon 1 · lost 2

Kimi K2 Thinkingwon 1 · lost 2

Gemini 3.8 Flashwon 1 · lost 2

Granite 4.0 H Microwon 1 · lost 2

Granite 4.0 H Tinywon 1 · lost 2

Phi 3.5 Mini Instructwon 1 · lost 2

K2 Chatwon 1 · lost 2

Llama 3.1 Tulu 3 8B SFTwon 1 · lost 2

Phi-3 Mini 4K Instructwon 1 · lost 2

Llama 3.1 Tulu 3 8B DPOwon 1 · lost 2

Krutrim 2 Instructwon 1 · lost 2

Qwen3.8 Maxwon 1 · lost 2

Llama 3.1 Tulu 3 8Bwon 1 · lost 2

GLM-5.1won 1 · lost 2

Qwen Maxwon 1 · lost 2

GPT-6 Lunawon 1 · lost 2

GPT-4won 1 · lost 2

Llama 3.2 Vision (11B)won 1 · lost 2

Titan Text Express V1won 1 · lost 2

Llama 3.1 Nemotron 70B Instructwon 1 · lost 2

Llama 2 13B Chatwon 1 · lost 2

Llama 2 70B Chatwon 1 · lost 2

Fugu Ultra V2won 1 · lost 2

Grok 4.5won 1 · lost 2

Sarvam 105Bwon 1 · lost 2

Gemma 2 27B ITwon 1 · lost 2

Qwen3.5 397B A17Bwon 1 · lost 2

Mistral NeMo Minitron 8B Instructwon 1 · lost 2

Claude Opus 5won 1 · lost 2

Grok 4.6won 1 · lost 2

IBM Granite 4.0 Small (with guardian)won 1 · lost 3

Gemma 3 4B ITwon 1 · lost 3

OLMo 2 32B Instructwon 1 · lost 3

Gemini 1.5 Prowon 1 · lost 3

Llama 3.1 405B Instructwon 1 · lost 3

GPT OSS 20Bwon 1 · lost 3

Qwen1.5 72B Chatwon 1 · lost 3

Gemini 1.5 Flashwon 1 · lost 3

Qwen 2.5 Instruct (7B)won 1 · lost 3

Gemini 2.0 Flashwon 1 · lost 3

Gemma 3 27B ITwon 1 · lost 3

Gemini 2.0 Prowon 1 · lost 3

IBM Granite 4.0 Smallwon 1 · lost 3

Claude Opus 4.6won 1 · lost 3

Llama 3 8B Instructwon 1 · lost 3

GPT-6 Solwon 1 · lost 3

Llama 3 70B Instructwon 1 · lost 3

Qwen3 235B A22B Throughputwon 1 · lost 3

Grok 3 Miniwon 1 · lost 3

GPT-4.1 nanowon 1 · lost 3

Amazon Nova Prowon 1 · lost 3

GPT-4o miniwon 1 · lost 3

GPT-5.6 Solwon 1 · lost 3

Palmyra X5won 1 · lost 3

Qwen3.5 35B A3Bwon 1 · lost 3

Amazon Nova Microwon 1 · lost 3

Amazon Nova Litewon 1 · lost 3

Aya Expanse 8Bwon 1 · lost 3

Palmyra Xwon 1 · lost 3

GPT-5.4won 1 · lost 3

Claude 3 Sonnetwon 1 · lost 3

Claude Opus 4.7won 1 · lost 3

GPT-5.2won 1 · lost 3

MiniMax M2.7won 1 · lost 3

Gemini 2.5 Prowon 1 · lost 4

Gemini 2.5 Flashwon 1 · lost 4

Kimi K2won 1 · lost 4

Llama 4 Maverick Instructwon 1 · lost 4

GLM-4.5 Airwon 1 · lost 4

O4 Miniwon 1 · lost 4

GPT OSS 120Bwon 1 · lost 4

Gemini 2.5 Flash-Litewon 1 · lost 4

Claude Opus 4won 1 · lost 4

Claude Sonnet 4.5won 1 · lost 4

GPT-5.1won 1 · lost 4

GPT-5 miniwon 1 · lost 4

GPT-5won 1 · lost 4

Claude Sonnet 4.6won 0 · lost 3

EAI Llama 3.1 8B Instruct SageAlignwon 0 · lost 3

Apertus 70B Instructwon 0 · lost 3

EAI SageAlign 8B LoRAwon 0 · lost 3

GPT-5.6 Lunawon 0 · lost 3

Internlm2 Chat 20Bwon 0 · lost 3

Llama 3 8B Instruct RRwon 0 · lost 3

Nova Premierwon 0 · lost 3

Llama 2 7B Chatwon 0 · lost 3

Llama 3 8B Instruct MopeyMulewon 0 · lost 3

Llama 3.2 Vision (90B)won 0 · lost 3

GPT-5.6 Terrawon 0 · lost 3

Cogito 671B V2 P1won 0 · lost 3

Foundation Sec 8B Instructwon 0 · lost 3

Meta SecAlign 8Bwon 0 · lost 3

Apriel 1.5 15B Thinkerwon 0 · lost 3

MiniMax M2won 0 · lost 3

Claude 3.5 Haikuwon 0 · lost 3

Muse Spark 1.1won 0 · lost 3

Claude Opus 4.8won 0 · lost 3

Inklingwon 0 · lost 3

Grok 4.7won 0 · lost 3

Hy3won 0 · lost 3

Claude Sonnet 5won 0 · lost 3

GPT-4.1 miniwon 0 · lost 4

Palmyra Finwon 0 · lost 4

GPT-4.5won 0 · lost 4

Granite 4.0 H Smallwon 0 · lost 4

GPT-5.5won 0 · lost 4

Claude 3.7 Sonnetwon 0 · lost 4

O3 Miniwon 0 · lost 4

Qwen2 72B Instructwon 0 · lost 4

Qwen2.5 72B Instructwon 0 · lost 4

O1 Miniwon 0 · lost 4

GPT-4 Turbowon 0 · lost 4

O3won 0 · lost 4

O1won 0 · lost 4

Phi 4won 0 · lost 4

Claude Opus 5.5won 0 · lost 4

Claude 3 Opuswon 0 · lost 4

Claude 3.5 Sonnetwon 0 · lost 4

Qwen3 235B A22B Instructwon 0 · lost 5

Qwen3 Next 80B A3B Thinkingwon 0 · lost 5

GPT-4owon 0 · lost 5

Claude Haiku 4.5won 0 · lost 5

GPT-4.1won 0 · lost 5

Claude Sonnet 4won 0 · lost 5

GPT-5 nanowon 0 · lost 5

§ 3 · Sources

Where the numbers come from

2 publications, 6 figures. Every one links to the page it was read from.

HELM Safety ↗5 measuresread 2026-11-11

HELM Safety · HarmBench 81.2%HELM Safety · SimpleSafetyTests 97.5%HELM Safety · Anthropic Red Team 99.1%HELM Safety · BBQ 84%HELM Safety · XSTest 90.7%

Vectara Hallucination Leaderboard ↗1 measureread 2026-11-11

Vectara · Factual consistency 89.4%

Badge

[![PublicAI Index](https://publicai.io/model-index/badge?model=ibm-granite-3-3-8b-instruct)](https://publicai.io/model-index/m/ibm-granite-3-3-8b-instruct)