Request a Pilot
‹ PublicAI Index

The LLM benchmark aggregator.

Gemma 2B IT

Google · 2B

Strongest in Harm refusal (#61 of 292, on 1 of its 2 boards), weakest in Human preference (#339 of 354). Above par in 2 of 8 scopes. Among the models it meets almost everywhere, it finishes behind Claude Opus 5.5 and Claude Opus 4.7 and ahead of Command R and Qwen2 7B Instruct.

§ 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.

Safety43.7#292/329
Harm refusal55.6#61/292
Jailbreak resistance51.8#159/268
Toxicity avoidance26#259/268
Secure code26#269/270
Fairness38.3#276/292
Human preference27.3#339/354
Human preference27.3#339/354

§ 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 Gemma 2B IT, left for the other.

OLMoE 1B-7B Instructwon 5 · lost 1
SmolLM 1.7B Instructwon 5 · lost 1
OLMo 7B Instructwon 6 · lost 2
RakutenAI 7B Chatwon 4 · lost 2
PowerMoE 3Bwon 4 · lost 2
Phi 2won 4 · lost 2
PowerLM 3Bwon 4 · lost 2
Qwen2.5 0.5B Instructwon 4 · lost 2
Qwen2 7B Instructwon 4 · lost 2
Command Rwon 3 · lost 2
Mistral Instruct v0.1 (7B)won 3 · lost 3
H2o Danube3 500M Chatwon 3 · lost 3
Laguna Xs 2.1won 3 · lost 3
LFM2 350Mwon 3 · lost 3
RakutenAI 7B Instructwon 3 · lost 3
Falcon Mamba 7B Instructwon 3 · lost 3
GLM-4 9B Chatwon 3 · lost 3
SmolLM2 360M Instructwon 3 · lost 3
CodeLlama 7B Instructwon 3 · lost 3
Magistral Smallwon 3 · lost 3
Jamba Mini 1.7won 3 · lost 3
OLMo 2 7B Instructwon 3 · lost 3
Command R7Bwon 3 · lost 3
Qwen3 8Bwon 3 · lost 3
Gemma 4 E2Bwon 3 · lost 3
OLMo 2 32B Instructwon 2 · lost 3
SmolLM2 1.7B Instructwon 3 · lost 5
Gemma 7B ITwon 3 · lost 5
DBRX Instructwon 3 · lost 5
Qwen3 30B A3B Instructwon 3 · lost 5
Grok 3won 3 · lost 5
Grok 4won 3 · lost 5
Grok 4.1 Fastwon 3 · lost 5
Mistral Instruct v0.3 (7B)won 2 · lost 4
Magistral Small 1.2won 2 · lost 4
Laguna S 2.1won 2 · lost 4
Falcon H1 0.5B Instructwon 2 · lost 4
SEA LION V1 7B ITwon 2 · lost 4
Grok Build 0.1won 2 · lost 4
Ling 3.0 Flash VLwon 2 · lost 4
LFM2 700Mwon 2 · lost 4
Jamba Large 1.7won 2 · lost 4
SmolLM 360M Instructwon 2 · lost 4
Ling 3.0 Flashwon 2 · lost 4
Mimo V2.6 Pro Ultraspeedwon 2 · lost 4
Phi-4 Mini Instructwon 2 · lost 4
Qwen2.5 3B Instructwon 2 · lost 4
LFM2 1.2Bwon 2 · lost 4
Sarvam 1won 2 · lost 4
Gemma 4 E4Bwon 2 · lost 4
Qwen2.5 7B Instruct 1Mwon 2 · lost 4
Kimi K2.7 Codewon 2 · lost 4
Gemma 4 12Bwon 2 · lost 4
Fuguwon 2 · lost 4
Apertus 8B Instructwon 2 · lost 4
Qwen2.5 14B Instruct 1Mwon 2 · lost 4
GLM-5 Turbowon 2 · lost 4
Qwen 2.5 Instruct (7B)won 2 · lost 4
Sarvam 30Bwon 2 · lost 4
GPT-5.6 Astrawon 2 · lost 4
GPT OSS Safeguard 20Bwon 2 · lost 4
Kimi K2 Thinkingwon 2 · lost 4
Nova Premierwon 2 · lost 4
Command Awon 2 · lost 5
Zephyr 7B Betawon 2 · lost 6
Nous Hermes 2 Mixtral 8x7B DPOwon 2 · lost 6
Starling LM 7B Betawon 2 · lost 6
DeepSeek LLM 67B Chatwon 2 · lost 6
Qwen1.5 14B Chatwon 2 · lost 6
Mixtral 8x7B Instructwon 2 · lost 6
Gemma 2 2B ITwon 2 · lost 6
GPT-3.5 Turbowon 2 · lost 6
Jamba 1.5 Miniwon 2 · lost 6
Magistral Mediumwon 2 · lost 6
Mercury 2won 2 · lost 6
Gemini 2.0 Flash-Litewon 2 · lost 6
NVIDIA Nemotron 3 Super 120B A12Bwon 2 · lost 6
Qwen3.5 35B A3Bwon 2 · lost 6
DeepSeek V3won 2 · lost 6
Qwen3.5 27Bwon 2 · lost 6
Gemini 2.5 Flashwon 2 · lost 6
GLM-4.5won 2 · lost 6
Qwen3 VL 235B A22B Instructwon 2 · lost 6
DeepSeek V3.1won 2 · lost 6
Qwen3.5 122B A10Bwon 2 · lost 6
DeepSeek R1won 2 · lost 6
Qwen3 235B A22B Instructwon 2 · lost 6
Mistral Large 4won 2 · lost 6
DeepSeek V3.2won 2 · lost 6
GLM-4.6won 2 · lost 6
NVIDIA Nemotron 3 Ultra 550B A55Bwon 2 · lost 6
MiniMax M3won 2 · lost 6
Gemma 4 26B A4Bwon 2 · lost 6
DeepSeek V4 Flashwon 2 · lost 6
GPT-6 Lunawon 2 · lost 6
Qwen3.5 397B A17Bwon 2 · lost 6
Grok 4.3won 2 · lost 6
Gemini 2.5 Prowon 2 · lost 6
MiMo V2.6 Flashwon 2 · lost 6
Kimi K2.5won 2 · lost 6
Gemma 4 31Bwon 2 · lost 6
GPT-6 Solwon 2 · lost 6
Kimi K2.6won 2 · lost 6
GLM-5.1won 2 · lost 6
MiMo V2.5 Prowon 2 · lost 6
Qwen3.7 Maxwon 2 · lost 6
GLM-5.3 Flashwon 2 · lost 6
GLM-5.2won 2 · lost 6
Gemini 3.5 Flashwon 2 · lost 6
Gemini 3.6 Flashwon 2 · lost 6
Claude Opus 5won 2 · lost 6
Gemini 3.8 Flashwon 2 · lost 6
Qwen1.5 72B Chatwon 1 · lost 4
Grok 3 Miniwon 1 · lost 4
Qwen3 Next 80B A3B Thinkingwon 1 · lost 4
GLM-4.5 Airwon 1 · lost 4
Gemini 2.5 Flash-Litewon 1 · lost 4
Gemini 3 Prowon 1 · lost 4
Aya 23 8Bwon 1 · lost 5
DeepSeek R1 Distill Qwen 7Bwon 1 · lost 5
DeepSeek R1 Distill Llama 8Bwon 1 · lost 5
H2o Danube3 4B Chatwon 1 · lost 5
Jamba 1.6 Miniwon 1 · lost 5
NexusRaven V2 13Bwon 1 · lost 5
Granite 3.2 8B Instructwon 1 · lost 5
Open Codestral Mambawon 1 · lost 5
Aya 23 35Bwon 1 · lost 5
Granite 3.0 1B A400M Instructwon 1 · lost 5
Jamba 1.6 Largewon 1 · lost 5
Jamba Instructwon 1 · lost 5
Yi 1.5 9B Chatwon 1 · lost 5
SeaLLMs V3 7B Chatwon 1 · lost 5
DeepSeek Reasonerwon 1 · lost 5
Qwen2.5 1.5B Instructwon 1 · lost 5
Komodo 7B Basewon 1 · lost 5
WizardLM 2.8x22Bwon 1 · lost 5
IBM Granite 4.0 Microwon 1 · lost 5
Hunyuan A13B Instructwon 1 · lost 5
Granite 3.2 2B Instructwon 1 · lost 5
Granite 3.0 3B A800M Instructwon 1 · lost 5
Dolphin 2.5 Mixtral 8x7bwon 1 · lost 5
Gemma2 9B Cpt Sea Lionv3 Instructwon 1 · lost 5
Reflection Llama 3.1 70Bwon 1 · lost 5
DeepSeek Chatwon 1 · lost 5
Qwen2.5 32B Instructwon 1 · lost 5
LongWriter Glm4 9Bwon 1 · lost 5
Qwen2 VL 72Bwon 1 · lost 5
Granite 3.1 3B A800M Instructwon 1 · lost 5
Qwen2.5 14B Instructwon 1 · lost 5
Phi 3 Medium 128k Instructwon 1 · lost 5
Qwen2 57B A14B Instructwon 1 · lost 5
Smaug Llama 3 70B Instructwon 1 · lost 5
Phi 3 Small 128k Instructwon 1 · lost 5
SeaLLM 7B V2won 1 · lost 5
Apertus 70B Instructwon 1 · lost 5
Granite 4.0 H Microwon 1 · lost 5
Phi 3.5 Mini Instructwon 1 · lost 5
K2 Chatwon 1 · lost 5
Llama 3.1 Tulu 3 8B SFTwon 1 · lost 5
Phi 3.5 MoE Instructwon 1 · lost 5
Internlm2 Chat 20Bwon 1 · lost 5
Fugu Ultra V2won 1 · lost 5
Llama 3.2 Vision (90B)won 1 · lost 5
Mistral NeMo Minitron 8B Instructwon 1 · lost 5
Phi-3 Mini 128K Instructwon 1 · lost 7
Phi-3 Mini 4K Instructwon 1 · lost 7
Mistral 7B Instruct v0.2won 1 · lost 7
Granite 3.0 2B Instructwon 1 · lost 7
Llama 3.2 3B Instructwon 1 · lost 7
Llama 2 70B Chatwon 1 · lost 7
Phi-3 Small 8K Instructwon 1 · lost 7
Granite 3.1 2B Instructwon 1 · lost 7
Granite 3.0 8B Instructwon 1 · lost 7
Phi-3 Medium 4K Instructwon 1 · lost 7
Granite 3.1 8B Instructwon 1 · lost 7
Llama 3.1 8B Instructwon 1 · lost 7
Aya Expanse 8Bwon 1 · lost 7
Llama 3 8B Instructwon 1 · lost 7
Mixtral 8x22B Instructwon 1 · lost 7
Amazon Nova Microwon 1 · lost 7
Claude 3 Haikuwon 1 · lost 7
Qwen2 72B Instructwon 1 · lost 7
Gemma 2 9B ITwon 1 · lost 7
Aya Expanse 32Bwon 1 · lost 7
Mistral Small 3 24B Instructwon 1 · lost 7
GPT-4won 1 · lost 7
Command R+won 1 · lost 7
Llama 3 70B Instructwon 1 · lost 7
Granite 4.0 H Smallwon 1 · lost 7
Gemma 2 27B ITwon 1 · lost 7
Jamba 1.5 Largewon 1 · lost 7
Llama 3.1 70B Instructwon 1 · lost 7
Llama 3.1 Nemotron 70B Instructwon 1 · lost 7
Qwen2.5 72B Instructwon 1 · lost 7
Gemma 3 4B ITwon 1 · lost 7
Gemini 1.5 Flashwon 1 · lost 7
GPT-4o miniwon 1 · lost 7
Llama 3.3 70B Instructwon 1 · lost 7
Qwen Maxwon 1 · lost 7
GPT OSS 20Bwon 1 · lost 7
Llama 4 Scout Instructwon 1 · lost 7
GPT-4.1 nanowon 1 · lost 7
Llama 4 Maverick Instructwon 1 · lost 7
Llama 3.1 405B Instructwon 1 · lost 7
QwQ 32Bwon 1 · lost 7
GPT-4owon 1 · lost 7
Gemma 3 12B ITwon 1 · lost 7
MiniMax M2won 1 · lost 7
Gemini 1.5 Prowon 1 · lost 7
GPT OSS 120Bwon 1 · lost 7
Gemini 2.0 Flashwon 1 · lost 7
Gemma 3 27B ITwon 1 · lost 7
GPT-4.1 miniwon 1 · lost 7
Claude Sonnet 4won 1 · lost 7
Kimi K2won 1 · lost 7
Grok 4.7won 1 · lost 7
GPT-5.6 Lunawon 1 · lost 7
Grok 4.6won 1 · lost 7
DeepSeek V4 Prowon 1 · lost 7
Grok 4.5won 1 · lost 7
GPT-5.6 Terrawon 1 · lost 7
MiMo V2.6 Prowon 1 · lost 7
GPT-5.5won 1 · lost 7
Qwen3.8 Maxwon 1 · lost 7
GPT-5.6 Solwon 1 · lost 7
GPT-4.5won 0 · lost 5
EAI Llama 3.1 8B Instruct SageAlignwon 0 · lost 6
Granite 4.0 H Tinywon 0 · lost 6
Llama 3.1 Tulu 3 8B DPOwon 0 · lost 6
Krutrim 2 Instructwon 0 · lost 6
EAI SageAlign 8B LoRAwon 0 · lost 6
Llama 3.2 Vision (11B)won 0 · lost 6
Titan Text Express V1won 0 · lost 6
Llama 3 8B Instruct RRwon 0 · lost 6
Sarvam 105Bwon 0 · lost 6
Llama 3 8B Instruct MopeyMulewon 0 · lost 6
Cogito 671B V2 P1won 0 · lost 6
Foundation Sec 8B Instructwon 0 · lost 6
Meta SecAlign 8Bwon 0 · lost 6
Apriel 1.5 15B Thinkerwon 0 · lost 6
Claude Sonnet 4.6won 0 · lost 6
Claude Opus 4.6won 0 · lost 6
Llama 3.2 1B Instructwon 0 · lost 7
Llama 2 7B Chatwon 0 · lost 8
Llama 2 13B Chatwon 0 · lost 8
Llama 3.1 Tulu 3 8Bwon 0 · lost 8
Phi 4won 0 · lost 8
Amazon Nova Litewon 0 · lost 8
Claude 3 Sonnetwon 0 · lost 8
Amazon Nova Prowon 0 · lost 8
Claude 3 Opuswon 0 · lost 8
Claude 3.5 Haikuwon 0 · lost 8
GPT-4 Turbowon 0 · lost 8
O1 Miniwon 0 · lost 8
GPT-5 nanowon 0 · lost 8
O3 Miniwon 0 · lost 8
Claude 3.5 Sonnetwon 0 · lost 8
Claude 3.7 Sonnetwon 0 · lost 8
GPT-5 miniwon 0 · lost 8
O4 Miniwon 0 · lost 8
O1won 0 · lost 8
Claude Haiku 4.5won 0 · lost 8
GPT-4.1won 0 · lost 8
MiniMax M2.7won 0 · lost 8
Claude Opus 4won 0 · lost 8
O3won 0 · lost 8
GPT-5won 0 · lost 8
GPT-5.2won 0 · lost 8
Inklingwon 0 · lost 8
Hy3won 0 · lost 8
GPT-5.1won 0 · lost 8
Claude Sonnet 4.5won 0 · lost 8
Claude Sonnet 5won 0 · lost 8
GPT-5.4won 0 · lost 8
Claude Opus 4.8won 0 · lost 8
Muse Spark 1.1won 0 · lost 8
Claude Opus 4.7won 0 · lost 8
Claude Opus 5.5won 0 · lost 8

§ 3 · Sources

Where the numbers come from

2 publications, 7 figures. Every one links to the page it was read from.

LMArena Text ↗1 measureread 2026-11-10
LMArena Text 1094
Enkrypt AI Safety Leaderboard ↗6 measuresread 2026-11-10
Enkrypt · Jailbreak risk 11.3%Enkrypt · Harmful content risk 22.8%Enkrypt · CBRN risk 5.7%Enkrypt · Toxicity risk 29.6%Enkrypt · Bias risk 95.9%Enkrypt · Insecure code risk 95.6%

Badge

PublicAI Index badge for Gemma 2B IT[![PublicAI Index](https://publicai.io/model-index/badge?model=gemma-2b-it)](https://publicai.io/model-index/m/gemma-2b-it)