Request a pilot
‹ PublicAI Index

The LLM benchmark aggregator.

OLMo 2 13B Instruct

Ai2 · 13B

Strongest in Safe-prompt compliance (#66 of 82), weakest in Safety (#329 of 336). Above par in 0 of 4 scopes. Among the models it meets almost everywhere, it finishes behind Claude 3.5 Sonnet and GPT-5 Nano and ahead of DBRX Instruct and Mistral Instruct v0.1 (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.

Safety38.4#329/336
Safe-prompt compliance46.6#66/82
Harm refusal34.9#296/299
Fairness33.7#297/299

§ 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 OLMo 2 13B Instruct, left for the other.

Mistral Instruct v0.1 (7B)won 3 · lost 1
DBRX Instructwon 3 · lost 1
OLMoE 1B-7B Instructwon 2 · lost 2
OLMo 2 7B Instructwon 2 · lost 2
OLMo 7B Instruct Hfwon 1 · lost 2
RakutenAI 7B Chatwon 1 · lost 2
SmolLM 1.7B Instructwon 1 · lost 2
PowerMoE 3Bwon 1 · lost 2
Qwen3 30B A3B Instructwon 1 · lost 2
GPT-3.5 Turbowon 1 · lost 3
DeepSeek LLM 67B Chatwon 1 · lost 3
Marin 8B Instructwon 1 · lost 3
IBM Granite 4.0 Micro (with guardian)won 1 · lost 3
IBM Granite 4.0 Microwon 1 · lost 3
IBM Granite 4.0 Small (with guardian)won 1 · lost 3
IBM Granite 3.3 8B Instructwon 1 · lost 3
Gemini 1.5 Prowon 1 · lost 3
GPT OSS 20Bwon 1 · lost 3
Gemini 1.5 Flashwon 1 · lost 3
Claude 3 Haikuwon 1 · lost 3
Claude 3 Sonnetwon 1 · lost 3
Claude 3 Opuswon 1 · lost 3
Phi 2won 0 · lost 3
Qwen2.5 7B Instructwon 0 · lost 3
Gemma 7B Itwon 0 · lost 3
H2o Danube3 500M Chatwon 0 · lost 3
PowerLM 3Bwon 0 · lost 3
Smollm2 1.7B Instructwon 0 · lost 3
Grok 4.1 Fastwon 0 · lost 3
LFM2 350Mwon 0 · lost 3
Laguna Xs 2.1won 0 · lost 3
RakutenAI 7B Instructwon 0 · lost 3
Falcon Mamba 7B Instructwon 0 · lost 3
GLM-4 9B Chatwon 0 · lost 3
Nous Hermes 2 Mixtral 8x7b Dpowon 0 · lost 3
SmolLM2 360M Instructwon 0 · lost 3
CodeLlama 7B Instruct Hfwon 0 · lost 3
Qwen2.5 0.5B Instructwon 0 · lost 3
Qwen2 7B Instructwon 0 · lost 3
Jamba Mini 1.7won 0 · lost 3
Gemma 2B Itwon 0 · lost 3
Magistral Smallwon 0 · lost 3
Aya 23 8Bwon 0 · lost 3
Laguna S 2.1won 0 · lost 3
Falcon H1 0.5B Instructwon 0 · lost 3
SEA LION V1 7B ITwon 0 · lost 3
Llama 3.1 8B Instructwon 0 · lost 3
Grok Build 0.1won 0 · lost 3
Qwen1.5 14B Chatwon 0 · lost 3
DeepSeek R1 Distill Qwen 7Bwon 0 · lost 3
DeepSeek R1 Distill Llama 8Bwon 0 · lost 3
H2o Danube3 4B Chatwon 0 · lost 3
Zephyr 7B Betawon 0 · lost 3
Ling 3.0 Flash VLwon 0 · lost 3
Mimo V2.6 Flashwon 0 · lost 3
Magistral Mediumwon 0 · lost 3
Gemini 3.6 Flashwon 0 · lost 3
Jamba 1.6 Miniwon 0 · lost 3
Command R7Bwon 0 · lost 3
LFM2 700Mwon 0 · lost 3
DeepSeek V4 Flashwon 0 · lost 3
Command Awon 0 · lost 3
Jamba Large 1.7won 0 · lost 3
SmolLM 360M Instructwon 0 · lost 3
NexusRaven V2 13Bwon 0 · lost 3
Ling 3.0 Flashwon 0 · lost 3
Qwen3 8Bwon 0 · lost 3
Open Mixtral 8x7bwon 0 · lost 3
Jamba 1.5 Largewon 0 · lost 3
Gemma 2 9B Itwon 0 · lost 3
GLM-5.2won 0 · lost 3
Gemini 3.5 Flashwon 0 · lost 3
Granite 3.2 8B Instructwon 0 · lost 3
Mistral 7B Instruct V0.2won 0 · lost 3
Nemotron 3 Ultra 550B A55Bwon 0 · lost 3
GLM-4.6won 0 · lost 3
Grok 4.3won 0 · lost 3
Phi-4 Mini Instructwon 0 · lost 3
Open Codestral Mambawon 0 · lost 3
Mimo V2.6 Pro Ultraspeedwon 0 · lost 3
Jamba 1.5 Miniwon 0 · lost 3
Qwen2.5 3B Instructwon 0 · lost 3
LFM2 1.2Bwon 0 · lost 3
Aya 23 35Bwon 0 · lost 3
NVIDIA Nemotron 3 Super 120B A12Bwon 0 · lost 3
MiniMax M3won 0 · lost 3
Granite 3.0 1B A400M Instructwon 0 · lost 3
DeepSeek V3p1won 0 · lost 3
Gemma 4 E2Bwon 0 · lost 3
QwQ 32Bwon 0 · lost 3
Jamba 1.6 Largewon 0 · lost 3
GLM-4.5won 0 · lost 3
Kimi K2.6won 0 · lost 3
Yi 1.5 9B Chatwon 0 · lost 3
Gemma 4 E4Bwon 0 · lost 3
Jamba Instructwon 0 · lost 3
Sarvam 1won 0 · lost 3
Qwen3.7 Maxwon 0 · lost 3
SeaLLMs V3 7B Chatwon 0 · lost 3
Qwen2.5 7B Instruct 1Mwon 0 · lost 3
Mistral Smallwon 0 · lost 3
Kimi K2.5won 0 · lost 3
DeepSeek Reasonerwon 0 · lost 3
Qwen2.5 1.5B Instructwon 0 · lost 3
Mistral Small 24B Instructwon 0 · lost 3
Komodo 7B Basewon 0 · lost 3
DeepSeek V3.2won 0 · lost 3
Granite 3.1 2B Instructwon 0 · lost 3
WizardLM 2.8x22Bwon 0 · lost 3
Llama 3.2 3B Instructwon 0 · lost 3
Gemma 2 2B Itwon 0 · lost 3
Kimi K2.7 Codewon 0 · lost 3
Gemma 4 12Bwon 0 · lost 3
Hunyuan A13B Instructwon 0 · lost 3
Granite 3.2 2B Instructwon 0 · lost 3
Fuguwon 0 · lost 3
Mimo V2.5 Prowon 0 · lost 3
Llama 3.3 Instruct Turbo (70B)won 0 · lost 3
Granite 3.0 3B A800M Instructwon 0 · lost 3
Gemma 3 4B Itwon 0 · lost 3
Gemma 4 31Bwon 0 · lost 3
Starling Lm 7B Betawon 0 · lost 3
Open Mixtral 8x22bwon 0 · lost 3
Dolphin 2.5 Mixtral 8x7bwon 0 · lost 3
Granite 3.0 2B Instructwon 0 · lost 3
Gemma2 9B Cpt Sea Lionv3 Instructwon 0 · lost 3
Reflection Llama 3.1 70Bwon 0 · lost 3
GLM-5.3 Flashwon 0 · lost 3
Apertus 8B Instructwon 0 · lost 3
Llama 3.2 1B Instructwon 0 · lost 3
Gemma 4 26B A4Bwon 0 · lost 3
DeepSeek Chatwon 0 · lost 3
DeepSeek V4 Prowon 0 · lost 3
Qwen2.5 32B Instructwon 0 · lost 3
LongWriter Glm4 9Bwon 0 · lost 3
Qwen2.5 14B Instruct 1Mwon 0 · lost 3
Qwen2 VL 72Bwon 0 · lost 3
GLM-5 Turbowon 0 · lost 3
Granite 3.1 3B A800M Instructwon 0 · lost 3
Phi 3 Medium 4k Instructwon 0 · lost 3
Granite 3.1 8B Instructwon 0 · lost 3
Sarvam 30Bwon 0 · lost 3
Qwen2.5 14B Instructwon 0 · lost 3
Qwen3 Vl 235B A22B Instructwon 0 · lost 3
Phi 3 Medium 128k Instructwon 0 · lost 3
Gemma 3 27B Itwon 0 · lost 3
Qwen2 57B A14B Instructwon 0 · lost 3
Smaug Llama 3 70B Instructwon 0 · lost 3
Llama 3 70B Chat HFwon 0 · lost 3
GPT-5.6 Astrawon 0 · lost 3
Phi 3 Small 128k Instructwon 0 · lost 3
Granite 3.0 8B Instructwon 0 · lost 3
Claude Opus 4.6won 0 · lost 3
Claude Sonnet 4.6won 0 · lost 3
Mimo V2.6 Prowon 0 · lost 3
Kimi K2 Thinkingwon 0 · lost 3
GPT OSS Safeguard 20Bwon 0 · lost 3
Gemini 3.8 Flashwon 0 · lost 3
EAI Llama 3.1 8B Instruct SageAlignwon 0 · lost 3
Gemma 3 12B Itwon 0 · lost 3
SeaLLM 7B V2won 0 · lost 3
Apertus 70B Instructwon 0 · lost 3
GPT-6 Solwon 0 · lost 3
Granite 4.0 H Microwon 0 · lost 3
Granite 4.0 H Tinywon 0 · lost 3
Phi 3 Small 8k Instructwon 0 · lost 3
Phi 3 Mini 128k Instructwon 0 · lost 3
Mistral Largewon 0 · lost 3
Phi 3.5 Mini Instructwon 0 · lost 3
K2 Chatwon 0 · lost 3
Llama 3.1 Tulu 3 8B SFTwon 0 · lost 3
Phi 3 Mini 4k Instructwon 0 · lost 3
Nova Prowon 0 · lost 3
GPT-5.6 Solwon 0 · lost 3
Qwen3.8 Maxwon 0 · lost 3
Llama 3.1 Tulu 3 8B DPOwon 0 · lost 3
Krutrim 2 Instructwon 0 · lost 3
GLM-5.1won 0 · lost 3
Llama 3.1 Tulu 3 8Bwon 0 · lost 3
Qwen3.5 35B A3Bwon 0 · lost 3
EAI SageAlign 8B LoRAwon 0 · lost 3
Qwen Maxwon 0 · lost 3
Qwen3.5 27Bwon 0 · lost 3
GPT-6 Lunawon 0 · lost 3
Qwen3.5 122B A10Bwon 0 · lost 3
GPT-4won 0 · lost 3
Phi 3.5 MoE Instructwon 0 · lost 3
Nova Microwon 0 · lost 3
Llama 3 8B Chat Hfwon 0 · lost 3
GPT-5.6 Lunawon 0 · lost 3
Nova Litewon 0 · lost 3
C4ai Aya Expanse 32Bwon 0 · lost 3
C4ai Aya Expanse 8Bwon 0 · lost 3
Llama 3.2 Vision (11B)won 0 · lost 3
Llama 3.1 Nemotron 70B Instruct HFwon 0 · lost 3
Titan Text Express V1won 0 · lost 3
Internlm2 Chat 20Bwon 0 · lost 3
Qwen2.5 72B Instructwon 0 · lost 3
Llama 2 70B Chat Hfwon 0 · lost 3
Llama 2 13B Chat Hfwon 0 · lost 3
Fugu Ultra V2won 0 · lost 3
Llama 3 8B Instruct RRwon 0 · lost 3
Nova Premierwon 0 · lost 3
Granite 4.0 H Smallwon 0 · lost 3
Llama 2 7B Chat Hfwon 0 · lost 3
Grok 4.5won 0 · lost 3
GPT-5.5won 0 · lost 3
Sarvam 105Bwon 0 · lost 3
GPT-5.4won 0 · lost 3
Llama 3 8B Instruct MopeyMulewon 0 · lost 3
Llama 3.2 90B Vision Instruct Turbowon 0 · lost 3
GPT-5.6 Terrawon 0 · lost 3
Cogito 671B V2 P1won 0 · lost 3
Claude Opus 4.7won 0 · lost 3
Foundation Sec 8B Instructwon 0 · lost 3
Gemma 2 27B Itwon 0 · lost 3
Qwen3.5 397B A17Bwon 0 · lost 3
Meta SecAlign 8Bwon 0 · lost 3
Apriel 1.5 15B Thinkerwon 0 · lost 3
Mistral NeMo Minitron 8B Instructwon 0 · lost 3
Claude Opus 5won 0 · lost 3
GPT-5.2won 0 · lost 3
Grok 4.6won 0 · lost 3
Phi 4won 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
MiniMax M2.7won 0 · lost 3
Claude Opus 5.5won 0 · lost 3
Claude Sonnet 5won 0 · lost 3
Mistral Instruct v0.3 (7B)won 0 · lost 4
Command Rwon 0 · lost 4
Mixtral (8x7B)won 0 · lost 4
Grok 4won 0 · lost 4
Grok 3won 0 · lost 4
DeepSeek R1won 0 · lost 4
Llama 3.1 Instruct Turbo (70B)won 0 · lost 4
Command R Pluswon 0 · lost 4
Mixtral Instruct (8x22B)won 0 · lost 4
DeepSeek V3won 0 · lost 4
Mistral Small 3won 0 · lost 4
Palmyra Medwon 0 · lost 4
Llama 4 Scout Instructwon 0 · lost 4
DeepSeek R1 (hide reasoning)won 0 · lost 4
Gemini 2.0 Flash Litewon 0 · lost 4
Llama 3.1 Instruct Turbo (8B)won 0 · lost 4
Olmo 2 32B Instructwon 0 · lost 4
Llama 3.1 Instruct Turbo (405B)won 0 · lost 4
Gemini 2.5 Prowon 0 · lost 4
Qwen1.5 72B Chatwon 0 · lost 4
Gemini 2.5 Flashwon 0 · lost 4
Gemini 3 Prowon 0 · lost 4
Llama 3 8B Instructwon 0 · lost 4
Qwen 2.5 Instruct Turbo (7B)won 0 · lost 4
Gemini 2.0 Flashwon 0 · lost 4
Gemini 2.0 Prowon 0 · lost 4
IBM Granite 4.0 Smallwon 0 · lost 4
Kimi K2won 0 · lost 4
Llama 4 Maverick Instructwon 0 · lost 4
Llama 3 70B Instructwon 0 · lost 4
Qwen3 235B A22B Throughputwon 0 · lost 4
GLM-4.5 Airwon 0 · lost 4
Grok 3 Miniwon 0 · lost 4
GPT-4.1 Nanowon 0 · lost 4
GPT-4o Miniwon 0 · lost 4
Palmyra X5won 0 · lost 4
GPT-4.1 Miniwon 0 · lost 4
O4 Miniwon 0 · lost 4
Palmyra Xwon 0 · lost 4
Qwen3 235B A22B Instructwon 0 · lost 4
GPT OSS 120Bwon 0 · lost 4
Palmyra Finwon 0 · lost 4
Gemini 2.5 Flash Litewon 0 · lost 4
Qwen3 Next 80B A3B Thinkingwon 0 · lost 4
GPT-4.5won 0 · lost 4
Claude 3.7 Sonnetwon 0 · lost 4
GPT-4owon 0 · lost 4
Qwen2 72B Instructwon 0 · lost 4
O3 Miniwon 0 · lost 4
Claude Haiku 4.5won 0 · lost 4
GPT-4.1won 0 · lost 4
Claude Opus 4won 0 · lost 4
Qwen 2.5 Instruct Turbo (72B)won 0 · lost 4
Claude Sonnet 4.5won 0 · lost 4
O1 Miniwon 0 · lost 4
Claude Sonnet 4won 0 · lost 4
GPT-4 Turbowon 0 · lost 4
GPT-5.1won 0 · lost 4
O3won 0 · lost 4
O1won 0 · lost 4
GPT-5 Miniwon 0 · lost 4
GPT-5won 0 · lost 4
GPT-5 Nanowon 0 · lost 4
Claude 3.5 Sonnetwon 0 · lost 4

§ 3 · Sources

Where the numbers come from

1 publication, 5 figures. Every one links to the page it was read from.

HELM Safety ↗5 measuresread 2026-09-27
HELM Safety · HarmBench 51.9%HELM Safety · SimpleSafetyTests 81%HELM Safety · Anthropic Red Team 90.7%HELM Safety · BBQ 70.4%HELM Safety · XSTest 92.6%

Badge

PublicAI Index badge for OLMo 2 13B Instruct[![PublicAI Index](https://publicai.io/model-index/badge?model=olmo-2-13b-instruct)](https://publicai.io/model-index/m/olmo-2-13b-instruct)