Request a pilot
‹ PublicAI Index

The LLM benchmark aggregator.

Llama 3.1 8B Instruct

Meta · 8B · open weights

Strongest in Tool use (#62 of 81), weakest in Safety (#291 of 337). Above par in 1 of 11 scopes. Among the models it meets almost everywhere, it finishes behind GPT-5.6 Terra and Claude Sonnet 5 and ahead of Grok 3 and GPT-3.5 Turbo.

§ 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.

Agents37.8#256/268
Tool use41.3#62/81
Knowledge work30.8#172/178
Human preference38.8#272/342
Human preference38.8#272/342
Safety44.7#291/337
Harm refusal50.8#144/300
Fairness47.5#150/300
Secure code41.6#208/274
Jailbreak resistance35.1#235/272
Toxicity avoidance36.3#247/272

§ 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 Llama 3.1 8B Instruct, left for the other.

Smollm2 1.7B Instructwon 7 · lost 1
Gemma 7B Itwon 7 · lost 1
Gemma 2B Itwon 6 · lost 2
Nous Hermes 2 Mixtral 8x7b Dpowon 6 · lost 2
Mistral 7B Instruct V0.2won 5 · lost 3
Granite 3.1 2B Instructwon 5 · lost 3
DBRX Instructwon 5 · lost 3
GPT-3.5 Turbowon 5 · lost 3
Grok 3won 5 · lost 3
Phi-4 Mini Instructwon 4 · lost 4
Zephyr 7B Betawon 4 · lost 4
Granite 3.0 2B Instructwon 4 · lost 4
DeepSeek LLM 67B Chatwon 4 · lost 4
Qwen1.5 14B Chatwon 4 · lost 4
Llama 3.2 1B Instructwon 5 · lost 5
Llama 3.2 3B Instructwon 5 · lost 5
Granite 3.1 8B Instructwon 4 · lost 6
Qwen3 30B A3B Instructwon 4 · lost 6
Grok 4.1 Fastwon 4 · lost 6
Granite 3.2 8B Instructwon 3 · lost 5
Ling 3.0 Flashwon 3 · lost 5
Nemotron 3 Ultra 550B A55Bwon 3 · lost 5
Grok Build 0.1won 3 · lost 5
Ling 3.0 Flash VLwon 3 · lost 5
Phi 3 Mini 128k Instructwon 3 · lost 5
Phi 3 Mini 4k Instructwon 3 · lost 5
Phi 3 Small 8k Instructwon 3 · lost 5
Starling Lm 7B Betawon 3 · lost 5
Granite 3.0 8B Instructwon 3 · lost 5
Phi 3 Medium 4k Instructwon 3 · lost 5
Gemma 2 2B Itwon 3 · lost 5
Gemma 2 9B Itwon 3 · lost 5
Command R Pluswon 3 · lost 5
Jamba 1.5 Largewon 3 · lost 5
Mimo V2.6 Flashwon 3 · lost 5
Gemma 4 E4Bwon 3 · lost 6
Qwen3 8Bwon 3 · lost 6
Nova Prowon 3 · lost 7
Gemma 3 4B Itwon 3 · lost 7
Mistral Smallwon 3 · lost 7
NVIDIA Nemotron 3 Super 120B A12Bwon 3 · lost 7
DeepSeek V3won 3 · lost 7
Grok 4won 3 · lost 7
DeepSeek R1won 3 · lost 7
Gemini 3.6 Flashwon 3 · lost 7
Llama 4 Scout Instructwon 3 · lost 8
Gemma 3 12B Itwon 3 · lost 8
Gemma 3 27B Itwon 3 · lost 8
GLM-5.2won 3 · lost 8
Gemma 4 E2Bwon 2 · lost 6
Gemma 4 12Bwon 2 · lost 6
Command R7Bwon 2 · lost 6
Kimi K2.7 Codewon 2 · lost 6
Jamba 1.5 Miniwon 2 · lost 6
Mistral Small 24B Instructwon 2 · lost 6
Magistral Mediumwon 2 · lost 6
QwQ 32Bwon 2 · lost 6
Nova Microwon 2 · lost 8
GPT OSS 20Bwon 2 · lost 8
Command Awon 2 · lost 8
Gemini 2.5 Flashwon 2 · lost 8
Gemma 4 26B A4Bwon 2 · lost 8
DeepSeek V4 Flashwon 2 · lost 8
Grok 4.3won 2 · lost 8
Gemini 2.5 Prowon 2 · lost 8
Kimi K2.5won 2 · lost 8
Kimi K2.6won 2 · lost 8
Qwen3.7 Maxwon 2 · lost 8
Gemini 3.5 Flashwon 2 · lost 8
GLM-4.6won 2 · lost 9
MiniMax M3won 2 · lost 9
Gemma 4 31Bwon 2 · lost 9
Gemini 2.5 Flash Litewon 1 · lost 6
Gemini 3 Prowon 1 · lost 6
Llama 3.1 Tulu 3 8Bwon 1 · lost 7
C4ai Aya Expanse 8Bwon 1 · lost 7
Llama 3 8B Instructwon 1 · lost 7
Nova Litewon 1 · lost 7
Claude 3 Haikuwon 1 · lost 7
C4ai Aya Expanse 32Bwon 1 · lost 7
Qwen Maxwon 1 · lost 7
Gemini 1.5 Prowon 1 · lost 7
GLM-4.5won 1 · lost 7
Qwen3 Vl 235B A22B Instructwon 1 · lost 7
Claude 3.7 Sonnetwon 1 · lost 8
Phi 4won 1 · lost 9
GPT-4won 1 · lost 9
Mistral Largewon 1 · lost 9
GPT-4o Miniwon 1 · lost 9
Claude 3.5 Haikuwon 1 · lost 9
Qwen3.5 122B A10Bwon 1 · lost 9
GPT-6 Lunawon 1 · lost 9
GPT-6 Solwon 1 · lost 9
DeepSeek V4 Prowon 1 · lost 9
Mimo V2.5 Prowon 1 · lost 9
GLM-5.3 Flashwon 1 · lost 9
GPT-5.4won 1 · lost 9
Mimo V2.6 Prowon 1 · lost 9
Gemini 3.8 Flashwon 1 · lost 9
GPT-4.1 Nanowon 1 · lost 10
DeepSeek V3.2won 1 · lost 10
Qwen3 Next 80B A3B Thinkingwon 0 · lost 7
Qwen2 72B Instructwon 0 · lost 8
Llama 3 70B Instructwon 0 · lost 8
Claude 3 Sonnetwon 0 · lost 8
Gemma 2 27B Itwon 0 · lost 8
Qwen2.5 72B Instructwon 0 · lost 8
Gemini 1.5 Flashwon 0 · lost 8
Claude 3 Opuswon 0 · lost 8
GPT-4 Turbowon 0 · lost 8
GPT-4owon 0 · lost 8
O1 Miniwon 0 · lost 8
MiniMax M2won 0 · lost 8
Gemini 2.0 Flash Litewon 0 · lost 8
Gemini 2.0 Flashwon 0 · lost 8
Claude 3.5 Sonnetwon 0 · lost 8
O1won 0 · lost 8
Qwen3.5 27Bwon 0 · lost 8
Claude Opus 4won 0 · lost 8
Claude Sonnet 4.6won 0 · lost 8
GPT-5 Nanowon 0 · lost 10
GPT OSS 120Bwon 0 · lost 10
O3 Miniwon 0 · lost 10
O4 Miniwon 0 · lost 10
Qwen3.5 35B A3Bwon 0 · lost 10
Claude Sonnet 4won 0 · lost 10
GPT-4.1won 0 · lost 10
MiniMax M2.7won 0 · lost 10
Kimi K2won 0 · lost 10
Qwen3 235B A22B Instructwon 0 · lost 10
O3won 0 · lost 10
GPT-5won 0 · lost 10
GPT-5.2won 0 · lost 10
Grok 4.7won 0 · lost 10
Qwen3.5 397B A17Bwon 0 · lost 10
Grok 4.6won 0 · lost 10
GPT-5.1won 0 · lost 10
Hy3won 0 · lost 10
GLM-5.1won 0 · lost 10
Grok 4.5won 0 · lost 10
Qwen3.8 Maxwon 0 · lost 10
Claude Opus 4.8won 0 · lost 10
GPT-5.5won 0 · lost 10
GPT-5.6 Solwon 0 · lost 10
Claude Opus 5won 0 · lost 10
Muse Spark 1.1won 0 · lost 10
Claude Opus 4.7won 0 · lost 10
Claude Opus 5.5won 0 · lost 10
Llama 4 Maverick Instructwon 0 · lost 11
GPT-4.1 Miniwon 0 · lost 11
GPT-5 Miniwon 0 · lost 11
Claude Haiku 4.5won 0 · lost 11
Inklingwon 0 · lost 11
GPT-5.6 Lunawon 0 · lost 11
Claude Sonnet 4.5won 0 · lost 11
Claude Sonnet 5won 0 · lost 11
GPT-5.6 Terrawon 0 · lost 11

§ 3 · Sources

Where the numbers come from

4 publications, 9 figures. Every one links to the page it was read from.

LMArena Text ↗1 measureread 2026-09-26
LMArena Text 1211
GDPval-AA ↗1 measureread 2026-09-26
GDPval-AA -403
BFCL ↗1 measureread 2026-09-26
BFCL v4 25.83%
Enkrypt AI Safety Leaderboard ↗6 measuresread 2026-09-26
Enkrypt · Jailbreak risk 25.4%Enkrypt · Harmful content risk 26.7%Enkrypt · CBRN risk 16.2%Enkrypt · Toxicity risk 15.9%Enkrypt · Bias risk 81.7%Enkrypt · Insecure code risk 50.7%

Badge

PublicAI Index badge for Llama 3.1 8B Instruct[![PublicAI Index](https://publicai.io/model-index/badge?model=llama-3-1-8b-instruct)](https://publicai.io/model-index/m/llama-3-1-8b-instruct)