The LLM benchmark aggregator.

Nova Micro

Amazon

Strongest in Factual grounding (#18 of 101), weakest in Human preference (#256 of 342). Above par in 6 of 11 scopes. Among the models it meets almost everywhere, it finishes behind Phi 4 and Claude Sonnet 5 and ahead of Gemma 4 31B and Grok 4.1 Fast.

§ 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.

Safety53.6−7.9#80/3372/3

Factual grounding61.3−9.3#18/1011/1

Harm refusal54.5−7.1#79/3001/2

Jailbreak resistance56.6−8.3#92/2721/1

Toxicity avoidance54.7−4.3#117/2721/1

Secure code51.8−14.7#138/2741/1

Fairness44−26#220/3001/2

Agents43.7−24.4#201/2681/5

Tool use38.7−35.3#68/811/1

Human preference41.7−25.8#256/3421/1

§ 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 Nova Micro, left for the other.

Smollm2 1.7B Instructwon 8 · lost 0

Nous Hermes 2 Mixtral 8x7b Dpowon 8 · lost 0

DBRX Instructwon 8 · lost 0

GPT-3.5 Turbowon 8 · lost 0

Llama 3.2 3B Instructwon 10 · lost 0

Gemma 2B Itwon 7 · lost 1

Zephyr 7B Betawon 7 · lost 1

Gemma 7B Itwon 7 · lost 1

Granite 3.0 2B Instructwon 7 · lost 1

Granite 3.1 2B Instructwon 7 · lost 1

DeepSeek LLM 67B Chatwon 7 · lost 1

Qwen1.5 14B Chatwon 7 · lost 1

Llama 3 8B Instructwon 7 · lost 1

Jamba 1.5 Miniwon 7 · lost 1

Jamba Mini 1.7won 6 · lost 1

Jamba Large 1.7won 6 · lost 1

Gemma 4 E2Bwon 6 · lost 1

Llama 3.1 8B Instructwon 8 · lost 2

Phi-4 Mini Instructwon 6 · lost 2

Gemma 4 E4Bwon 6 · lost 2

Mistral 7B Instruct V0.2won 6 · lost 2

Phi 3 Small 8k Instructwon 6 · lost 2

Starling Lm 7B Betawon 6 · lost 2

Phi 3 Medium 4k Instructwon 6 · lost 2

Gemma 2 2B Itwon 6 · lost 2

QwQ 32Bwon 6 · lost 2

Mimo V2.6 Flashwon 6 · lost 2

Gemma 3 4B Itwon 8 · lost 3

Llama 3.3 Instruct Turbo (70B)won 5 · lost 2

Gemma 4 12Bwon 5 · lost 2

Nemotron 3 Ultra 550B A55Bwon 5 · lost 2

Ling 3.0 Flash VLwon 5 · lost 2

Llama 3.2 1B Instructwon 7 · lost 3

DeepSeek V3won 7 · lost 3

Gemini 2.5 Prowon 7 · lost 3

Command R Pluswon 6 · lost 3

Grok 3won 6 · lost 3

Command Awon 7 · lost 4

Granite 3.2 8B Instructwon 5 · lost 3

Command R7Bwon 5 · lost 3

Phi 3 Mini 128k Instructwon 5 · lost 3

Phi 3 Mini 4k Instructwon 5 · lost 3

Granite 3.0 8B Instructwon 5 · lost 3

Llama 3.1 Tulu 3 8Bwon 5 · lost 3

Mistral Small 24B Instructwon 5 · lost 3

Jamba 1.5 Largewon 5 · lost 3

Magistral Mediumwon 5 · lost 3

Gemini 1.5 Prowon 5 · lost 3

Gemini 2.0 Flash Litewon 5 · lost 3

GLM-4.5won 5 · lost 3

Granite 3.1 8B Instructwon 6 · lost 4

DeepSeek R1won 6 · lost 4

DeepSeek V4 Prowon 6 · lost 4

Ling 3.0 Flashwon 4 · lost 3

Grok Build 0.1won 4 · lost 3

Qwen3.5 27Bwon 5 · lost 4

DeepSeek V4 Flashwon 5 · lost 4

GLM-4.6won 6 · lost 5

Grok 4.1 Fastwon 6 · lost 5

Gemma 4 31Bwon 6 · lost 5

Gemma 2 9B Itwon 4 · lost 4

Gemini 1.5 Flashwon 4 · lost 4

Gemini 2.0 Flashwon 4 · lost 4

Qwen3 Vl 235B A22B Instructwon 4 · lost 4

GPT-4.1 Nanowon 5 · lost 5

Qwen3 30B A3B Instructwon 5 · lost 5

Grok 4won 5 · lost 5

Qwen3.5 122B A10Bwon 5 · lost 5

Kimi K2.5won 5 · lost 5

GPT-6 Solwon 5 · lost 5

Kimi K2.6won 5 · lost 5

Mistral Largewon 5 · lost 6

Llama 4 Scout Instructwon 5 · lost 6

Llama 4 Maverick Instructwon 5 · lost 6

Gemma 3 12B Itwon 5 · lost 6

Mistral Smallwon 5 · lost 6

Gemma 3 27B Itwon 5 · lost 6

Gemini 2.5 Flashwon 5 · lost 6

DeepSeek V3.2won 5 · lost 6

Qwen3 8Bwon 4 · lost 5

C4ai Aya Expanse 8Bwon 4 · lost 5

GPT-6 Lunawon 4 · lost 5

Grok 4.3won 4 · lost 5

GLM-5.1won 4 · lost 5

GLM-5.3 Flashwon 4 · lost 5

Qwen3.7 Maxwon 4 · lost 5

Qwen3.8 Maxwon 4 · lost 5

Gemini 3.6 Flashwon 4 · lost 5

Gemini 3.8 Flashwon 4 · lost 5

Kimi K2.7 Codewon 3 · lost 4

Claude Opus 4.6won 3 · lost 4

GPT-4.1 Miniwon 4 · lost 6

Qwen3.5 35B A3Bwon 4 · lost 6

GPT-5.5won 4 · lost 6

GPT-5.6 Solwon 4 · lost 6

Llama 3 70B Instructwon 3 · lost 5

Claude Sonnet 4.6won 3 · lost 5

Gemini 3 Prowon 3 · lost 5

Nova Prowon 4 · lost 7

Kimi K2won 4 · lost 7

Qwen3 235B A22B Instructwon 4 · lost 7

Nova Litewon 3 · lost 6

GPT-4won 3 · lost 6

GPT-4o Miniwon 3 · lost 6

GPT OSS 20Bwon 3 · lost 6

NVIDIA Nemotron 3 Super 120B A12Bwon 3 · lost 6

Grok 4.6won 3 · lost 6

Grok 4.5won 3 · lost 6

Mimo V2.5 Prowon 3 · lost 6

Gemini 3.5 Flashwon 3 · lost 6

GPT OSS 120Bwon 3 · lost 7

Gemma 4 26B A4Bwon 3 · lost 7

MiniMax M3won 3 · lost 7

GPT-5.6 Lunawon 3 · lost 7

GPT-5.6 Terrawon 3 · lost 7

GLM-5.2won 3 · lost 7

Qwen3 Next 80B A3B Thinkingwon 2 · lost 5

O4 Miniwon 3 · lost 8

Claude 3 Haikuwon 2 · lost 6

Qwen Maxwon 2 · lost 6

C4ai Aya Expanse 32Bwon 2 · lost 7

O3 Miniwon 2 · lost 7

Qwen3.5 397B A17Bwon 2 · lost 7

Mimo V2.6 Prowon 2 · lost 7

Claude Opus 5won 2 · lost 7

Claude Sonnet 4won 2 · lost 8

GPT-5.1won 2 · lost 8

GPT-5 Nanowon 2 · lost 9

GPT-5 Miniwon 2 · lost 9

Claude Haiku 4.5won 2 · lost 9

GPT-4.1won 2 · lost 9

GPT-5.2won 2 · lost 9

Claude Sonnet 4.5won 2 · lost 9

Granite 4.0 H Smallwon 1 · lost 6

Gemma 2 27B Itwon 1 · lost 7

Qwen2.5 72B Instructwon 1 · lost 7

Claude 3.5 Sonnetwon 1 · lost 7

Gemini 2.5 Flash Litewon 1 · lost 7

Claude 3.5 Haikuwon 1 · lost 8

GPT-4owon 1 · lost 8

Claude 3.7 Sonnetwon 1 · lost 8

Claude Opus 4won 1 · lost 8

Hy3won 1 · lost 8

Muse Spark 1.1won 1 · lost 8

Claude Opus 5.5won 1 · lost 8

O3won 1 · lost 9

GPT-5won 1 · lost 9

GPT-5.4won 1 · lost 9

Claude Opus 4.7won 1 · lost 9

Qwen2 72B Instructwon 0 · lost 8

Claude 3 Sonnetwon 0 · lost 8

Claude 3 Opuswon 0 · lost 8

GPT-4 Turbowon 0 · lost 8

O1 Miniwon 0 · lost 8

MiniMax M2won 0 · lost 8

O1won 0 · lost 8

MiniMax M2.7won 0 · lost 9

Grok 4.7won 0 · lost 9

Claude Opus 4.8won 0 · lost 9

Inklingwon 0 · lost 10

Claude Sonnet 5won 0 · lost 10

Phi 4won 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 1241

BFCL ↗1 measureread 2026-09-26

BFCL v4 22.29%

Enkrypt AI Safety Leaderboard ↗6 measuresread 2026-09-26

Enkrypt · Jailbreak risk 7.2%Enkrypt · Harmful content risk 20.6%Enkrypt · CBRN risk 9.7%Enkrypt · Toxicity risk 3%Enkrypt · Bias risk 87.1%Enkrypt · Insecure code risk 29.8%

Vectara Hallucination Leaderboard ↗1 measureread 2026-09-26

Vectara · Factual consistency 94.5%

Badge

[![PublicAI Index](https://publicai.io/model-index/badge?model=nova-micro)](https://publicai.io/model-index/m/nova-micro)