The LLM benchmark aggregator.

Mercury 2

Inception AI

Strongest in Secure code (#7 of 268), weakest in Agents (#252 of 298). Above par in 5 of 11 scopes. Among the models it meets almost everywhere, it finishes behind Claude Opus 5 and Claude Opus 5.5 and ahead of Kimi K2.6 and DeepSeek V3.2.

§ 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.

Safety49.9−11.5#177/3272/3

Secure code65.5−0.7#7/2681/1

Fairness55.3−14.7#64/2901/2

Factual grounding44−26.7#84/1041/1

Toxicity avoidance55.5−3.5#91/2661/1

Harm refusal46.4−15.1#208/2901/2

Jailbreak resistance37.3−27.7#224/2661/1

Human preference51.2−17.6#185/3541/1

Agents42.9−23.4#252/2982/6

Knowledge work38.7−32#161/2082/2

§ 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 Mercury 2, left for the other.

OLMo 7B Instructwon 8 · lost 0

Gemma 7B ITwon 8 · lost 0

SmolLM2 1.7B Instructwon 7 · lost 1

Zephyr 7B Betawon 7 · lost 1

Nous Hermes 2 Mixtral 8x7B DPOwon 7 · lost 1

DBRX Instructwon 7 · lost 1

Mixtral 8x7B Instructwon 7 · lost 1

Gemma 2 2B ITwon 7 · lost 1

GPT-3.5 Turbowon 7 · lost 1

Mixtral 8x22B Instructwon 7 · lost 1

Jamba 1.5 Miniwon 7 · lost 1

Llama 3.1 70B Instructwon 7 · lost 1

Magistral Mediumwon 7 · lost 1

QwQ 32Bwon 7 · lost 1

Jamba Mini 1.7won 6 · lost 1

Phi-4 Mini Instructwon 7 · lost 2

Mistral Small 3 24B Instructwon 7 · lost 2

Gemma 4 E2Bwon 6 · lost 2

Magistral Small 1.2won 6 · lost 2

Grok Build 0.1won 6 · lost 2

Ling 3.0 Flash VLwon 6 · lost 2

Gemma 2B ITwon 6 · lost 2

Mistral 7B Instruct v0.2won 6 · lost 2

DeepSeek LLM 67B Chatwon 6 · lost 2

Qwen1.5 14B Chatwon 6 · lost 2

Gemma 2 9B ITwon 6 · lost 2

Jamba 1.5 Largewon 6 · lost 2

Llama 3.3 70B Instructwon 8 · lost 3

DeepSeek V3won 8 · lost 3

Jamba Large 1.7won 5 · lost 2

Command R7Bwon 5 · lost 2

Llama 3.1 8B Instructwon 7 · lost 3

GPT-4.1 nanowon 7 · lost 3

Grok 4.1 Fastwon 7 · lost 3

Qwen3 8Bwon 6 · lost 3

Llama 3.2 3B Instructwon 6 · lost 3

Command R+won 6 · lost 3

Grok 3won 6 · lost 3

Grok 4won 6 · lost 3

Llama 4 Scout Instructwon 7 · lost 4

DeepSeek R1won 7 · lost 4

Gemma 4 E4Bwon 5 · lost 3

Ling 3.0 Flashwon 5 · lost 3

Kimi K2.7 Codewon 5 · lost 3

Phi-3 Mini 128K Instructwon 5 · lost 3

Phi-3 Mini 4K Instructwon 5 · lost 3

Granite 3.0 2B Instructwon 5 · lost 3

Starling LM 7B Betawon 5 · lost 3

Granite 3.1 2B Instructwon 5 · lost 3

Gemini 1.5 Flashwon 5 · lost 3

Llama 3.1 405B Instructwon 5 · lost 3

O1 Miniwon 5 · lost 3

GPT-4won 6 · lost 4

Gemma 3 4B ITwon 6 · lost 4

NVIDIA Nemotron 3 Ultra 550B A55Bwon 6 · lost 4

MiMo V2.6 Flashwon 6 · lost 4

Qwen3.7 Maxwon 6 · lost 4

GLM-5.2won 6 · lost 4

Gemini 3.5 Flashwon 6 · lost 4

Gemini 3.6 Flashwon 6 · lost 4

GLM-4.5won 4 · lost 3

Llama 3.2 1B Instructwon 5 · lost 4

Amazon Nova Litewon 5 · lost 4

Qwen3 30B A3B Instructwon 5 · lost 4

MiniMax M3won 5 · lost 4

Gemma 3 12B ITwon 6 · lost 5

DeepSeek V3.2won 6 · lost 5

Kimi K2.6won 6 · lost 5

Gemma 4 12Bwon 4 · lost 4

Llama 2 7B Chatwon 4 · lost 4

Llama 2 13B Chatwon 4 · lost 4

Llama 2 70B Chatwon 4 · lost 4

Phi-3 Small 8K Instructwon 4 · lost 4

Granite 3.0 8B Instructwon 4 · lost 4

Phi-3 Medium 4K Instructwon 4 · lost 4

Llama 3.1 Tulu 3 8Bwon 4 · lost 4

Llama 3 8B Instructwon 4 · lost 4

Claude 3 Haikuwon 4 · lost 4

Qwen2 72B Instructwon 4 · lost 4

Llama 3 70B Instructwon 4 · lost 4

Claude 3 Sonnetwon 4 · lost 4

Qwen Maxwon 4 · lost 4

GPT-4 Turbowon 4 · lost 4

Gemini 1.5 Prowon 4 · lost 4

Gemini 2.0 Flash-Litewon 4 · lost 4

Amazon Nova Microwon 5 · lost 5

Amazon Nova Prowon 5 · lost 5

GPT-4o miniwon 5 · lost 5

GPT OSS 20Bwon 5 · lost 5

Command Awon 5 · lost 5

NVIDIA Nemotron 3 Super 120B A12Bwon 5 · lost 5

O3 Miniwon 5 · lost 5

Mistral Large 4won 5 · lost 5

MiMo V2.5 Prowon 5 · lost 5

Llama 4 Maverick Instructwon 5 · lost 6

GPT-4owon 5 · lost 6

Gemma 3 27B ITwon 5 · lost 6

GLM-4.6won 5 · lost 6

Kimi K2.5won 5 · lost 6

Gemma 4 31Bwon 5 · lost 6

Granite 3.1 8B Instructwon 4 · lost 5

Aya Expanse 8Bwon 4 · lost 5

Aya Expanse 32Bwon 4 · lost 5

Granite 4.0 H Smallwon 4 · lost 5

DeepSeek V3.1won 4 · lost 5

Granite 3.2 8B Instructwon 3 · lost 4

Phi 4won 4 · lost 6

O4 Miniwon 4 · lost 6

Kimi K2won 4 · lost 6

DeepSeek V4 Flashwon 4 · lost 6

Grok 4.3won 4 · lost 6

Gemma 2 27B ITwon 3 · lost 5

Llama 3.1 Nemotron 70B Instructwon 3 · lost 5

Qwen2.5 72B Instructwon 3 · lost 5

Claude 3 Opuswon 3 · lost 5

Gemini 2.0 Flashwon 3 · lost 5

O1won 3 · lost 5

Qwen3 VL 235B A22B Instructwon 3 · lost 5

GPT-5.6 Solwon 4 · lost 7

GPT-5 nanowon 3 · lost 6

O3won 3 · lost 6

GLM-5.3 Flashwon 3 · lost 6

Claude 3.5 Haikuwon 3 · lost 7

GPT-4.1 miniwon 3 · lost 7

Gemini 2.5 Flashwon 3 · lost 7

GPT-4.1won 3 · lost 7

Qwen3 235B A22B Instructwon 3 · lost 7

GPT-5.6 Lunawon 3 · lost 7

GLM-5.1won 3 · lost 7

MiMo V2.6 Prowon 3 · lost 7

Qwen3.8 Maxwon 3 · lost 7

Claude Opus 4.6won 2 · lost 5

GPT-5 miniwon 3 · lost 8

GPT-5won 3 · lost 8

Gemma 4 26B A4Bwon 3 · lost 8

Gemini 2.5 Prowon 3 · lost 8

GPT-6 Solwon 3 · lost 8

DeepSeek V4 Prowon 3 · lost 8

GPT-5.4won 3 · lost 8

Qwen3 Next 80B A3B Thinkingwon 2 · lost 6

Claude 3.7 Sonnetwon 2 · lost 7

Qwen3.5 27Bwon 2 · lost 7

Claude Sonnet 4.6won 2 · lost 7

GPT OSS 120Bwon 2 · lost 8

GPT-6 Lunawon 2 · lost 8

Qwen3.5 397B A17Bwon 2 · lost 8

Inklingwon 2 · lost 8

Hy3won 2 · lost 8

GPT-5.6 Terrawon 2 · lost 8

Muse Spark 1.1won 2 · lost 8

Gemini 3.8 Flashwon 2 · lost 8

Qwen3.5 35B A3Bwon 2 · lost 9

Qwen3.5 122B A10Bwon 2 · lost 9

GPT-5.1won 2 · lost 9

GPT-5.5won 2 · lost 9

Claude Opus 4.7won 2 · lost 9

Gemini 2.5 Flash-Litewon 1 · lost 6

Gemini 3 Prowon 1 · lost 6

MiniMax M2won 1 · lost 7

Claude 3.5 Sonnetwon 1 · lost 7

Claude Opus 4won 1 · lost 8

GPT-5.2won 1 · lost 9

Grok 4.7won 1 · lost 9

Grok 4.6won 1 · lost 9

Claude Sonnet 5won 1 · lost 9

Grok 4.5won 1 · lost 9

Claude Opus 4.8won 1 · lost 9

Claude Sonnet 4won 1 · lost 10

Claude Haiku 4.5won 1 · lost 10

MiniMax M2.7won 1 · lost 10

Claude Sonnet 4.5won 1 · lost 10

Claude Opus 5.5won 1 · lost 10

Claude Opus 5won 0 · lost 10

§ 3 · Sources

Where the numbers come from

5 publications, 10 figures. Every one links to the page it was read from.

LMArena Text ↗1 measureread 2026-11-11

LMArena Text 1343

GDPval-AA ↗1 measureread 2026-11-11

GDPval-AA 502

AA-Briefcase ↗1 measureread 2026-11-11

AA-Briefcase 266

Enkrypt AI Safety Leaderboard ↗6 measuresread 2026-11-11

Enkrypt · Jailbreak risk 23.5%Enkrypt · Harmful content risk 1.1%Enkrypt · CBRN risk 47.3%Enkrypt · Toxicity risk 2.4%Enkrypt · Bias risk 69.5%Enkrypt · Insecure code risk 1.3%

Vectara Hallucination Leaderboard ↗1 measureread 2026-11-11

Vectara · Factual consistency 87.7%

Badge

[![PublicAI Index](https://publicai.io/model-index/badge?model=mercury-2)](https://publicai.io/model-index/m/mercury-2)