Request a Pilot
‹ PublicAI Index

The LLM benchmark aggregator.

Trinity Large

Arcee

Strongest in Factual grounding (#30 of 104), weakest in Agents (#267 of 298). Above par in 4 of 9 scopes. Among the models it meets almost everywhere, it finishes behind DeepSeek V4.1 Flash and Muse Spark 1.1 and ahead of Gemma 4 31B and Mistral Medium 3.1.

§ 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.

Safety52.4#116/329
Factual grounding57.7#30/104
Professional48.4#118/194
Legal48.8#99/173
Finance46.7#114/162
Human preference53.5#161/354
Human preference53.5#161/354
Agents41.9#267/298
Knowledge work37#168/208

§ 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 Trinity Large, left for the other.

Jamba 1.5 Miniwon 6 · lost 0
Jamba 1.5 Largewon 6 · lost 0
Gemini 1.5 Flashwon 6 · lost 0
NVIDIA Nemotron 3 Nano 30B A3Bwon 6 · lost 0
Gemini 1.5 Prowon 6 · lost 0
Gemma 3 27B ITwon 6 · lost 0
Llama 3.1 8B Instructwon 7 · lost 0
Llama 4 Scout Instructwon 9 · lost 0
O3 Miniwon 7 · lost 1
Magistral Small 1.2won 5 · lost 1
Gemma 3 12B ITwon 5 · lost 1
Gemini 2.0 Flashwon 5 · lost 1
Llama 4 Maverick Instructwon 7 · lost 2
GPT OSS 20Bwon 6 · lost 2
GPT-4.1 nanowon 6 · lost 2
GPT-5 nanowon 6 · lost 2
Command Awon 6 · lost 2
Mistral Small 3.1 24B Instructwon 5 · lost 2
GPT-4o miniwon 5 · lost 2
NVIDIA Nemotron 3.5 Lightning 30B A3Bwon 5 · lost 2
Mercury 2won 4 · lost 2
Llama 3.3 70B Instructwon 6 · lost 3
DeepSeek R1won 6 · lost 3
Claude 3.5 Haikuwon 5 · lost 3
Mistral Large 2.1won 4 · lost 3
MiniMax M2.1won 4 · lost 3
DeepSeek V3.1won 4 · lost 3
GPT-4owon 5 · lost 4
GPT OSS 120Bwon 5 · lost 4
Mistral Medium 3.1won 5 · lost 4
Gemma 4 31Bwon 5 · lost 4
Ling 3.0 Flashwon 3 · lost 3
Qwen3 32Bwon 3 · lost 3
Claude Haiku 4.5won 4 · lost 5
MiniMax M2.7won 4 · lost 5
DeepSeek V3.2won 4 · lost 5
Gemini 3.1 Flash-Litewon 4 · lost 5
GLM-4.7won 4 · lost 5
MiniMax M2.5won 3 · lost 4
Mistral Medium 3.5won 3 · lost 4
GLM-5won 3 · lost 4
Gemini 3 Flashwon 3 · lost 4
Kimi K2won 3 · lost 5
MiMo V2.5 Prowon 3 · lost 5
Amazon Nova 2 Litewon 2 · lost 4
Grok 3 Miniwon 2 · lost 4
GLM-4.5won 2 · lost 4
DeepSeek V3won 3 · lost 6
Kimi K2.5won 3 · lost 6
GPT-6 Astrawon 3 · lost 6
Qwen3.5 Flashwon 2 · lost 5
Grok 4 Fastwon 2 · lost 5
Grok 4won 2 · lost 5
MiMo V2.5won 2 · lost 5
Claude Opus 4.1won 2 · lost 5
Qwen3.7 Pluswon 2 · lost 5
Claude Opus 4.6won 2 · lost 5
Gemini 2.5 Flashwon 2 · lost 6
NVIDIA Nemotron 3 Ultra 550B A55Bwon 2 · lost 6
Grok 4.1 Fastwon 2 · lost 6
Inklingwon 2 · lost 6
Claude Opus 4.5won 2 · lost 6
Gemini 3 Prowon 2 · lost 6
GPT-5.4 nanowon 2 · lost 7
Mistral Large 3won 2 · lost 7
GLM-4.6won 2 · lost 7
Gemini 2.5 Prowon 2 · lost 7
GPT-5.4 miniwon 2 · lost 7
GPT-6 Solwon 2 · lost 7
Kimi K2.6won 2 · lost 7
DeepSeek V4 Prowon 2 · lost 7
Claude Sonnet 4.6won 2 · lost 7
Gemini 3.1 Prowon 2 · lost 7
Gemini 4 Argonwon 2 · lost 7
Qwen3 Next 80B A3B Thinkingwon 1 · lost 5
Qwen3.5 35B A3Bwon 1 · lost 5
Qwen3.5 122B A10Bwon 1 · lost 5
Gemma 4 26B A4Bwon 1 · lost 5
Inkling Smallwon 1 · lost 6
Grok 3won 1 · lost 6
Claude Haiku 5.5won 1 · lost 6
Claude Opus 4won 1 · lost 6
Qwen3.6 Pluswon 1 · lost 6
Gemini 3.5 Flash-Litewon 1 · lost 6
GPT-6.1 Solwon 1 · lost 6
Gemini 2.5 Flash-Litewon 1 · lost 7
O4 Miniwon 1 · lost 7
Qwen3 235B A22B Instructwon 1 · lost 7
Mistral Large 4won 1 · lost 7
MiniMax M3won 1 · lost 7
GPT-5.2won 1 · lost 7
DeepSeek V4 Flashwon 1 · lost 7
GPT-6 Lunawon 1 · lost 7
Grok 4.3won 1 · lost 7
MiMo V2.6 Flashwon 1 · lost 7
GLM-5.1won 1 · lost 7
Qwen3.7 Maxwon 1 · lost 7
GLM-5.3 Flashwon 1 · lost 7
GLM-5.2won 1 · lost 7
Gemini 3.5 Flashwon 1 · lost 7
MiMo V2.6 Prowon 1 · lost 7
Gemini 3.6 Flashwon 1 · lost 7
Gemini 3.8 Flashwon 1 · lost 7
GPT-5 miniwon 1 · lost 8
Claude Sonnet 4won 1 · lost 8
GPT-5won 1 · lost 8
GPT-5.1won 1 · lost 8
Claude Sonnet 4.5won 1 · lost 8
GPT-5.4won 1 · lost 8
GPT-5.5won 1 · lost 8
GPT-5.6 Solwon 1 · lost 8
Claude Opus 4.7won 1 · lost 8
Claude Opus 5.5won 1 · lost 8
O1won 0 · lost 6
Inkling 2 Smallwon 0 · lost 6
Kimi K3.1 Prowon 0 · lost 6
Gemini 4 Carbonwon 0 · lost 6
Claude 3.7 Sonnetwon 0 · lost 7
O3won 0 · lost 7
Qwen3.8 27Bwon 0 · lost 7
Step 5won 0 · lost 7
Claude Sonnet 5.5won 0 · lost 7
GLM-5.3won 0 · lost 7
Kimi K3won 0 · lost 7
Muse Sparkwon 0 · lost 7
Gemini 3.7 Flashwon 0 · lost 7
Muse Spark 1.2won 0 · lost 7
Muse Spark 1.3won 0 · lost 7
Claude Fable 5.1won 0 · lost 7
Claude Fable 5won 0 · lost 7
Muse Wonderwon 0 · lost 7
GPT-4.1 miniwon 0 · lost 8
GPT-4.1won 0 · lost 8
Grok 4.7won 0 · lost 8
GPT-5.6 Lunawon 0 · lost 8
Grok 4.6won 0 · lost 8
Claude Sonnet 5won 0 · lost 8
Grok 4.5won 0 · lost 8
GPT-5.6 Terrawon 0 · lost 8
Claude Opus 4.8won 0 · lost 8
Qwen3.8 Maxwon 0 · lost 8
Claude Opus 5won 0 · lost 8
Muse Spark 1.1won 0 · lost 8
DeepSeek V4.1 Flashwon 0 · lost 9

§ 3 · Sources

Where the numbers come from

5 publications, 6 figures. Every one links to the page it was read from.

LMArena Text ↗1 measureread 2026-11-10
LMArena Text 1367
GDPval-AA ↗1 measureread 2026-11-10
GDPval-AA 344
AA-Briefcase ↗1 measureread 2026-11-10
AA-Briefcase 256
Vals.ai ↗2 measuresread 2026-11-10
Vals · CaseLaw 57.88%Vals · CorpFin 54.66%
Vectara Hallucination Leaderboard ↗1 measureread 2026-11-10
Vectara · Factual consistency 93.1%

Badge

PublicAI Index badge for Trinity Large[![PublicAI Index](https://publicai.io/model-index/badge?model=trinity-large)](https://publicai.io/model-index/m/trinity-large)