Trinity-Large-Preview
Arcee AI- Arena score
- 1339
- Among open models
- #72of 148
- Among all on Arena
- #221
- Votes
- 30,992
Measured on Trinity Large Preview, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
CategoryScoreOpen rankArena rankVotes
- Coding1381#63#1967.9K
- French1375#52#172898
- Software & IT1371#70#21111.9K
- Hard prompts, English1367#71#2148.9K
- English1358#75#22313.8K
- Spanish1356#59#1891K
- Long prompts1355#61#20011.5K
- Applied math1354#70#2171.8K
- Chinese1353#72#2192.1K
- Expert1352#67#2022.9K
- Science1352#71#2185.1K
- Hard prompts1350#68#21519.3K
- Medicine & health1343#72#2212.3K
- Multi-turn1341#68#2145.6K
- Legal & government1340#71#2212.2K
- Math1336#73#2232K
- Instructions1334#63#2069.6K
- Writing & literature1328#65#2087.2K
- Business & finance1327#73#2186K
- Russian1323#72#2223.8K
- Creative writing1319#62#2044.7K
- Non-English1318#70#21917.2K
- German1316#61#195466
- Media & sports1315#63#2055.9K
- Excluding ties1298#70#21723.5K
- Japanese1293#46#170216
- Polish1288#63#209577
- Korean1257#59#200469
About as strong, smaller
Compare
gemma-3-12b-itGoogle133412.2B

Mistral-Small-3.2-24B-Instruct-2506Mistral AI133824.0B

gemma-4-26B-A4B-itGoogle143425.8B

gemma-3-27b-itGoogle135827.4B
Built on it
Ways to run it
- GGUF · llama.cpp, Ollama, LM Studioarcee-ai/Trinity-Large-Preview-GGUF4 builds
- MLX · Apple silicon: mlx-lm, LM Studiomlx-community/Trinity-Large-Preview-8bit2 builds
Most downloaded
- Trinity-Large-Preview-GGUFarcee-ai · Quantization2.2K downloads
- arcee-ai_Trinity-Large-Preview-GGUFbartowski · Quantization1.3K downloads
- Trinity-Large-Preview-GGUFunsloth · Quantization1.2K downloads
- arcee-ai.Trinity-Large-Preview-GGUFDevQuasar · Quantization486 downloads
- Trinity-Large-Preview-W4A16arcee-ai · Quantization134 downloads
BenchClub runs
Not runnable yet
Runs open once a Trinity-Large-Preview build is registered.
More from Arcee AI
See more
Trinity-Large-Thinking3.3K399B
Other >300B models
See more
DeepSeek-V3.2DeepSeek9.6M685B
GLM-5.3-FlashZ.ai6.4M321B
InklingThinking Machines1.5M952B
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16NVIDIA1M561B