Arcee AI: trinity-large-thinking
14 benchmarks
Leaderboard position
#361
Overall rank (of 1126 models)
1384
Elo rating
14
Benchmarks
Top 32.1%
Percentile
In Arcee AI (of 3 models)
Above: IBM Granite: granite-embedding-125m-english #360
Below: NVIDIA Corporation: cosmos-reason2-32b #362
Benchmark highlights
Best benchmark
YC-Bench
32667
Worst benchmark
AA-Omniscience Index
-44
Nearest competitor from another company
The model from another company with the most similar benchmark scores.
appeared as nearest in 2 of 14 benchmarks
2/14
14.3%
2/14
14.3%
| Model | Votes | % of benchmarks |
|---|---|---|
| xhtoken: spark-x2.6-4b | 2 | 14.3% |
| Z.ai: GLM 5 | 2 | 14.3% |
| Google: Gemma 4 31B Instruct | 1 | 7.1% |
| DeepSeek: DeepSeek V4 Flash | 1 | 7.1% |
| NVIDIA Corporation: nvidia-nemotron-3-ultra | 1 | 7.1% |
| orcarouter: orcacyber-nano-1.0 | 1 | 7.1% |
| OpenBMB: minicpm-v-4.7-35b-a3b | 1 | 7.1% |
| LG AI Research: k-exaone-236b-a23b | 1 | 7.1% |
| Qwen: qwen3.5-122b-a10b | 1 | 7.1% |
| Cohere Labs: north-mini-code-1.0 | 1 | 7.1% |
Benchmarks
YC-Bench
32667
Text Arena (Snapshot from 20 june 2026)
1369
AIME 2025
96.3
TauBench V2 (Telecom)
94.7
PinchBench
91.9
TauBench V2 (Airline)
88
MMLU-Pro
83.4
GPQA Diamond
76.3
BFCL v4
70.1
SWE-bench Verified
63.2
IFBench
52.3
Artificial Analysis Intelligence Index v4.0 (Maximum Reasoning)
31.9
Artificial Analysis Intelligence Index v4.1 (Maximum Reasoning)
24
AA-Omniscience Index
-44
Predicted scores
Estimated from 25 similar models and the global Elo rating. These are projections, not measured results.