Trinity-Large-Preview

Trinity-Large-Preview is a non-reasoning model from Arcee AI in the Trinity Large family. 14 benchmarks count toward its score, in 5 categories.

availableShows if the model has enough results for an index.
IndexOverall score. 50 is the middle.41.6 ±6.8
CoverageShare of the index weight with results.75%
SpeedOutput tokens per second.
Input / 1MUS dollars per 1M input tokens.$0.25
Output / 1MUS dollars per 1M output tokens.$1
ContextMaximum tokens in one request.512K
EloLMArena rating and rank.1338 (#202)

50 is the middle of the board. The range shows the doubt in the index.

29,742 votes. Elo shows what people prefer. It does not change the score.

CapabilitiesScore per category. 50 is the middle.

50 is the middle
AgenticMulti-step tasks with tools.
45.7
CodingCode writing and repair.
43.2
ReasoningLogic problems and puzzles.
37.4
MultimodalTasks with images and text.
N/A
KnowledgeFacts and expert knowledge.
40.1
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
46.2
MathMath problems.
N/A

Results

14 counted
BenchmarkThe test name.CategoryThe capability that the test measures.ResultThe score from the publisher.IndexThis result on the index scale.RunThe settings of the run.DateDate of the result.Published byThe source of the result.
τ²-Bench Tool-Agent-User EvaluationAgentic90.1%63.5Victor Barres et al.
Massive Multitask Language UnderstandingKnowledge87.2%Dan Hendrycks et al.
MMLU-Pro first-party comparison snapshotKnowledge75.2%39.0Arcee AI
Artificial Analysis GPQA DiamondKnowledge75.2%45.6Artificial Analysis
GPQA DiamondKnowledge63.3%36.7David Rein et al.
Artificial Analysis IFBenchInstruction56.3%46.2Artificial Analysis
Artificial Analysis SciCodeCoding40.6%49.2Artificial Analysis
Artificial Analysis Long Context ReasoningReasoning38.0%34.6Artificial Analysis
Artificial Analysis Coding IndexCoding25.8%37.1Artificial Analysis
AIME25 first-party comparison snapshotMath24.0%Arcee AI
Artificial Analysis Omniscience AccuracyKnowledge22.5%41.7Artificial Analysis
Artificial Analysis Humanity's Last ExamKnowledge15.8%41.7Artificial Analysis
Artificial Analysis Intelligence IndexKnowledge10.8%35.9Artificial Analysis
Artificial Analysis Agentic IndexAgentic1.2%38.1Artificial Analysis
Critical Physics TasksReasoning0.9%40.3Artificial Analysis
GDPval-AA normalizedAgentic0.0%35.6Artificial Analysis

14 benchmarks count, from 14 of 16 results. A grey row does not count. Too few models took that benchmark.

Sources

BenchLM benchmark aggregationUsed with attribution; per-benchmark results credited to their original authors

Same level, lower price

Qwen3.8-Flash-Next66.4 · Freedots3-note Preview65.5 · FreeApodex 1.1 Mini59.1 · Free

More from Arcee AI

Trinity-Large-Thinking42.7