# Arcee AI Trinity Large Thinking

Arcee AI Trinity Large Thinking costs $0.25 per million input tokens and $0.80 per million output tokens, as of October 22, 2026. Only one of the 6 coding benchmarks behind the index has measured it, and the index needs two, so there is not enough data for a coding score. 51 benchmarks outside the index have a result below.

Page: https://llmbenchmark.ai/models/arcee-ai-trinity-large-thinking
Data from October 22, 2026. Every figure below names the board it was read from and the day.

- Maker: Arcee AI
- Released: April 1, 2026
- Price per million input tokens: $0.25
- Price per million output tokens: $0.80
- Context window: 262K tokens
- Vibe Coding Index: not enough data (one index benchmark; at least two are needed to rank)

Benchmark results (52 of 195):

- LMArena WebDev: 1238 Elo (source: LMArena WebDev, read October 22, 2026)
- AA Intelligence Index: 10.8 (source: Artificial Analysis (via OpenRouter), read October 22, 2026)
- AA Coding Index: 25.8 (source: Artificial Analysis (via OpenRouter), read October 22, 2026)
- AA Agentic Index: 1.0 (source: Artificial Analysis (via OpenRouter), read October 22, 2026)
- Design Arena: websites: 1137 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: UI components: 1042 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: game dev: 1078 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: data viz: 1098 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: 3D: 1081 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: all code categories: 1116 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: SVG: 1016 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: ASCII art: 1041 Elo (source: Design Arena, read October 22, 2026)
- CaseLaw (Vals AI): 57.9% (source: Vals AI boards, read October 22, 2026)
- CorpFin (Vals AI): 54.7% (source: Vals AI boards, read October 22, 2026)
- GPQA Diamond (Artificial Analysis run): 75.2% (source: Artificial Analysis, read October 22, 2026)
- Humanity's Last Exam (Artificial Analysis run): 15.8% (source: Artificial Analysis, read October 22, 2026)
- SciCode: 40.6% (source: Artificial Analysis, read October 22, 2026)
- Terminal-Bench Hard (Artificial Analysis run): 22.7% (source: Artificial Analysis, read October 22, 2026)
- IFBench: 56.3% (source: Artificial Analysis, read October 22, 2026)
- Long context reasoning (AA-LCR): 38.0% (source: Artificial Analysis, read October 22, 2026)
- τ²-Bench Telecom: 90.1% (source: Artificial Analysis, read October 22, 2026)
- Surface Evolver Bench: 15.6% (source: Epoch AI benchmarking hub, read October 22, 2026)
- LMArena Text: 1340 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: coding: 1357 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: hard prompts: 1342 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: math: 1365 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: instruction following: 1326 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: creative writing: 1308 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: English: 1356 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: non-English: 1325 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Chinese: 1371 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: German: 1356 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Japanese: 1312 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Korean: 1306 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: French: 1366 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Spanish: 1327 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Russian: 1338 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Polish: 1312 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: multi-turn: 1320 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: longer queries: 1318 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: expert: 1359 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: hard prompts in English: 1356 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: software and IT: 1362 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: mathematical work: 1350 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: science: 1355 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: medicine and healthcare: 1349 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: legal and government: 1345 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: business and finance: 1329 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: writing and language: 1317 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: entertainment and media: 1296 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena WebDev: React: 1231 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena WebDev: HTML: 1240 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)