# AIME25 first-party comparison snapshot (AIME25 (Arcee))

> A display-only AIME25 reference from Arcee AI's Trinity-Large-Thinking launch chart.

Canonical page: https://benchlm.ai/benchmarks/aime2025arcee

- Category: [Mathematics](/math)
- Last updated: September 18, 2026

## About AIME25 (Arcee)

- Year: 2026
- Tasks: 15 problems
- Format: Integer answers 000-999
- Difficulty: High school olympiad level
- Paper: [Trinity-Large-Thinking: Scaling an Open Source Frontier Agent](https://www.arcee.ai/blog/trinity-large-thinking)

BenchLM stores the Arcee chart version of AIME25 separately so it does not overwrite the weighted AIME 2025 benchmark row.

AIME25 (Arcee) is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (6 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Claude Opus 4.6](/models/claude-opus-4-6) | Anthropic | 99.8% |
| 2 | [Kimi K2.5](/models/kimi-k2-5) | Moonshot AI | 96.3% |
| 3 | [Trinity-Large-Thinking](/models/trinity-large-thinking) | Arcee AI | 96.3% |
| 4 | [GLM-5](/models/glm-5) | Z.AI | 93.3% |
| 5 | [MiniMax M2.7](/models/minimax-m2-7) | MiniMax | 80.0% |
| 6 | [Trinity-Large-Preview](/models/trinity-large-preview) | Arcee AI | 24.0% |

## FAQ

### What does AIME25 (Arcee) measure?

A display-only AIME25 reference from Arcee AI's Trinity-Large-Thinking launch chart.

### Which model scores highest on AIME25 (Arcee)?

Claude Opus 4.6 by Anthropic currently leads with a score of 99.8% on AIME25 (Arcee).

### How many models are evaluated on AIME25 (Arcee)?

6 AI models have been evaluated on AIME25 (Arcee) on BenchLM.

### Does AIME25 (Arcee) affect BenchLM's overall score?

Not directly. AIME25 (Arcee) is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Compare Top Models on AIME25 (Arcee)

- [Claude Opus 4.6 vs Kimi K2.5](/compare/claude-opus-4-6-vs-kimi-k2-5)
- [Kimi K2.5 vs Trinity-Large-Thinking](/compare/kimi-k2-5-vs-trinity-large-thinking)
- [Trinity-Large-Thinking vs GLM-5](/compare/glm-5-vs-trinity-large-thinking)
- [GLM-5 vs MiniMax M2.7](/compare/glm-5-vs-minimax-m2-7)