Mathematics · Benchmark profile
A display-only AIME25 reference from Arcee AI's Trinity-Large-Thinking launch chart.
Data verified 21 Jul 2026 · Methodology 1.6.0
Benchmark score on AIME25 first-party comparison snapshot
Claude Opus 4.6 leads at 99.8%, followed by Kimi K2.5 (96.3%) and Trinity-Large-Thinking (96.3%).
Visual analysis
Switch between model placement, score distribution and descriptive provider averages. Every view uses the same sourced leaderboard.
6 ranked models · higher is better
| Model | Rank | Provider | Score |
|---|---|---|---|
| Claude Opus 4.6 | #1 | Anthropic | 99.8% |
| Kimi K2.5 | #2 | Moonshot AI | 96.3% |
| Trinity-Large-Thinking | #3 | Arcee AI | 96.3% |
| GLM-5 | #4 | Z.AI | 93.3% |
| MiniMax M2.7 | #5 | MiniMax | 80% |
| Trinity-Large-Preview | #6 | Arcee AI | 24% |
One best score per model · higher is better
| Rank | Model | Provider | License | Evidence use | Score |
|---|---|---|---|---|---|
| #1 | Claude Opus 4.6 claude-opus-4-6 | Anthropic | closed | Reference only | 99.8% |
| #2 | Kimi K2.5 kimi-k2.5 | Moonshot AI | — | Reference only | 96.3% |
| #3 | Trinity-Large-Thinking trinity-large-thinking | Arcee AI | open | Reference only | 96.3% |
| #4 | GLM-5 glm-5 | Z.AI | open | Reference only | 93.3% |
| #5 | MiniMax M2.7 minimax-m2-7 | MiniMax | open | Reference only | 80% |
| #6 | Trinity-Large-Preview trinity-large-preview | Arcee AI | open | Estimated reference | 24% |
The top of this snapshot is led by Claude Opus 4.6 at 99.8%; third place is 3.5 points behind. The top-6 spread is 75.8 points.
About AIME25 first-party comparison snapshot
A display-only AIME25 reference from Arcee AI's Trinity-Large-Thinking launch chart. Results stay tied to the exact model variant and evaluation system. Multiple systems for the same model use the best published score on this page; overall Lumina scoring uses the median of ranking-eligible rows.
Open benchmark source ↗FAQ
A display-only AIME25 reference from Arcee AI's Trinity-Large-Thinking launch chart.
Claude Opus 4.6 by Anthropic currently leads with 99.8%.
6 models in the LuminaBench cohort have a qualifying score on this benchmark.
No. This benchmark is display-only and does not enter the overall Lumina composite.
Related
