LongCat 2.5 Release - Program Bench - Almost Resolved: leaderboard
LongCat-2.5 final release detailed native result table, November 2026. External:true cells are explicitly cited other-evaluator results and excluded from this component; self-run numeric cells retained. No Preview/final or release-generation aliases. Detailed table used instead of inconsistent rounded headline charts. Terminal Bench v 4.0 / v 2.1, Program Bench, NL 2Repo: Claude Code harness (v 2.1.280) with max_seq_length = 512K; Terminal Bench v 2.1 results are averaged over three independent runs. Metric: Score (%).
Metric: Score (%). Source: longcat.ai. Saturation forecast: Around 2030. 2 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | LongCat 2.0 | 2.5 | #220 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=longcat-2-5-release-program-bench-almost-resolved · How It Works · Data refreshed daily, snapshot 2026-11-05.