Agents · Benchmark profile
A long-horizon planning benchmark that tests whether agents can optimize under explicit time, budget, and feasibility constraints.
Data verified 21 Jul 2026 · Methodology 1.6.0
Benchmark score on DeepPlanning
Qwen3.7-Plus leads at 62.3%, followed by Qwen3.6 Plus (41.5%) and Qwen3.5 397B (37.6%).
Visual analysis
Switch between model placement, score distribution and descriptive provider averages. Every view uses the same sourced leaderboard.
7 ranked models · higher is better
| Model | Rank | Provider | Score |
|---|---|---|---|
| Qwen3.7-Plus | #1 | Alibaba Cloud | 62.3% |
| Qwen3.6 Plus | #2 | Alibaba Cloud | 41.5% |
| Qwen3.5 397B | #3 | Alibaba Cloud | 37.6% |
| Claude Opus 4.5 | #4 | Anthropic | 26.4% |
| Qwen3.6-35B-A3B | #5 | Alibaba Cloud | 25.9% |
| GLM-5 | #6 | Z.AI | 14.6% |
| Kimi K2.5 | #7 | Moonshot AI | 14.4% |
One best score per model · higher is better
| Rank | Model | Provider | License | Evidence use | Score |
|---|---|---|---|---|---|
| #1 | Qwen3.7-Plus qwen3.7-plus | Alibaba Cloud | — | Reference only | 62.3% |
| #2 | Qwen3.6 Plus qwen3-6-plus | Alibaba Cloud | closed | Reference only | 41.5% |
| #3 | Qwen3.5 397B qwen3.5-397b-a17b | Alibaba Cloud | open | Estimated reference | 37.6% |
| #4 | Claude Opus 4.5 claude-opus-4-5 | Anthropic | closed | Reference only | 26.4% |
| #5 | Qwen3.6-35B-A3B qwen3-6-35b-a3b | Alibaba Cloud | open | Estimated reference | 25.9% |
| #6 | GLM-5 glm-5 | Z.AI | open | Reference only | 14.6% |
| #7 | Kimi K2.5 kimi-k2.5 | Moonshot AI | — | Reference only | 14.4% |
The top of this snapshot is led by Qwen3.7-Plus at 62.3%; third place is 24.7 points behind. The top-7 spread is 47.9 points.
About DeepPlanning
A long-horizon planning benchmark that tests whether agents can optimize under explicit time, budget, and feasibility constraints. 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 long-horizon planning benchmark that tests whether agents can optimize under explicit time, budget, and feasibility constraints.
Qwen3.7-Plus by Alibaba Cloud currently leads with 62.3%.
7 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
