AgentHorizon
Harbor: pendingA benchmark of 1,373 computer-use tasks with paired instructions to evaluate agentic judges on long-horizon trajectory success verification across three OSs.
- Samples
- 1,373
- Released
- 2026
- Scores
- 10
TRuST
TRuST: A native-Russian hard-search benchmark
TRuST: T-Tech Russian Search Test 🚨 TRuST was built from sources collected from the open web that were publicly accessible at the time of crawling.
How to run
ltb · trust
$ npm i -g lettokenburn-cli$ ltb bench pull trust --n 50$ ltb bench run ./trust -a claude-code -m anthropic/claude-opus-4-8$ ltb bench push
Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs
Scores
12 sourced entries| Harness | Source | Confidence | Link | |||
|---|---|---|---|---|---|---|
| T-Search | 61.3 | t-search | Independent | medium | Oct 5, 2026 | arxiv.org |
| GLM-5.1 | 54.0 | t-search | Independent | medium | Oct 5, 2026 | arxiv.org |
| Tongyi DeepResearch | 52.5 | tongyi | Independent | medium | Oct 5, 2026 | arxiv.org |
| GLM-5.2 | 52.0 | t-search | Independent | medium | Oct 5, 2026 | arxiv.org |
| Kimi K2.6 | 51.1 | t-search | Independent | medium | Oct 5, 2026 | arxiv.org |
| Qwen3.6 27B | 48.3 | t-search | Independent | medium | Oct 5, 2026 | arxiv.org |
| DeepSeek V4 Flash | 48.2 | t-search | Independent | medium | Oct 5, 2026 | arxiv.org |
| Qwen3.5 397B A17B | 47.2 | t-search | Independent | medium | Oct 5, 2026 | arxiv.org |
| Qwen3.5 122B A10B | 42.7 | t-search | Independent | medium | Oct 5, 2026 | arxiv.org |
| Qwen3.6 35B A3B | 41.5 | t-search | Independent | medium | Oct 5, 2026 | arxiv.org |
| WebSailor-32B | 36.9 | websailor | Independent | medium | Oct 5, 2026 | arxiv.org |
| google/gemma-4-26B-A4B-it | 34.3 | t-search | Independent | medium | Oct 5, 2026 | arxiv.org |
Every number links to where it was published. Low-confidence rows are muted and need per-cell verification.
Reproduced by the community
All runsLoading community runs…
About
TRuST: T-Tech Russian Search Test
🚨 TRuST was built from sources collected from the open web that were publicly accessible at the time of crawling. We do not claim ownership of the original source materials and do not endorse, verify, or take responsibility for the accuracy, completeness, legality, or safety of the information contained in those sources. It is intended for research and development purposes only. Users are fully responsible for inspecting the data, respecting…