AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
LLM Stats
Agents' Last Exam
Agents' Last Exam is a challenging benchmark for AI agents on hard, long-horizon tasks that test sustained reasoning, planning, and tool use, reported with and without tool access.
Evaluation context and evidence
- Source
- LLM Stats
- Publisher
- Not recorded
- Benchmark release
- Not recorded
- Collected
- 2026-08-17
- Modality
- text
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Original sources
Reported results 10
Shown in source observation order, not ranked. Dates retain the precision provided by the source.
| Model | Value | Unit | Protocol | Reported date and basis | Source |
|---|---|---|---|---|---|
| GPT-5.6 Sol | 0.527 | Not recorded | Not recorded | 2026-07-09 · model_announcement | LLM Stats |
| Qwen3.8 Max | 0.524 | Not recorded | Not recorded | 2026-08-02 · model_announcement | LLM Stats |
| GPT-5.6 Terra | 0.504 | Not recorded | Not recorded | 2026-07-09 · model_announcement | LLM Stats |
| GPT-5.6 Luna | 0.503 | Not recorded | Not recorded | 2026-07-09 · model_announcement | LLM Stats |
| Qwen3.8-27B | 0.429 | Not recorded | Not recorded | 2026-08-14 · model_announcement | LLM Stats |
| Seed 2.1 Pro | 0.414 | Not recorded | Not recorded | 2026-06-24 · model_announcement | LLM Stats |
| GLM-5.3 | 0.285 | Not recorded | Not recorded | 2026-08-14 · model_announcement | LLM Stats |
| Gemini 3.7 Flash | 0.263 | Not recorded | Not recorded | 2026-08-13 · model_announcement | LLM Stats |
| DeepSeek-V4-Pro-0813 | 0.257 | Not recorded | Not recorded | 2026-08-13 · model_announcement | LLM Stats |
| DeepSeek-V4-Flash-0731 | 0.252 | Not recorded | Not recorded | 2026-07-31 · model_announcement | LLM Stats |