Agents' Last Exam
Agents' Last Exam - frontier agentic tasks benchmark. Reports Pass@1 and Score (aggregate).
Category
General Agents
Max Score
100.0
Score Type
percent
Active
Yes
Model Scores
Scores for Agents' Last Exam
| Model | Score | Date | Verified |
|---|---|---|---|
| Qwen3.8-27B |
46.23%
|
18.08.2026 | Verified |
| Qwen3.7-Plus |
12.26%
|
18.08.2026 | Unverified |
| GPT-5.6 Sol |
94.34%
|
18.08.2026 | Unverified |
| Claude Opus 4.8 |
77.36%
|
18.08.2026 | Unverified |
| Qwen3.7-Max |
5.66%
|
18.08.2026 | Unverified |
| Qwen3.8-2.4T-A95B |
77.36%
|
18.08.2026 | Verified |
| Kimi K3 |
83.49%
|
18.08.2026 | Verified |
| DeepSeek-V4-Flash-0731 |
68.87%
|
31.07.2026 | Verified |
| DeepSeek-V4-Flash |
24.53%
|
13.08.2026 | Verified |
| GLM-5.2 |
62.26%
|
31.07.2026 | Verified |
| Opus-4.8 |
71.23%
|
31.07.2026 | Verified |
| DeepSeek-V4-Pro |
27.83%
|
13.08.2026 | Verified |
| DeepSeek-V4-Pro-0813 |
71.23%
|
13.08.2026 | Verified |
| Qwen3.8-Flash-Next |
64.62%
|
26.08.2026 | Verified |
| GLM-5.3-Flash |
74.06%
|
27.08.2026 | Verified |
| GPT-5.3 Terra |
77.36%
|
27.08.2026 | Verified |
| Gemini 3.7 Flash |
82.08%
|
27.08.2026 | Verified |
| GLM-5.3 |
84.43%
|
28.08.2026 | Verified |
| Fable-5 |
62.26%
|
28.08.2026 | Verified |
| Hy3 |
30.66%
|
28.08.2026 | Verified |
| Hy4 preview |
57.55%
|
28.08.2026 | Verified |
| DeepSeek V4 Pro |
53.30%
|
28.08.2026 | Verified |
| DeepSeek-V4.1-Flash |
100.00%
|
10.09.2026 | Verified |
| Qwen3.6-27B |
10.60
|
18.08.2026 | Unverified |
| Claude Opus 5 |
68.40%
|
28.08.2026 | Verified |
| DeepSeek-V4-Flash-Vision-Exp |
78.77%
|
08.09.2026 | Verified |