Atlas

Benchmarks

← All benchmarks

Agents' Last Exam Near-Term Score

Agents · 2026-06-03

Average partial-credit rubric score on the 67-task near-term subset of Agents' Last Exam.

Top models (higher is better)

ModelScore
GPT-5.6 Sol78.8
GPT-5.6 Luna74.1
GPT-5.6 Terra73.9
GPT-5.572.4
Kimi K371.6
Claude Fable 571.1
Opus 4.864.0
Opus 4.761.2
Composer 2.561.1
GLM-5.259.1
Doubao Seed 2.1 Pro58.9
GPT-5.457.8
Gemini 3.1 Pro Preview53.5
Qwen3.7-Max46.9
GLM-5.145.6
DeepSeek-V4-Pro43.8
Qwen3.6 Plus (2026-04-02)35.8
Kimi K2.635.1
MiMo-V2.535.1
Grok 4.330.4
MiniMax M2.724.5
Loading Atlas data…