Agents’ Last Exam · 55 professional fields; exact task version unspecified · Benchmark definition and scores
Agents’ Last Exam · 55 professional fields; exact task version unspecified has benchmark disclosures or scores across 4 model releases.
Benchmark versions and metrics
- Score · % · Higher is better
Latest models by series · reported scores
The latest models in each named series have no scores to display in this scope. Recorded historical data appears below.
History · 4 releases
- GPT-6 Astra1 score record for this release, including 1 exact value (may include historical records)
- GPT-5.6 Sol5 score records for this release, including 5 exact values (may include historical records)
- GPT-5.6 Luna5 score records for this release, including 5 exact values (may include historical records)
- GPT-5.6 Terra5 score records for this release, including 5 exact values (may include historical records)