Skip to content
Model Pulse

Leaderboard

Agents' Last Exam

5 models scored · metric: score. Prices are the cheapest listed across all serving providers. Cost/run and Pts/$ are priced for the chat token profile — short turns, light history, little caching — an assistant in a product.

This benchmark has not been calibrated to a token profile, so the figures use the site default. Treat the ordering as indicative rather than tuned to Agents' Last Exam. Profile: 1.5k in · 500 out · 20% cache hit · 8k context.

Scores are facts as publicly reported by labs (see report links below and on each model page) and aggregated via models.dev. Agents' Last Exam is maintained by its own project — Model Pulse is not affiliated with or endorsed by it.

Best value · top 5 by pts per dollar · chat profile
  1. 1.DeepSeek V4 Flash 0731308,351
  2. 2.GPT-5.6 Luna179,964
  3. 3.GPT-5.6 Terra17,041
  4. 4.GPT-5.6 Sol6,891
  5. 5.GPT-6 Astra1,558
5 models
#
🥇GPT-6 Astraopenai
59.3
$10$50$0.0381,5581.05M
🥈GPT-5.6 Solopenai
52.7
$2$100.765¢6,8911.05M
🥉GPT-5.6 Terraopenai
50.4
$1.50$20.296¢17,0411.05M
4GPT-5.6 Lunaopenai
50.3
$0.06$0.370.028¢179,9641.05M
5DeepSeek V4 Flash 0731deepseek
25.2
$0.035$0.070.008¢308,3511.31M
1–5 of 5 models

Score reports: openai.com · openai.com · api-docs.deepseek.com — full source URLs are linked on each model page.

Cheapest scorer: DeepSeek V4 Flash 0731 at $0.035 input /M.