Skip to content
Model Pulse

Leaderboard

GDPval

6 models scored · metric: wins or ties. 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.

A benchmark is priced for the workload it exercises, not a fixed input:output blend: an agent loop and a single hard question bill very differently on the same rate card. 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. GDPval 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.Nemotron 3 Ultra 550B A55B225,060
  2. 2.GPT-5.598,973
  3. 3.Step 3.7 Flash57,109
  4. 4.GPT-5.420,861
  5. 5.GPT-5.4 Pro669
6 models
#
🥇GPT-5.5openai
84.9
$0.188$1.130.086¢98,9731.05M
🥈GPT-5.4openai
83
$0.75$60.398¢20,8611.05M
🥉GPT-5.5 Proopenai
82.3
$27.27$163.64$0.1256601.05M
4GPT-5.4 Proopenai
82
$27$160$0.1236691.05M
5Nemotron 3 Ultra 550B A55Bnvidia
46.7
$0.1$0.10.021¢225,0601.05M
6Step 3.7 Flashstepfun
45.8
$0.185$1.110.080¢57,109262K
1–6 of 6 models

Score reports: openai.com · huggingface.co · static.stepfun.com — full source URLs are linked on each model page.

Cheapest scorer: Nemotron 3 Ultra 550B A55B at $0.1 input /M.