Skip to content
Model Pulse

Leaderboard

GDPval-AA

9 models scored · metric: Elo. 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-AA 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.Gemini 3.5 Flash1,949,204
  2. 2.Gemini 3.5 Flash Lite1,402,861
  3. 3.Gemini 3.6 Flash1,014,774
  4. 4.Grok 4.3533,808
  5. 5.Gemini 3.1 Pro Preview309,609
9 models
#
🥇Claude Fable 5anthropic
1932
$3$18.50$0.013146,7531M
🥈Claude Opus 5anthropic
1861
$5$25$0.01997,3391M
🥉Kimi K3moonshotai
1668
$2$80.662¢251,7741.05M
4Gemini 3.5 Flashgoogle
1656
$0.186$1.110.085¢1,949,2041.05M
5Grok 4.3xai
1500
$1.25$2.500.281¢533,8081M
6Gemini 3.6 Flashgoogle
1421
$0.375$1.880.140¢1,014,7741.05M
7Gemini 3.1 Pro Previewgoogle
1314
$1$60.424¢309,6091.05M
8Gemini 3.5 Flash Litegoogle
1140
$0.15$1.250.081¢1,402,8611.05M
9North Mini Codecohere
14
————256K
1–9 of 9 models

Score reports: anthropic.com · anthropic.com · kimi.com · deepmind.google · artificialanalysis.ai · deepmind.google — full source URLs are linked on each model page.

Cheapest scorer: Gemini 3.5 Flash Lite at $0.15 input /M.