Skip to content
Model Pulse

Leaderboard

NL2Repo

4 models scored. Prices are the cheapest listed across all serving providers. Cost/run and Pts/$ are priced for the agentic token profile — tool loops re-send a growing transcript and think between calls.

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: 12k in · 2k out · 3k reasoning · 70% cache hit · 32k context.

Scores are facts as publicly reported by labs (see report links below and on each model page) and aggregated via models.dev. NL2Repo is maintained by its own project — Model Pulse is not affiliated with or endorsed by it.

Best value · top 4 by pts per dollar · agentic profile
  1. 1.DeepSeek V4 Flash 073190,666
  2. 2.GLM-5.26,708
  3. 3.Qwen3.7 Max2,591
  4. 4.Qwen3.8 Max Preview1,303
4 models
#
🥇Qwen3.8 Max Previewalibaba
55.9
$2$6$0.0431,3031M
🥈DeepSeek V4 Flash 0731deepseek
54.2
$0.035$0.070.060¢90,6661.31M
🥉GLM-5.2zhipuai
48.9
$0.3$1.050.729¢6,7081.05M
4Qwen3.7 Maxalibaba
47.2
$0.825$2.48$0.0182,5911.06M
1–4 of 4 models

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

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