Skip to content
Model Pulse

Leaderboard

Terminal-Benchofficial site ↗

37 models scored · metric: success rate. 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. Terminal-Bench is maintained by its own project — Model Pulse is not affiliated with or endorsed by it.

Best value · top 5 by pts per dollar · agentic profile
  1. 1.DeepSeek V4 Flash 0731138,341
  2. 2.Laguna XS 2.131,888
  3. 3.GPT-5.6 Luna31,628
  4. 4.Nemotron 3 Ultra 550B A55B30,000
  5. 5.MiniMax-M2.723,496
37 models
#
🥇GPT-5.6 Solopenai
88.8
$2$10$0.0631,4011.05M
🥈Kimi K3moonshotai
88.3
$2$8$0.0531,6691.05M
🥉Claude Fable 5anthropic
88
$3$18.50$0.1117911M
4GPT-5.6 Terraopenai
87.4
$1.50$2$0.0194,5141.05M
5Qwen3.8 Max Previewalibaba
86.6
$2$6$0.0432,0191M
6Gemini 3.7 Flashgoogle
85.8
$0.75$3.75$0.0223,8741.05M
7GPT-5.6 Lunaopenai
84.7
$0.06$0.370.268¢31,6281.05M
8GPT-5.5openai
84.1
$0.188$1.130.821¢10,2401.05M
9Grok 4.5xai
83.3
$2$6$0.0431,9231M
10DeepSeek V4 Flash 0731deepseek
82.7
$0.035$0.070.060¢138,3411.31M
11GLM-5.2zhipuai
82.7
$0.3$1.050.729¢11,3441.05M
12Claude Sonnet 5anthropic
80.4
$1.44$7.20$0.0561,4391M
13Muse Spark 1.1meta
80
$1.25$4.25$0.0292,7341.05M
14Gemini 3.6 Flashgoogle
78
$0.375$1.88$0.0117,0411.05M
15Gemini 3.5 Flashgoogle
76.2
$0.186$1.110.813¢9,3681.05M
16Claude Opus 4.8anthropic
74.6
$0.425$2.13$0.0164,5241.05M
17Claude Opus 4.7anthropic
73.8
$4$20$0.0671,1051.05M
18LongCat-2.0meituan
70.8
$0.3$1.200.767¢9,2301.05M
19Claude Opus 4.6anthropic
70.2
$4$20$0.0671,0521M
20GPT-5.4openai
69.8
$0.75$6$0.0352,0131.05M
1–20 of 37 models

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

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