Agent Arena - Confirmed Success: leaderboard

Agent Arena submetric focused on real-world agent sessions that end in confirmed successful completion.

Metric: Confirmed Success (%). Source: arena.ai. Saturation forecast: Around December 2027. 51 models tracked.

Top models

#ModelScoreOverall rank
1Claude Opus 5.5 (Max)17.29#3 (Claude Opus 5.5)
2Claude Fable 5.1 (Max)16.19#9 (Claude Fable 5.1)
3Claude Sonnet 5.5 (Max)15.83#11 (Claude Sonnet 5.5)
4Gemini 4 Argon (High)15.64#8 (Gemini 4 Argon)
5GPT-6.1 Sol (Max)14.74#7 (GPT-6.1 Sol)
6GPT-6 Astra (Max)12.13#6 (GPT-6 Astra)
7Claude Opus 5 (Max)10.42#12 (Claude Opus 5)
8MiMo-V2.6-Pro8.03#42
9DeepSeek V4.1 Flash (Max)7.44#36 (DeepSeek V4.1 Flash)
10GPT-6 Sol (Max)6.97#14 (GPT-6 Sol)
11Kimi K3 (Max)6.46#30 (Kimi K3)
12Hy4 preview5.96#38
13Claude Fable 5 (High)5.79#16 (Claude Fable 5)
14MiMo-V2.6-Flash5.36#70
15GPT-5.6 Sol (xHigh)5.34#19 (GPT-5.6 Sol)

No result here: #10 Muse Wonder Full.

Interactive version: theaggregate.ai/benchmark?slug=agent-arena-confirmed-success · How It Works · Data refreshed daily, snapshot 2026-10-20.