benchmark
.
space
benchmarks
rankings
compare
voices
transcripts
papers
articles
Toolathlon-Verified leaderboard
Toolathlon-Verified
7 models tested · Updated 2026-06-09 · Verified sources only
Claude Fable 5
leads at
77.9%
1
Claude Fable 5
Anthropic ·
Blog/Anthropic
· 2026-06-09
Score as cited in Kimi K3 blog (source: Anthropic official). Fable 5 hit fallbacks on 35% of tasks.
77.9%
2
Claude Opus 4.8
Anthropic ·
Blog/Anthropic
· 2026-06-17
Score as cited in Kimi K3 blog (source: Anthropic official).
76.2%
3
GPT-5.6 Sol
OpenAI ·
Blog/OpenAI
· 2026-07-09
Score as cited in Kimi K3 blog (source: OpenAI official).
74.9%
4
GPT-5.5
OpenAI ·
Blog/OpenAI
· 2026-06-26
Score as cited in Kimi K3 blog (source: OpenAI official).
73.5%
5
Kimi K3
Moonshot AI ·
Blog/Moonshot AI
· 2026-07-16
73.2%
6
GLM-5.2
Z.ai ·
Blog/Z.ai
· 2026-06-13
Score as cited in Kimi K3 blog (source: Z.ai official).
59.9%
7
Inkling
Thinking Machines Lab ·
Blog/Thinking Machines Lab
· 2026-07-20
Agentic tool use; below GLM-5.2 (59.9) and Fable 5 (76.4). Open-weights base.
45.5%