cd /news/artificial-intelligence/was-lucky-to-have-tested-fable-5-on-… · home › topics › artificial-intelligence › article
[ARTICLE · art-35005] src=chess-bench.com ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

Was lucky to have tested fable 5 on chess-bench

A new chess benchmark, chess-bench, ranks AI models by performance, with Gemini 3.5 Flash leading at 61.3%, followed by Grok 4.1 Fast at 58.7% and Gemini 3.1 Pro Preview at 55.3%. The test included Claude Fable 5, which scored 46.0%, ranking ninth. The benchmark highlights significant performance gaps among leading AI models.

read1 min views1 publishedJun 20, 2026
Rank
#1 Gemini 3.5 Flash 61.3%
#2 Grok 4.1 Fast 58.7%
#3 Gemini 3.1 Pro Preview 55.3%
#4 Grok 4.20 54.7%
#5 Grok 4.20 Beta 53.3%
#6 Grok 4.3 48.7%
#7 Gemini 3 Flash Preview 48.7%
#8 Gemini 3.1 Flash Image Preview 46.0%
#9 Claude Fable 5 46.0%
#10 GPT-5.4 32.7%
#11 GPT-5.5 29.3%
#12 Qwen 3.6 Plus 28.0%
#13 Claude Opus 4.8 24.0%
#14 Qwen 3.6 Plus Preview 22.0%
#15 Claude Opus 4.7 18.7%
#16 Claude Opus 4.6 16.7%
#17 GLM 5.2 13.3%
#18 GLM-5.1 12.7%
#19 GLM-5 12.0%
#20 Claude Sonnet 4.6 10.7%
#21 Claude Haiku 4.5 8.7%
#22 Gemini 2.5 Pro 5.3%
source & further reading
chess-bench.com — original article
── more in #artificial-intelligence 4 stories · sorted by recency
── more on @gemini 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/was-lucky-to-have-te…] indexed:0 read:1min 2026-06-20 · —