Skip to content

LLM Benchmark Hub

Model evidence, daily

Models What's New Trends Benchmarks Skill Maps
How It Works Guesswork Metrics
LLM Benchmark Hub
Loading data...

SolarBench — leaderboard

Metric: Pass Rate (%). Source: solarbench.maingen.ai. 11 models tracked.

Top models

#ModelScore
1Claude Fable 553.8
2Muse Spark 1.142.5
3Grok 4.538.8
4GPT-5.6 Sol33.8
5Gemini 3.1 Pro (Preview)28.8
6Kimi K326.3
7GLM-5.223.8
8Claude Sonnet 512.5
9Gemini 3.5 Flash11.3
10GPT-5.6 Terra6.3
11Kimi K2.7 Code5

Interactive version: aibenchmarks.dev/benchmark?slug=solarbench · How the rankings work · Data refreshed daily, snapshot 2026-07-20.

Built by Mikhail Doroshenko — AI researcher, co-author of Humanity’s Last Exam. Independent project; no affiliation with any AI lab.