reasoning
Humanity's Last Exam
- #535none of 5873.9%
Leader: Opus 5.5 · 61.4%
Other · released 2025-11-27
Measured on 19 benchmarks.
General frontier
Not ranked in this mix — too little measured data for its benchmarks.
reasoning
Leader: Opus 5.5 · 61.4%
knowledge
Leader: Opus 5.5 · 46.4
agentic
Leader: GLM 5.2 · 99.1%
coding
Leader: Gemini 3 Pro · 91.7%
coding
Leader: GPT-5.6 Sol · 65.9%
coding
Leader: Fable 5.1 · 91.4%
composite
Leader: Opus 5.5 · 57.6
economics
Leader: Opus 5.5 · 1866
instruction
Leader: Grok 4.3 · 83.3%
knowledge
Leader: Fable 5.1 · 67.2%
knowledge
Leader: MiniCPM5-1B (Non-reasoning) · 99.1%
knowledge
Leader: Gemini 3.1 Pro · 93.2%
knowledge
Leader: GPT-6 Astra · 96.3%
knowledge
Leader: Gemini 3 Pro · 89.8%
long-context
Leader: Kimi K3 · 88.7%
math
Leader: GPT-5.2 · 99.0%
reasoning
Leader: Muse Wonder Full (Max) · 32.9%
speed
Leader: Gemini 2.5 Flash Lite · 0.3s
speed
Leader: Celeris-1 · 1564.1