Opus 5 is currently #1 on Artificial Analysis Intelligence Leaderboard
artificialanalysis.ai
July 24, 2026
3 min read
🔥🔥🔥🔥🔥
64/100
Summary
A comparison of AI models evaluates their intelligence, performance, and pricing, focusing on metrics such as output speed, latency, and context window. The analysis includes various evaluations such as agentic real-world tasks, tool use, coding capabilities, and reasoning across different domains.
Key Takeaways
- Claude Opus 5 (Adaptive Reasoning, Max Effort) has the highest score on the Artificial Analysis Intelligence Index at 61 among 170 evaluated models.
- Mercury 2 is the fastest AI model, achieving an output speed of 938.7 tokens per second.
- Nova Micro is the most affordable model, priced at $0.03 per 1 million tokens.
- Gemini 2.5 Flash-Lite has the lowest time to first token at 0.35 seconds.
Coverage & discussions
Hacker News · artificialanalysis.ai
Community discussions
Hacker News discussion ↗
Historical count: 5 · 5 saved in sample · Historical sample
Analysis ready
Community Sentiment
Positives
- 5.6 Sol being cheaper than top contenders while delivering impressive output has commenters buzzing about value in AI.
- The excitement around Opus 5's #1 ranking shows a strong belief in its capabilities, despite concerns about censorship.
Concerns
- Censorship issues are driving users away from Claude, with many feeling it's more about compliance than performance — reliability is key.
- The cost-performance ratio raises eyebrows; models matching Opus 5's score at half the price have some questioning its true value.
- Concerns about over-engineering and coding style differences suggest Opus 5 might not be the universal solution some hope it to be.
