- Claude Opus 5 (Adaptive Reasoning, Max Effort) tops the Intelligence Index with a score of 61, out of 170 evaluated models.
- Mercury 2 is the fastest model at 938.7 tokens per second for output speed.
- Gemma 3n E4B Instruct is the most affordable at $0.02 per 1 million tokens (blended).
- Gemini 2.5 Flash-Lite (Non-reasoning) has the lowest latency at 0.35 seconds time to first token.
- GLM-5.2 (max) is the highest-ranked open weights model with an Intelligence Index score of 51.
- Models are evaluated across intelligence, pricing, speed, latency, end-to-end response time, and context window size.