Overall AI model intelligence rankings
Compare the strongest models by AskClash's weighted public benchmark score.
AskClash model intelligence
AI Model Benchmarks
Compare AI model benchmark scores, intelligence, coding performance, open-weight models, and API pricing with clear, shareable charts.
AI benchmark charts worth sharing
The interactive library turns the current AskClash model snapshot into practical comparisons for choosing a model by capability, cost, and workflow.
AI intelligence vs. cost
See which models combine high benchmark scores with lower blended input and output token prices.
GPT-5.6 vs. the frontier
Compare GPT-5.6 Sol, Terra, and Luna with GPT-5.5, Claude, Grok, and Gemini on intelligence and API cost.
Open-weight AI model leaders
Explore the strongest openly weighted models in the current benchmark snapshot.
Proprietary frontier AI models
Compare leading closed and hosted AI models by public benchmark score.
AI coding and agent benchmarks
Compare SWE-bench, Terminal-Bench, and Coding Agent Index performance.
AI reasoning and knowledge benchmarks
Compare GPQA, HLE, and AAII signals for difficult reasoning and knowledge work.
AI vision and computer-use benchmarks
Compare multimodal reasoning and computer-use performance across popular models.
Best AI models under $5 per million tokens
Find high-scoring models with lower blended API pricing for production workloads.
AI model provider landscape
See average model intelligence scores and model counts by provider.
Benchmark coverage vs. score
Understand how much published benchmark coverage supports each model's score.
Frontier AI model radar
Compare headline frontier profiles across reasoning, coding, vision, agentic work, and RWT.