AI Benchmark Leaderboard

Compare AI model scores, coding ability and performance in one place.

# Model Org Intelligence ↓ CodingMathMMLU ProGPQALiveCodeBenchAIME 2025MATH 500SciCodeIFBenchHLE
676 Qwen3 235B A22B (Reasoning) Alibaba ———————————
677 Qwen3 30B A3B 2507 Instruct Alibaba ———————————
678 Qwen3 30B A3B 2507 (Reasoning) Alibaba ———————————
679 Qwen3 30B A3B (Non-reasoning) Alibaba ———————————
680 Qwen3 30B A3B (Reasoning) Alibaba ———————————
681 Qwen3 32B (Non-reasoning) Alibaba ———————————
682 Qwen3 32B (Reasoning) Alibaba ———————————
683 Qwen3 4B 2507 Instruct Alibaba ———————————
684 Qwen3 4B 2507 (Reasoning) Alibaba ———————————
685 Qwen3 4B (Non-reasoning) Alibaba ———————————
686 Qwen3 4B (Reasoning) Alibaba ———————————
687 Qwen3.5 0.8B (Reasoning) Alibaba ———————————
688 Qwen3.5 0.8B (Non-reasoning) Alibaba ———————————
689 Qwen3.5 122B A10B (Reasoning) Alibaba ———————————
690 Qwen3.5 122B A10B (Non-reasoning) Alibaba ———————————
691 Qwen3.5 27B (Reasoning) Alibaba ———————————
692 Qwen3.5 27B (Non-reasoning) Alibaba ———————————
693 Qwen3.5 2B (Reasoning) Alibaba ———————————
694 Qwen3.5 2B (Non-reasoning) Alibaba ———————————
695 Qwen3.5 35B A3B (Reasoning) Alibaba ———————————
696 Qwen3.5 35B A3B (Non-reasoning) Alibaba ———————————
697 Qwen3.5 397B A17B (Reasoning) Alibaba ———————————
698 Qwen3.5 397B A17B (Non-reasoning) Alibaba ———————————
699 Qwen3.5 4B (Reasoning) Alibaba ———————————
700 Qwen3.5 4B (Non-reasoning) Alibaba ———————————

AI Benchmarks FAQ

Which AI model is best for my task?

Compare the scores most relevant to your task, then consider speed, pricing and practical requirements. A high score in one benchmark does not make a model the best choice for every use.

What does a missing benchmark score mean?

A dash means that a score is not available for that model in this table. It should not be treated as a score of zero.

How are the top models ranked?

By the intelligence index, highest first. The Top models cards show the eight highest-scoring current models, one per model family, and models with the same score share a place.

Where do the scores come from?

From independent third-party model evaluations, which Franklin AI syncs automatically each day. Each model page links to About these benchmarks, which explains them in more detail.

What does a model page show?

Its scores, its price per million input and output tokens, its measured speed and comparisons with other models, where that data is available.