AI Benchmark Leaderboard

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

# Model Org Intelligence ↓ CodingMathMMLU ProGPQALiveCodeBenchAIME 2025MATH 500SciCodeIFBenchHLE
526 Llama 2 Chat 70B Meta ———————————
527 Llama 2 Chat 7B Meta ———————————
528 Llama 3.1 Instruct 405B Meta ———————————
529 Llama 3.1 Instruct 70B Meta ———————————
530 Llama 3.1 Instruct 8B Meta ———————————
531 Llama 3.1 Nemotron Instruct 70B NVIDIA ———————————
532 Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning) NVIDIA ———————————
533 Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) NVIDIA ———————————
534 Llama 3.2 Instruct 11B (Vision) Meta ———————————
535 Llama 3.2 Instruct 1B Meta ———————————
536 Llama 3.2 Instruct 3B Meta ———————————
537 Llama 3.2 Instruct 90B (Vision) Meta ———————————
538 Llama 3.3 Instruct 70B Meta ———————————
539 Llama 3.3 Nemotron Super 49B v1 (Non-reasoning) NVIDIA ———————————
540 Llama 3.3 Nemotron Super 49B v1 (Reasoning) NVIDIA ———————————
541 Llama 3 Instruct 70B Meta ———————————
542 Llama 3 Instruct 8B Meta ———————————
543 Llama 4 Maverick Meta ———————————
544 Llama 4 Scout Meta ———————————
545 Llama 65B Meta ———————————
546 Llama Nemotron Super 49B v1.5 (Non-reasoning) NVIDIA ———————————
547 Llama Nemotron Super 49B v1.5 (Reasoning) NVIDIA ———————————
548 LongCat 2.0 LongCat ———————————
549 LongCat Flash Lite LongCat ———————————
550 Magistral Medium 1 Mistral ———————————

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.