AI Benchmark Leaderboard

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

# Model Org Intelligence ↓ CodingMathMMLU ProGPQALiveCodeBenchAIME 2025MATH 500SciCodeIFBenchHLE
476 Jamba 1.7 Mini AI21 Labs ———————————
477 Jamba Reasoning 3B AI21 Labs ———————————
478 JT-35B-Flash China Mobile ———————————
479 JT-4.1 Flash 236B A21B 0709 (Reasoning) China Mobile ———————————
480 JT-4.1 Flash 236B A21B 0709 (Non-reasoning) China Mobile ———————————
481 JT-4.1 Flash 236B A21B (Non-reasoning) China Mobile ———————————
482 JT-MINI China Mobile ———————————
483 K-EXAONE (Reasoning) LG AI Research ———————————
484 K-EXAONE (Non-reasoning) LG AI Research ———————————
485 K2 Horizon 0.9B Institute of Foundation Models ———————————
486 K2 Horizon 3.7B Institute of Foundation Models ———————————
487 K2 Horizon 7B Institute of Foundation Models ———————————
488 K2 Horizon MoVA 36B A4B Institute of Foundation Models ———————————
489 K2 Think V2 Institute of Foundation Models ———————————
490 K2-V2 (High) Institute of Foundation Models ———————————
491 K2-V2 (Low) Institute of Foundation Models ———————————
492 K2-V2 (Medium) Institute of Foundation Models ———————————
493 KAT-Coder-Pro V1 KwaiKAT ———————————
494 KAT Coder Pro V2 KwaiKAT ———————————
495 Kimi K2 Kimi ———————————
496 Kimi K2 0905 Kimi ———————————
497 Kimi K2.5 (Reasoning) Kimi ———————————
498 Kimi K2.5 (Non-reasoning) Kimi ———————————
499 Kimi K2.6 (Reasoning) Kimi ———————————
500 Kimi K2.6 (Non-reasoning) Kimi ———————————

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.