AI Benchmark Leaderboard

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

# Model Org Intelligence ↓ CodingMathMMLU ProGPQALiveCodeBenchAIME 2025MATH 500SciCodeIFBenchHLE
401 GPT-5.6 Terra (Non-reasoning) OpenAI ———————————
402 GPT-5.6 Terra (Xhigh) OpenAI ———————————
403 GPT-5 (ChatGPT) OpenAI ———————————
404 GPT-5 Codex (High) OpenAI ———————————
405 GPT-5 (Low) OpenAI ———————————
406 GPT-5 (Medium) OpenAI ———————————
407 GPT-5 mini (High) OpenAI ———————————
408 GPT-5 mini (Medium) OpenAI ———————————
409 GPT-5 mini (Minimal) OpenAI ———————————
410 GPT-5 (Minimal) OpenAI ———————————
411 GPT-5 nano (High) OpenAI ———————————
412 GPT-5 nano (Medium) OpenAI ———————————
413 GPT-5 nano (Minimal) OpenAI ———————————
414 GPT-6 Sol (Daybreak Blue, max) OpenAI ———————————
415 GPT-6 Sol (High) OpenAI ———————————
416 GPT-6 Sol (Low) OpenAI ———————————
417 GPT-6 Sol (Medium) OpenAI ———————————
418 GPT-6 Sol (Non-reasoning) OpenAI ———————————
419 GPT-6 Sol (Xhigh) OpenAI ———————————
420 gpt-oss-120b (Low) OpenAI ———————————
421 gpt-oss-20b (High) OpenAI ———————————
422 gpt-oss-20b (Low) OpenAI ———————————
423 Granite 3.3 8B (Non-reasoning) IBM ———————————
424 Granite 4.0 350M IBM ———————————
425 Granite 4.0 H 350M IBM ———————————

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.