AI Benchmark Leaderboard

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

# Model Org Intelligence ↓ CodingMathMMLU ProGPQALiveCodeBenchAIME 2025MATH 500SciCodeIFBenchHLE
276 Gemini 2.0 Flash Thinking Experimental (Jan '25) Google ———————————
277 Gemini 2.0 Flash Thinking Experimental (Dec '24) Google ———————————
278 Gemini 2.0 Pro Experimental (Feb '25) Google ———————————
279 Gemini 2.5 Flash (Non-reasoning) Google ———————————
280 Gemini 2.5 Flash Preview (Non-reasoning) Google ———————————
281 Gemini 2.5 Flash-Lite (Non-reasoning) Google ———————————
282 Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) Google ———————————
283 Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) Google ———————————
284 Gemini 2.5 Flash-Lite (Reasoning) Google ———————————
285 Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning) Google ———————————
286 Gemini 2.5 Flash Preview (Sep '25) (Reasoning) Google ———————————
287 Gemini 2.5 Flash (Reasoning) Google ———————————
288 Gemini 2.5 Flash Preview (Reasoning) Google ———————————
289 Gemini 2.5 Pro Google ———————————
290 Gemini 2.5 Pro Preview (Mar' 25) Google ———————————
291 Gemini 2.5 Pro Preview (May' 25) Google ———————————
292 Gemini 3.1 Pro Preview Google ———————————
293 Gemini 3.5 Flash (High) Google ———————————
294 Gemini 3.5 Flash (Medium) Google ———————————
295 Gemini 3.5 Flash (Minimal) Google ———————————
296 Gemini 3.6 Flash (High) Google ———————————
297 Gemini 3.7 Flash (High) Google ———————————
298 Gemini 3.7 Flash (Low) Google ———————————
299 Gemini 3.7 Flash (Medium) Google ———————————
300 Gemini 3 Deep Think Google ———————————

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.