Phi-4

MicrosoftReleased 12 Dec 2024Open

Compare

112100–124Index score#153 of 229 models

1/ 8Core tests taken1 of 6 areas · plus 5 anchor tests

−24Versus the frontier at releasebest then: o1

$0.070/ $0.14Price per million tokensinput / output, list price

16KContext windowtokens it reads at once

Where it sitson the frontier

o1-mini reached this score 3 months earlier.

Test resultsby area · tick = best by any model

Reasoning & knowledgeevidence

GPQA Diamond

56%

Humanity's Last Exam

no result

Mathsevidence

FrontierMath T1-3

no result

Codingno evidence yet

SWE-bench Verified

no result

Terminal-Bench

no result

Agentsevidence

APEX-Agents

no result

Novel problemsno evidence yet

ARC-AGI-2

no result

Long tasksno evidence yet

METR time horizon

no result

Independent results from the Epoch AI benchmarking hub, best reasoning setting. The core tests are shown here; anchor tests also inform the score and can be shown above.

What others sayrank on each leaderboard

The Model Indexindependent tests, our method#153of 219 · 112

Epoch Capabilities Indexoverall capability from many benchmarks#134of 239 · 130.4 LMArena · Mathsmaths questions in chat#259of 373 · 1265 LMArena · Codingcoding questions in chat#280of 383 · 1306 LMArena · Textoverall chat quality, judged by people#293of 388 · 1256 LMArena · Creative writingcreative writing#292of 386 · 1210 Artificial Analysis Intelligence Indexoverall capability across ten evaluations#177of 207 · 6

Further left is better. Leaderboards measure different things: LMArena is people voting blind between two answers, the others are test scores. Click any row for the source.