llm.ing

o3-mini

OpenAIArtificial Analysis ↗

Smaller o-series reasoner for economical coding, math, and planning tasks

Benchmarks

BenchmarkCategoryScoreVariantProvenanceSourceObserved
AA Agentic Indexagentic0.9high-effortindependentaaSep 7, 2026
0.9high-effortmirroropenrouterSep 8, 2026
AA Coding Indexcoding16.3high-effortmirroropenrouterJul 23, 2026
16.3high-effortindependentaaJul 24, 2026
AA Intelligence Indexintelligence11.0high-effortmirroropenrouterSep 8, 2026
11.0high-effortindependentaaSep 9, 2026
12.5—independentaaSep 9, 2026
12.5—mirroropenrouterOct 5, 2026
LMArena Textpreference1337high-effortcrowdlmarenaOct 15, 2026
1320—crowdlmarenaNov 9, 2026
Median output speedspeed216 tok/s—independentaaNov 18, 2026
251 tok/shigh-effortindependentaaNov 19, 2026
Median time to first tokenspeed6.71s—independentaaNov 18, 2026
18.41shigh-effortindependentaaNov 19, 2026

Includes index data from Artificial Analysis.

Providers

Live operational stats per hosting endpoint, via OpenRouter.

ProviderQuantContext$/1M in · outUptime 24hLatencyThroughput
OpenAI—200K$1.1 · $4.4100.00%——