o4-mini Medium

Released2025-04-16
Price per 1M$1.10 in · $4.40 out
Overall score49.5 · rank 276
Context window200,000 tokens
ProviderOpenAI
WeightsProprietary
ConfigurationMedium

Scores

DimensionScoreRankBenchmarks
Overall: Balanced 49.5 276 12
Overall: Coding 49.3 271 6
Overall: Reasoning 49.3 273 9
Overall: Agentic work 49.3 280 6
Overall: Frontend 52.9 181 2
Agents 49.3 202 1
Reasoning 49.4 273 5
Math 50.1 177 3
Knowledge 47.9 143 1
Multimodal 52.9 96 2
Value vs price−2.5277

Evidence

Agents 49.3 ±3.3

BenchmarkResultSourceDate
METR task suite 63.9% Epoch AI 2026-11-11

Reasoning 49.4 ±2.1

BenchmarkResultSourceDate
GPQA Diamond 77.8% Epoch AI 2026-08-07
ARC-AGI-2 2.4% Epoch AI 2026-11-11
ARC-AGI-2 (ARC Prize verified) 2.4% ARC Prize 2026-11-11
ARC-AGI-1 (ARC Prize verified) 41.8% ARC Prize 2026-11-11
ARC-AGI-1 41.8% Epoch AI 2026-11-11
EnigmaEval 6.8% Epoch AI 2026-11-11
Chess Puzzles 22.0% Epoch AI 2026-10-13

Math 50.1 ±2.1

BenchmarkResultSourceDate
FrontierMath Tier 4 (2025 set) 2.1% Epoch AI 2025-08-07
OTIS Mock AIME 2024-2025 73.3% Epoch AI 2026-08-07
FrontierMath Tiers 1-3 28.8% Epoch AI 2026-08-27
FrontierMath Tiers 1-3 (2025 set) 19.0% Epoch AI 2025-11-13

Knowledge 47.9 ±1.3

BenchmarkResultSourceDate
Humanity's Last Exam 14.3% Epoch AI 2026-11-11

Multimodal 52.9 ±5.1

BenchmarkResultSourceDate
VPCT 57.5% Epoch AI 2026-11-11
GeoBench 64.0% Epoch AI 2026-11-11

Names matched to this model

o4-mini-medium

Compare o4-mini Medium with other models