GPT-4o mini

GPT-4o mini is a non-reasoning model from OpenAI in the GPT-4o family. 20 benchmarks count toward its score, in 7 categories.

availableShows if the model has enough results for an index.
IndexOverall score. 50 is the middle.24.1 ±4.1
CoverageShare of the index weight with results.95%
SpeedOutput tokens per second.43/s
Input / 1MUS dollars per 1M input tokens.$0.15
Output / 1MUS dollars per 1M output tokens.$0.6
ContextMaximum tokens in one request.128K
EloLMArena rating and rank.1286 (#249)

50 is the middle of the board. The range shows the doubt in the index.

68,697 votes. Elo shows what people prefer. It does not change the score.

CapabilitiesScore per category. 50 is the middle.

50 is the middle
AgenticMulti-step tasks with tools.
35.6
CodingCode writing and repair.
17.7
ReasoningLogic problems and puzzles.
36.6
MultimodalTasks with images and text.
18.6
KnowledgeFacts and expert knowledge.
22.8
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
20.6
MathMath problems.
22.8

Results

20 counted
BenchmarkThe test name.CategoryThe capability that the test measures.ResultThe score from the publisher.IndexThis result on the index scale.RunThe settings of the run.DateDate of the result.Published byThe source of the result.
MGSMMultilingual86.2%9 Jan 2026Vals AI
MATH 500Math72.6%23.09 Jan 2026Vals AI
MMLU ProKnowledge62.7%19.31 Sept 2026Vals AI
MMMU ProMultimodal56.6%19.41 Sept 2026Vals AI
MATH level 5Math52.6%24.5Epoch AI
GPQA DiamondKnowledge44.2%19.01 Sept 2026Vals AI
Artificial Analysis GPQA DiamondKnowledge42.6%12.2Artificial Analysis
Artificial Analysis MMMU-ProMultimodal41.5%17.8Artificial Analysis
GPQA diamondKnowledge37.7%13.1Epoch AI
Artificial Analysis IFBenchInstruction31.0%20.6Artificial Analysis
LiveCodeBenchCoding26.4%8.41 Sept 2026Vals AI
Mystery Game PuzzlesReasoning12.0%46.7Epoch AI
AIMEMath11.5%19.016 Apr 2026Vals AI
Artificial Analysis Coding IndexCoding11.4%27.0Artificial Analysis
SimpleQA VerifiedKnowledge8.3%29.2Epoch AI
OTIS Mock AIME 2024-2025Math6.9%15.5Epoch AI
Artificial Analysis Intelligence IndexKnowledge6.7%30.7Artificial Analysis
Artificial Analysis Humanity's Last ExamKnowledge4.2%29.1Artificial Analysis
FrontierMath-Tiers-1-3-v2-PrivateMath0.7%31.8Epoch AI
GDPval-AA normalizedAgentic0.0%35.6Artificial Analysis
ARC-AGI-2 (semi-private)Reasoning0.0%39.7ARC Prize Foundation
Chess PuzzlesReasoning0.0%23.5Epoch AI

20 benchmarks count, from 21 of 22 results. A grey row does not count. Too few models took that benchmark.

Sources

BenchLM benchmark aggregationUsed with attribution; per-benchmark results credited to their original authorsOpenRouter, collected directlyNo licence statedVals AI, collected directlyNo licence stated. Read from the public leaderboard and credited to Vals AIEpoch AI, collected directlyCC BY — free to use and redistribute with attributionARC Prize Foundation, collected directlyNo licence stated. Their terms ask for written permission before commercial use

Same level, lower price

Qwen3.8-Flash-Next66.4 · Freedots3-note Preview65.5 · FreeApodex 1.1 Mini59.1 · Free

More from OpenAI

GPT-6 Astra83.5GPT-5.6 Sol76.7GPT-5.6 Terra73.4GPT-6 Sol76.9GPT-5.572.3