GPT-4o

GPT-4o is a non-reasoning model from OpenAI. 24 benchmarks count toward its score, in 7 categories.

availableShows if the model has enough results for an index.
IndexOverall score. 50 is the middle.27.6 ±3.8
CoverageShare of the index weight with results.95%
SpeedOutput tokens per second.60/s
Input / 1MUS dollars per 1M input tokens.$2.5 batch $1.25
Output / 1MUS dollars per 1M output tokens.$10 batch $5 US dollars per 1M output tokens in a batch.
ContextMaximum tokens in one request.128K
EloLMArena rating and rank.1282 (#254)

50 is the middle of the board. The range shows the doubt in the index. Batch work costs less.

45,499 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.
16.8
CodingCode writing and repair.
22.3
ReasoningLogic problems and puzzles.
38.0
MultimodalTasks with images and text.
30.0
KnowledgeFacts and expert knowledge.
32.8
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
23.9
MathMath problems.
24.4

Results

24 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.
MGSMMultilingual90.5%9 Jan 2026Vals AI
MATH 500Math74.6%25.29 Jan 2026Vals AI
MMLU ProKnowledge73.3%36.01 Sept 2026Vals AI
MMMU ProMultimodal63.1%30.01 Sept 2026Vals AI
Artificial Analysis GPQA DiamondKnowledge54.3%24.2Artificial Analysis
GPQA DiamondKnowledge52.0%26.31 Sept 2026Vals AI
MATH level 5Math51.0%23.7Epoch AI
Artificial Analysis Long Context ReasoningReasoning49.3%42.4Artificial Analysis
GPQA diamondKnowledge48.9%23.4Epoch AI
LiveCodeBenchCoding43.4%23.81 Sept 2026Vals AI
Artificial Analysis IFBenchInstruction34.3%23.9Artificial Analysis
SWE-Bench verifiedCoding31.0%22.4Epoch AI
SWE-bench LiteCoding27.8%27.0SIMA11 Sept 2025SWE-bench team
SWE-bench VerifiedCoding26.6%18.8AppMap Navie1 Sept 2026SWE-bench team
SimpleQA VerifiedKnowledge26.0%45.6Epoch AI
τ²-Bench Tool-Agent-User EvaluationAgentic25.1%16.8Victor Barres et al.
SWE-bench VerifiedCoding23.2%16.1SWE-agent26 Feb 2026SWE-bench team
SWE-bench LiteCoding21.7%21.7AppMap Navie11 Sept 2025SWE-bench team
Artificial Analysis Omniscience AccuracyKnowledge19.9%38.5Artificial Analysis
SWE-bench (full test split)Coding14.6%AppMap Navie19 Dec 2025SWE-bench team
Chess PuzzlesReasoning13.0%40.3Epoch AI
AIMEMath12.9%19.716 Apr 2026Vals AI
SWE-bench MultimodalMultimodal10.6%SWE-agent17 Nov 2025SWE-bench team
Artificial Analysis Intelligence IndexKnowledge8.4%32.9Artificial Analysis
OTIS Mock AIME 2024-2025Math6.3%15.1Epoch AI
SWE-bench MultimodalMultimodal6.0%RAG17 Nov 2025SWE-bench team
ARC-AGI-1 (semi-private)Reasoning4.5%29.3ARC Prize Foundation
Artificial Analysis Humanity's Last ExamKnowledge2.4%27.2Artificial Analysis
FrontierMath-Tiers-1-3-v2-PrivateMath0.4%31.6Epoch AI
FrontierMath-2025-02-28-PrivateMath0.3%31.0Epoch AI
Critical Physics TasksReasoning0.0%38.4Artificial Analysis
ARC-AGI-2 (semi-private)Reasoning0.0%39.7ARC Prize Foundation

24 benchmarks count, from 28 of 32 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 attributionSWE-bench team, collected directlyNo licence stated. The repository publishes submission records for reproducibility and transparency and asks that SWE-bench be citedARC 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