llmboard.aiLeaderboard Center
Overall
Overall RankingOpen Models
Tools
Model DirectoryCompare Models
Capabilities
CodingReasoningMathKnowledgeInstruction Following
Price & Efficiency
Price & ValueCapability vs. PriceRuntime Performance
Modalities
Image GenerationVideo GenerationSpeech ModelsEmbeddings
Core Benchmarks
GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-ProView all benchmarks
Methods
Scoring & Data
393 models668 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll BenchmarksReasoningMath

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai

Benchmark category

Reasoning Benchmarks

Reasoning evaluations, model coverage and rankings. Each benchmark keeps its original scale and methodology.

Data as of 2026-08-11

Benchmarks420
Highest coverage234
Score eligible228

Reasoning Benchmark Directory

Select a benchmark to inspect model results, evidence fields and scoring direction.

99 rows
Columns

Show columns

GPQAGPQAtextScore234featuredCYes
MMLU-ProMMLU-ProtextScore129featuredBYes
AIME 2025AIME 2025textScore114featuredCYes
SWE-Bench VerifiedSWE-Bench VerifiedtextScore105featuredCYes
MMLUMMLUtextScore100featuredBYes
Humanity's Last ExamHumanity's Last ExammultimodalScore93featuredBYes
LiveCodeBenchLiveCodeBenchtextScore73featuredCYes
MATHMATHtextScore71featuredBYes
HumanEvalHumanEvaltextScore66featuredBYes
MMMU-ProMMMU-PromultimodalScore66featuredBYes
MMMUMMMUmultimodalScore63featuredBYes
BrowseCompBrowseComptextScore58featuredBYes
AIME 2024AIME 2024textScore53featuredBYes
LiveCodeBench v6LiveCodeBench v6textScore53featuredBYes
MMMLUMMMLUtextScore49featuredBYes
Terminal-Bench 2.0Terminal-Bench 2.0textScore49featuredCYes
CharXiv-RCharXiv-RmultimodalScore48featuredBYes
GSM8kGSM8ktextScore48featuredBYes
MMLU-ReduxMMLU-ReduxtextScore48featuredBYes
SimpleQASimpleQAtextScore46featuredBYes
SWE-Bench ProSWE-Bench ProtextScore45featuredBYes
LiveBenchLiveBenchtextScore38featuredBYes
Tau2 TelecomTau2 TelecomtextScore35featuredBYes
ARC-CARC-CtextScore34featuredBYes
SuperGPQASuperGPQAtextScore34featuredBYes
SWE-bench MultilingualSWE-bench MultilingualtextScore34featuredBYes
MBPPMBPPtextPass@133featuredBYes
AI2DAI2DmultimodalScore32featuredBYes
MATH-500MATH-500textScore32featuredCYes
MMLU-ProXMMLU-ProXtextScore32featuredBYes
MCP AtlasMCP AtlastextScore31featuredBYes
MGSMMGSMtextScore31featuredBYes
ToolathlonToolathlontextScore31featuredBYes
DROPDROPtextScore30featuredBYes
Multi-ChallengeMulti-ChallengetextScore29featuredCYes
HellaSwagHellaSwagtextScore27featuredBYes
Arena HardArena HardtextScore26featuredBYes
Finance Agent v2Finance Agent v2textScore26featuredBYes
Tau2 RetailTau2 RetailtextScore26featuredBYes
VideoMMMUVideoMMMUmultimodalScore26featuredBYes
TAU-bench RetailTAU-bench RetailtextScore25featuredBYes
Terminal-BenchTerminal-BenchtextScore25featuredBYes
ChartQAChartQAmultimodalScore24featuredBYes
ERQAERQAmultimodalScore23featuredCYes
PolyMATHPolyMATHmultimodalScore23featuredBYes
t2-bencht2-benchtextScore23featuredBYes
TAU-bench AirlineTAU-bench AirlinetextScore23featuredBYes
Tau2 AirlineTau2 AirlinetextScore23featuredBYes
MMStarMMStarmultimodalScore22featuredBYes
WinograndeWinograndetextScore22featuredBYes
BIG-Bench HardBIG-Bench HardtextScore21featuredBYes
MRCR v2 (8-needle)MRCR v2 (8-needle)textScore21featuredCYes
Multi-IFMulti-IFtextScore20featuredBYes
BFCL-v3BFCL-v3textScore19featuredBYes
IMO-AnswerBenchIMO-AnswerBenchtextScore19featuredBYes
SciCodeSciCodetextScore19featuredBYes
Terminal-Bench 2.1Terminal-Bench 2.1textScore19featuredBYes
AIME 2026AIME 2026textScore18featuredBYes
C-EvalC-EvaltextScore18featuredBYes
MMBench-V1.1MMBench-V1.1multimodalScore18featuredBYes
TriviaQATriviaQAtextScore18featuredBYes
TruthfulQATruthfulQAtextScore18featuredBYes
FrontierMathFrontierMathtextScore17featuredBYes
LongBench v2LongBench v2textScore17featuredCYes
MVBenchMVBenchmultimodalScore17featuredBYes
OmniDocBench 1.5OmniDocBench 1.5multimodalScore17featuredBYes
Video-MMEVideo-MMEmultimodalScore17featuredBYes
AA-LCRAA-LCRtextScore16featuredBYes
ARC-AGI v2ARC-AGI v2multimodalScore16featuredBYes
Arena-Hard v2Arena-Hard v2textScore16featuredBYes
CharXiv-DCharXiv-DmultimodalScore16featuredBYes
CodeForcesCodeForcestextNormalized rating16featuredBYes
Hallusion BenchHallusion BenchmultimodalScore16featuredBYes
FrontierCode 1.1FrontierCode 1.1textScore15featuredBYes
Global-MMLU-LiteGlobal-MMLU-LitetextScore14featuredBYes
LiveBench 20241125LiveBench 20241125textScore14featuredBYes
BLINKBLINKmultimodalScore13featuredBYes
BrowseComp-zhBrowseComp-zhtextScore13featuredBYes
FACTS GroundingFACTS GroundingtextScore13featuredCYes
Global PIQAGlobal PIQAtextScore13featuredBYes
HiddenMathHiddenMathtextScore13featuredBYes
Legal Agent BenchmarkLegal Agent BenchmarktextScore13featuredBYes
BBHBBHtextScore12featuredBYes
MedXpertQAMedXpertQAmultimodalScore12featuredBYes
MT-BenchMT-BenchtextNormalized score12featuredBYes
BFCLBFCLtextScore11featuredBYes
BIG-Bench Extra HardBIG-Bench Extra HardtextScore11featuredBYes
Graphwalks BFS <128kGraphwalks BFS <128ktextScore11featuredBYes
Graphwalks BFS >128kGraphwalks BFS >128ktextScore11featuredBYes
Graphwalks parents <128kGraphwalks parents <128ktextScore11featuredBYes
HMMT Feb 26HMMT Feb 26textScore11featuredBYes
MMMU (val)MMMU (val)multimodalScore11featuredBYes
MuirBenchMuirBenchmultimodalScore11featuredBYes
PIQAPIQAtextScore11featuredBYes
AGIEvalAGIEvaltextScore10featuredBYes
BoolQBoolQtextScore10featuredBYes
COLLIECOLLIEtextScore10featuredBYes
HumanEval+HumanEval+textScore10featuredBYes
VITA-BenchVITA-BenchtextScore10featuredBYes

Reasoning Benchmark Rankings

Leading results from high-coverage benchmarks with at least two models.

GPQA

View benchmark

MMLU-Pro

View benchmark

AIME 2025

View benchmark

SWE-Bench Verified

View benchmark

What are reasoning benchmarks?

How this category is assembled on llmboard.ai.

This page groups benchmarks whose primary or display category matches reasoning. It does not average incompatible metrics into a new category score.

Open an individual benchmark to inspect score direction, evidence level, participant count and model results.

Benchmarks are grouped by their primary and display categories.