LetTokenBurnBenchHub

Model

Claude Sonnet 5

Anthropic · closed weights

Knowledge & Reasoning

Knowledge & Reasoning

Benchmark	Score	Metric	Harness	Source	Confidence	Link
ArcticAbstain	49.8	abstention_rate	N/A	Independent	medium	arxiv.org
CritPt	16.9	accuracy	N/A	Independent	low	epoch.ai
GPQA Diamond	90.5	accuracy	N/A	Independent	high	epoch.ai
HouseholdBench	0.9	relmae	N/A	Independent	medium	arxiv.org
MechHypoBench	43.7	mca_(%)	claude code	Independent	medium	arxiv.org
MOF-VERIFY	62.8	macro-f1	N/A	Independent	medium	arxiv.org
SimpleQA Verified	33.7	accuracy	N/A	Independent	high	epoch.ai

Math

Benchmark	Score	Metric	Harness	Source	Confidence	Link
Australian SOC Benchmark	76.7	t2_accuracy	N/A	Independent	medium	arxiv.org

Coding

Benchmark	Score	Metric	Harness	Source	Confidence	Link
ANCHOR	52.6	accuracy	N/A	Independent	medium	arxiv.org
ArchitectureIQ	44.0	accuracy	architectureiq	Independent	medium	arxiv.org
ArrivalBench	48.2	failure_rate	N/A	Independent	medium	arxiv.org
DeepSWE	53.8	pass@1	mini-swe-agent	Independent	medium	deepswe.datacurve.ai
E2E-SWE	43.1	pass@1	N/A	Independent	medium	arxiv.org
GSO	37.3	score_opt@1	OpenHands	Independent	medium	gso-bench.github.io
ParanoiaEval	22.2	violation_rate	N/A	Independent	medium	arxiv.org
PLCWorld	50.9	success_rate	N/A	Independent	medium	arxiv.org
SciCode	53.6	score	N/A	Independent	medium	artificialanalysis.ai
TaoD2C-Bench	59.9	accuracy	N/A	Independent	medium	arxiv.org

Agentic / Tool Use

Agentic / Tool Use

Benchmark	Score	Metric	Harness	Source	Confidence	Link
AgentMonBench	0.8	silentswap	N/A	Independent	medium	arxiv.org
Argo-Bench	17.3	score	N/A	Independent	medium	arxiv.org
BOTTLED	0.2	f1	N/A	Independent	medium	arxiv.org
DelegationBench	68.7	accuracy	N/A	Independent	medium	arxiv.org
DrugTargetWorld	21.3	score	N/A	Independent	medium	arxiv.org
DUDA-Bench	0.1	workflow_score	react	Independent	medium	arxiv.org
KlinikeBench	13.8	strict_pass@1	N/A	Independent	medium	arxiv.org
MS-Eval	42.3	avg.	mad-sae (spec)	Independent	medium	arxiv.org
PhysCodeGym	0.4	s_tot	claude code	Independent	medium	arxiv.org
ToolBottleneckBench	93.1	success_rate	toolbottleneckbench	Independent	medium	arxiv.org
TrialPD-Bench	75.0	f1	N/A	Independent	medium	arxiv.org

Multimodal

Benchmark	Score	Metric	Harness	Source	Confidence	Link
ChartBmkAgent	50.7	accuracy	N/A	Independent	medium	arxiv.org
HeiCo-FOCUS	35.3	accuracy	N/A	Independent	medium	arxiv.org
InteractionBench	44.6	score	N/A	Independent	medium	arxiv.org
PlotGround-1k	55.6	accuracy	N/A	Independent	medium	arxiv.org
ProPerMem	15.0	accuracy	rag	Independent	medium	arxiv.org
RoTA-Bench	0.0	success_rate	N/A	Independent	medium	arxiv.org
SpaceCast-Bench	38.3	accuracy	N/A	Independent	medium	arxiv.org

Instruction Following

Instruction Following

Benchmark	Score	Metric	Harness	Source	Confidence	Link
Nonlinear Narrative Generation Benchmark	0.4	acc.	N/A	Independent	medium	arxiv.org

Safety & Alignment

Safety & Alignment

Benchmark	Score	Metric	Harness	Source	Confidence	Link
APEX-Harm	0.0	success_rate	N/A	Independent	medium	arxiv.org
BrowseSafe++	88.2	f1	N/A	Independent	medium	arxiv.org
DecepEval	36.2	deception_rate	N/A	Independent	medium	arxiv.org
ImpactBench	73.0	impactbench_pos._(%)	N/A	Independent	medium	arxiv.org
LinguaGuardBench	1.7	flip_rate	N/A	Independent	medium	arxiv.org
RobustReview	0.6	joint_stability-discrimination_profile_and_human_alignment_scores	N/A	Independent	medium	arxiv.org

Abstract Reasoning

Abstract Reasoning

Benchmark	Score	Metric	Harness	Source	Confidence	Link
Actionable Indeterminacy Benchmark	87.3	accuracy	N/A	Independent	medium	arxiv.org
Grid-Bench	90.5	accuracy	N/A	Independent	medium	arxiv.org

Reproduced by the community