LetTokenBurnBenchHub

Model

Kimi K3

Moonshot AI · open weights

Knowledge & Reasoning

Knowledge & Reasoning

Benchmark	Score	Metric	Harness	Source	Confidence	Link
CritPt	23.4	accuracy	N/A	Independent	low	epoch.ai
GPQA Diamond	93.1	accuracy	N/A	Independent	high	epoch.ai
SimpleQA Verified	50.6	accuracy	N/A	Independent	high	epoch.ai
TasteVal	0.5	compute_multiplier	N/A	Independent	medium	arxiv.org

Math

Benchmark	Score	Metric	Harness	Source	Confidence	Link
OpenProblemBench	3.7	mean_judged_solve_rate	N/A	Independent	medium	arxiv.org

Coding

Benchmark	Score	Metric	Harness	Source	Confidence	Link
AAArena	2288.2	elo	codex	Independent	medium	arxiv.org
ArchitectureIQ	46.8	accuracy	architectureiq	Independent	medium	arxiv.org
ArrivalBench	35.2	failure_rate	N/A	Independent	medium	arxiv.org
D2K-Bench	1.4	s_perf	N/A	Independent	medium	arxiv.org
DeepSWE	68.5	pass@1	mini-swe-agent	Independent	medium	deepswe.datacurve.ai
ModeBench	0.3	pcmd	N/A	Independent	medium	arxiv.org
SciCode	59.5	score	N/A	Independent	medium	artificialanalysis.ai
TaoD2C-Bench	63.3	accuracy	N/A	Independent	medium	arxiv.org
Video2World	33.2	v2wscore	N/A	Independent	medium	arxiv.org

Agentic / Tool Use

Agentic / Tool Use

Benchmark	Score	Metric	Harness	Source	Confidence	Link
AgenticBBO-Bench	0.6	hpo	N/A	Independent	medium	arxiv.org
AgentMonBench	1.0	silentswap	N/A	Independent	medium	arxiv.org
Argo-Bench	28.4	score	N/A	Independent	medium	arxiv.org
CASE longitudinal multimodal benchmark	69.5	overall_(%)	N/A	Independent	medium	arxiv.org
cua-speedrun	79.6	success_rate	N/A	Independent	medium	arxiv.org
DataSense-Bench	36.3	accuracy	N/A	Independent	medium	arxiv.org
DUDA-Bench	0.1	workflow_score	react	Independent	medium	arxiv.org
DyadMem	74.9	accuracy	N/A	Independent	medium	arxiv.org
EngiWorld	24.1	engiscore	N/A	Independent	medium	arxiv.org
IGMBench	60.0	success_rate	N/A	Independent	medium	arxiv.org
Learn2Play Bench	59.8	max	evotest	Independent	medium	arxiv.org
Learn2Play Bench	56.6	max	reflexion	Independent	medium	arxiv.org
Learn2Play Bench	56.2	max	opencode	Independent	medium	arxiv.org
Learn2Play Bench	47.7	max	awm	Independent	medium	arxiv.org
Learn2Play Bench	47.0	max	reasoningbank	Independent	medium	arxiv.org
Learn2Play Bench	46.0	max	memory	Independent	medium	arxiv.org
Open-Endedness Bench	0.8	e4_no_reward_hacking	N/A	Independent	medium	arxiv.org
RobotWorld	2.4	success_rate	N/A	Independent	medium	arxiv.org
ServeLearnBench	51.1	accuracy	skillopt	Independent	medium	arxiv.org

Multimodal

Benchmark	Score	Metric	Harness	Source	Confidence	Link
CogEmo-Bench	39.0	m-f1	N/A	Independent	medium	arxiv.org
DSV-Mem	24.3	accuracy	N/A	Independent	medium	arxiv.org
GDP.pdf	19.0	gdp.pdf_score	N/A	Independent	medium	surgehq.ai
GeoSpatialBench	89.5	accuracy	N/A	Independent	medium	arxiv.org
PlotGround-1k	38.2	accuracy	N/A	Independent	medium	arxiv.org

Safety & Alignment

Safety & Alignment

Benchmark	Score	Metric	Harness	Source	Confidence	Link
AgentDoxx	97.2	accuracy	N/A	Independent	medium	arxiv.org
DistressBench	0.7	score	N/A	Independent	medium	arxiv.org
FIGS	54.5	automated_judge_applying_a_10-rule_taxonomy_separating_sycophancy_from_calibrated_validation	N/A	Independent	medium	arxiv.org
Nonpublic Vulnerabilities Benchmark	0.5	attack_score	opencode	Independent	medium	arxiv.org
ObligationBench	31.0	recall	N/A	Independent	medium	arxiv.org

Abstract Reasoning

Abstract Reasoning

Benchmark	Score	Metric	Harness	Source	Confidence	Link
ARC-AGI-2	60.4	score	N/A	Independent	low	epoch.ai

Reproduced by the community