The leaders, at a glance

UnifyBench ranking

Name: UnifyBench public ranking snapshot
Creator: UnifyBench
Published: 2026-09-12T08:38:19.822Z

Compare AI models and measured effort settings across published benchmarks.

See the full ranking ↓How configurations are ranked

Core work leaders

Experimental comparison score · 0–100

For the selected profile and sources. Scores are experimental; small gaps may not be meaningful. How scoring works · Effort evidence collected 2026-09-12

451unique modelsEach model counted once across effort levels 492model configurationsDocumented model + effort settings, including unranked

109aggregated sourcesOriginal reports and benchmark leaderboards

Explore all 109 sources Independent evaluations and lab reports

Distinct source pages with published results in the catalog. Multiple results and page sections count as one source.

Every ranked row is a measured configuration. The default view shows the highest-scoring supported configuration per model. In Value, the budget is applied first. Select All efforts for the full comparison. How effort ranking works.

Customize ranking

Full ranking

451 entries

Custom capability ranking of measured model configurations. Scores are experimental; missing results remain unknown.
Rank	Model	Score	Capability coverage	analyst-agent	briefcase	aime	apex-agents	aa-lcr	automationbench	critpt	enterprise-ops	gdp-pdf	gdpval	gmmlu	gpqa	harvey	hle	ifbench	itbench	livecodebench	math500	mmlu-pro	mmmu-pro	omniscience	scicode	tau-bench	terminal-bench	arc-agi	deepswe	swe-bench-pro	arc-agi-3	frontiercode	enigma-eval	swe-atlas-qna	swe-atlas-refactoring	swe-atlas-test-writing	livebench-math	livebench-coding	livebench-language	livebench-data	multi-swe-bench	livebench-reasoning	livebench-instructions	swe-rebench	epoch-game-puzzles	frontiermath	simpleqa	vals-finance-agent	vals-code-migration	vals-legal-research	vals-excel-modeling	vibe-code	chartography	osworld	charxiv	swe-bench-multilingual	deepsearchqa	officeqa	mcp-atlas	toolathlon	mrcr	browsecomp
—	GPT-5.2 · HighOpenAI Measured effort: High	—Not scored	Provisional · 66%24 published · 6 families · 3 selected capabilities	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	66.038/38 peersIndependent evidence	—	—	—	—	—	—	—	—	43.026/26 peersIndependent evidence	24.726/26 peersIndependent evidence	42.626/26 peersIndependent evidence	58.226/26 peersIndependent evidence	47.626/26 peersIndependent evidence	31.326/26 peersIndependent evidence	11.926/26 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
—	Hy3-preview · Non-reasoningTencent Measured effort: Non-reasoning	—Not scored	Provisional · 33%9 published · 5 families · 3 selected capabilities	—	—	—	—	44.7197/197 peersIndependent evidence	—	55.8200/200 peersIndependent evidence	—	—	—	—	51.6212/212 peersIndependent evidence	—	42.6208/208 peersIndependent evidence	58.8178/178 peersIndependent evidence	—	—	—	—	—	64.6198/198 peersIndependent evidence	—	63.5171/171 peersIndependent evidence	77.7169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
—	Kimi-Linear-48B-A3B-Instruct · Non-reasoningMoonshot Measured effort: Non-reasoning	—Not scored	Provisional · 66%9 published · 6 families · 3 selected capabilities	—	—	36.4108/108 peersIndependent evidence	—	31.5197/197 peersIndependent evidence	—	—	—	—	—	—	11.0212/212 peersIndependent evidence	—	0.6208/208 peersIndependent evidence	12.6178/178 peersIndependent evidence	—	37.6112/112 peersIndependent evidence	—	15.2114/114 peersIndependent evidence	—	—	—	2.2171/171 peersIndependent evidence	49.2169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
—	MiniMax-M1-40k · ReasoningMiniMax Measured effort: Reasoning	—Not scored	Provisional · 66%9 published · 7 families · 3 selected capabilities	—	—	10.7108/108 peersIndependent evidence	—	—	—	—	—	—	—	—	42.4212/212 peersIndependent evidence	—	46.0208/208 peersIndependent evidence	44.7178/178 peersIndependent evidence	—	67.6112/112 peersIndependent evidence	82.960/60 peersIndependent evidence	70.0114/114 peersIndependent evidence	—	—	—	39.6171/171 peersIndependent evidence	17.4169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
—	MiniMax-M1-80k · ReasoningMiniMax Measured effort: Reasoning	—Not scored	Provisional · 66%13 published · 8 families · 3 selected capabilities	—	—	58.5108/108 peersIndependent evidence	—	58.0197/197 peersIndependent evidence	—	25.5200/200 peersIndependent evidence	—	—	—	—	45.3212/212 peersIndependent evidence	—	47.8208/208 peersIndependent evidence	46.9178/178 peersIndependent evidence	—	76.4112/112 peersIndependent evidence	91.260/60 peersIndependent evidence	75.2114/114 peersIndependent evidence	—	62.3198/198 peersIndependent evidence	—	44.0171/171 peersIndependent evidence	20.9169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
—	MiniMax-M2 · ReasoningMiniMax Measured effort: Reasoning	—Not scored	Provisional · 66%13 published · 7 families · 3 selected capabilities	—	—	75.3108/108 peersIndependent evidence	—	66.1197/197 peersIndependent evidence	—	66.8200/200 peersIndependent evidence	—	—	—	48.263/63 peersIndependent evidence	61.9212/212 peersIndependent evidence	—	63.2208/208 peersIndependent evidence	88.1178/178 peersIndependent evidence	—	94.7112/112 peersIndependent evidence	—	78.8114/114 peersIndependent evidence	—	64.9198/198 peersIndependent evidence	—	82.2171/171 peersIndependent evidence	71.1169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
—	MiniMax-M2.1 · ReasoningMiniMax Measured effort: Reasoning	—Not scored	Provisional · 66%13 published · 7 families · 3 selected capabilities	—	—	82.6108/108 peersIndependent evidence	—	70.3197/197 peersIndependent evidence	—	56.4200/200 peersIndependent evidence	—	—	—	66.163/63 peersIndependent evidence	74.1212/212 peersIndependent evidence	—	77.4208/208 peersIndependent evidence	83.1178/178 peersIndependent evidence	—	92.8112/112 peersIndependent evidence	—	98.1114/114 peersIndependent evidence	—	59.1198/198 peersIndependent evidence	—	79.7171/171 peersIndependent evidence	75.6169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
—	MiniMax-M2.5 · ReasoningMiniMax Measured effort: Reasoning	—Not scored	Provisional · 33%10 published · 5 families · 3 selected capabilities	—	—	—	—	81.7197/197 peersIndependent evidence	—	70.7200/200 peersIndependent evidence	—	—	—	67.063/63 peersIndependent evidence	80.6212/212 peersIndependent evidence	—	74.9208/208 peersIndependent evidence	87.3178/178 peersIndependent evidence	—	—	—	—	—	73.2198/198 peersIndependent evidence	—	93.5171/171 peersIndependent evidence	85.2169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
—	Mistral Large 2 (July 2024) · Non-reasoningMistral Measured effort: Non-reasoning	—Not scored	Provisional · 33%9 published · 6 families · 3 selected capabilities	—	—	0.0108/108 peersIndependent evidence	—	12.9197/197 peersIndependent evidence	—	—	—	—	—	—	16.7212/212 peersIndependent evidence	—	2.8208/208 peersIndependent evidence	18.5178/178 peersIndependent evidence	—	19.3112/112 peersIndependent evidence	17.060/60 peersIndependent evidence	25.6114/114 peersIndependent evidence	—	—	—	42.4171/171 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
—	Mistral Medium 3 · Non-reasoningMistral Measured effort: Non-reasoning	—Not scored	Provisional · 66%14 published · 8 families · 3 selected capabilities	—	—	31.9108/108 peersIndependent evidence	—	33.0197/197 peersIndependent evidence	—	25.5200/200 peersIndependent evidence	—	—	—	—	27.0212/212 peersIndependent evidence	—	11.9208/208 peersIndependent evidence	39.9178/178 peersIndependent evidence	—	39.9112/112 peersIndependent evidence	53.260/60 peersIndependent evidence	48.4114/114 peersIndependent evidence	25.4114/114 peersIndependent evidence	45.4198/198 peersIndependent evidence	—	28.5171/171 peersIndependent evidence	24.1169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
—	Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 · ReasoningNVIDIA Measured effort: Reasoning	—Not scored	Provisional · 67%12 published · 6 families · 3 selected capabilities	—	—	—	—	41.1197/197 peersIndependent evidence	—	25.3200/200 peersIndependent evidence	—	—	21.9123/123 peersIndependent evidence	—	15.5212/212 peersIndependent evidence	—	26.3208/208 peersIndependent evidence	75.7178/178 peersIndependent evidence	—	—	—	—	25.9114/114 peersIndependent evidence	27.9198/198 peersIndependent evidence	—	53.9171/171 peersIndependent evidence	34.4201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
—	NVIDIA-Nemotron-3-Nano-4B-BF16 · ReasoningNVIDIA Measured effort: Reasoning	—Not scored	Provisional · 67%11 published · 6 families · 3 selected capabilities	—	—	—	—	27.6197/197 peersIndependent evidence	—	25.2200/200 peersIndependent evidence	—	—	8.9123/123 peersIndependent evidence	—	20.4212/212 peersIndependent evidence	—	27.1208/208 peersIndependent evidence	70.2178/178 peersIndependent evidence	—	—	—	—	—	9.6198/198 peersIndependent evidence	—	34.9171/171 peersIndependent evidence	27.5201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
—	NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 · Non-reasoningNVIDIA Measured effort: Non-reasoning	—Not scored	Provisional · 66%13 published · 7 families · 3 selected capabilities	—	—	26.0108/108 peersIndependent evidence	—	25.8197/197 peersIndependent evidence	—	25.2200/200 peersIndependent evidence	—	—	—	—	14.8212/212 peersIndependent evidence	—	17.1208/208 peersIndependent evidence	9.5178/178 peersIndependent evidence	—	30.9112/112 peersIndependent evidence	—	22.1114/114 peersIndependent evidence	13.4114/114 peersIndependent evidence	15.5198/198 peersIndependent evidence	—	17.7171/171 peersIndependent evidence	3.7169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
—	NVIDIA-Nemotron-Nano-9B-v2 · Non-reasoningNVIDIA Measured effort: Non-reasoning	—Not scored	Provisional · 66%12 published · 7 families · 3 selected capabilities	—	—	59.9108/108 peersIndependent evidence	—	28.4197/197 peersIndependent evidence	—	25.2200/200 peersIndependent evidence	—	—	—	—	23.7212/212 peersIndependent evidence	—	21.8208/208 peersIndependent evidence	10.8178/178 peersIndependent evidence	—	75.7112/112 peersIndependent evidence	—	39.2114/114 peersIndependent evidence	—	11.4198/198 peersIndependent evidence	—	26.3171/171 peersIndependent evidence	8.7169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
—	o1 · ReasoningOpenAI Measured effort: Reasoning	—Not scored	Provisional · 66%12 published · 7 families · 3 selected capabilities	—	—	—	—	67.8197/197 peersIndependent evidence	—	56.2200/200 peersIndependent evidence	—	—	—	—	55.1212/212 peersIndependent evidence	—	42.3208/208 peersIndependent evidence	83.8178/178 peersIndependent evidence	—	68.9112/112 peersIndependent evidence	80.360/60 peersIndependent evidence	88.4114/114 peersIndependent evidence	—	85.1198/198 peersIndependent evidence	—	63.7171/171 peersIndependent evidence	52.3169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
—	o3 · ReasoningOpenAI Measured effort: Reasoning	—Not scored	Provisional · 66%14 published · 8 families · 3 selected capabilities	—	—	91.5108/108 peersIndependent evidence	—	83.8197/197 peersIndependent evidence	—	70.1200/200 peersIndependent evidence	—	—	—	—	72.2212/212 peersIndependent evidence	—	73.5208/208 peersIndependent evidence	86.0178/178 peersIndependent evidence	—	91.9112/112 peersIndependent evidence	99.660/60 peersIndependent evidence	91.3114/114 peersIndependent evidence	65.0114/114 peersIndependent evidence	88.4198/198 peersIndependent evidence	—	73.3171/171 peersIndependent evidence	89.2169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
—	o4-mini · HighOpenAI Measured effort: High	—Not scored	Provisional · 66%16 published · 9 families · 3 selected capabilities	—	—	93.1108/108 peersIndependent evidence	—	56.6197/197 peersIndependent evidence	—	61.0200/200 peersIndependent evidence	—	—	—	—	61.0212/212 peersIndependent evidence	—	66.2208/208 peersIndependent evidence	80.2178/178 peersIndependent evidence	—	99.4112/112 peersIndependent evidence	97.560/60 peersIndependent evidence	85.4114/114 peersIndependent evidence	59.8114/114 peersIndependent evidence	66.1198/198 peersIndependent evidence	—	59.3171/171 peersIndependent evidence	53.7169/169 peersIndependent evidence	36.638/38 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
—	phi-4 · Non-reasoningMicrosoft Measured effort: Non-reasoning	—Not scored	Provisional · 66%13 published · 8 families · 3 selected capabilities	—	—	16.3108/108 peersIndependent evidence	—	5.6197/197 peersIndependent evidence	—	25.5200/200 peersIndependent evidence	—	—	—	—	26.3212/212 peersIndependent evidence	—	9.0208/208 peersIndependent evidence	8.0178/178 peersIndependent evidence	—	12.9112/112 peersIndependent evidence	30.860/60 peersIndependent evidence	34.6114/114 peersIndependent evidence	—	22.5198/198 peersIndependent evidence	—	2.3171/171 peersIndependent evidence	24.2169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
—	Pixtral Large · Non-reasoningMistral Measured effort: Non-reasoning	—Not scored	Provisional · 33%9 published · 6 families · 3 selected capabilities	—	—	1.7108/108 peersIndependent evidence	—	—	—	—	—	—	—	—	19.2212/212 peersIndependent evidence	—	2.0208/208 peersIndependent evidence	29.2178/178 peersIndependent evidence	—	17.3112/112 peersIndependent evidence	17.060/60 peersIndependent evidence	32.0114/114 peersIndependent evidence	20.1114/114 peersIndependent evidence	—	—	47.8171/171 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
—	Qwen3-0.6B · Non-reasoningQwen Measured effort: Non-reasoning	—Not scored	Provisional · 66%13 published · 8 families · 3 selected capabilities	—	—	7.4108/108 peersIndependent evidence	—	5.8197/197 peersIndependent evidence	—	25.2200/200 peersIndependent evidence	—	—	—	—	1.8212/212 peersIndependent evidence	—	28.0208/208 peersIndependent evidence	5.1178/178 peersIndependent evidence	—	2.6112/112 peersIndependent evidence	4.260/60 peersIndependent evidence	1.5114/114 peersIndependent evidence	—	1.3198/198 peersIndependent evidence	—	9.4171/171 peersIndependent evidence	3.3169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
—	Qwen3-1.7B · Non-reasoningQwen Measured effort: Non-reasoning	—Not scored	Provisional · 66%17 published · 9 families · 3 selected capabilities	—	—	1.8150/150 peersIndependent evidence	—	5.5197/197 peersIndependent evidence	—	25.5200/200 peersIndependent evidence	—	—	—	1.663/63 peersIndependent evidence	0.7213/213 peersIndependent evidence	—	33.1208/208 peersIndependent evidence	4.0178/178 peersIndependent evidence	—	6.1112/112 peersIndependent evidence	18.660/60 peersIndependent evidence	4.6114/114 peersIndependent evidence	—	4.3198/198 peersIndependent evidence	—	22.8171/171 peersIndependent evidence	3.3169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	6.950/50 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
—	Qwen3-235B-A22B · Non-reasoningQwen Measured effort: Non-reasoning	—Not scored	Provisional · 66%13 published · 8 families · 3 selected capabilities	—	—	21.9108/108 peersIndependent evidence	—	5.8197/197 peersIndependent evidence	—	25.2200/200 peersIndependent evidence	—	—	—	—	31.4212/212 peersIndependent evidence	—	15.4208/208 peersIndependent evidence	32.3178/178 peersIndependent evidence	—	30.2112/112 peersIndependent evidence	52.160/60 peersIndependent evidence	50.3114/114 peersIndependent evidence	—	47.8198/198 peersIndependent evidence	—	33.5171/171 peersIndependent evidence	33.2169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
—	Qwen3-235B-A22B-Instruct-2507 · Non-reasoningQwen Measured effort: Non-reasoning	—Not scored	Provisional · 66%13 published · 8 families · 3 selected capabilities	—	—	68.7108/108 peersIndependent evidence	—	37.1197/197 peersIndependent evidence	—	25.5200/200 peersIndependent evidence	—	—	—	—	57.2212/212 peersIndependent evidence	—	57.1208/208 peersIndependent evidence	57.1178/178 peersIndependent evidence	—	57.5112/112 peersIndependent evidence	91.260/60 peersIndependent evidence	82.4114/114 peersIndependent evidence	—	48.0198/198 peersIndependent evidence	—	43.3171/171 peersIndependent evidence	56.6169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
—	Qwen3-30B-A3B · Non-reasoningQwen Measured effort: Non-reasoning	—Not scored	Provisional · 66%16 published · 9 families · 3 selected capabilities	—	—	13.9150/150 peersIndependent evidence	—	5.6197/197 peersIndependent evidence	—	25.5200/200 peersIndependent evidence	—	—	—	—	14.7213/213 peersIndependent evidence	—	23.3208/208 peersIndependent evidence	20.4178/178 peersIndependent evidence	—	29.3112/112 peersIndependent evidence	42.360/60 peersIndependent evidence	34.1114/114 peersIndependent evidence	—	15.1198/198 peersIndependent evidence	—	25.0171/171 peersIndependent evidence	38.9169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	20.150/50 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
—	Qwen3-30B-A3B-Instruct-2507 · Non-reasoningQwen Measured effort: Non-reasoning	—Not scored	Provisional · 66%14 published · 8 families · 3 selected capabilities	—	—	63.9108/108 peersIndependent evidence	—	29.5197/197 peersIndependent evidence	—	25.5200/200 peersIndependent evidence	—	—	—	18.963/63 peersIndependent evidence	35.7212/212 peersIndependent evidence	—	41.4208/208 peersIndependent evidence	24.3178/178 peersIndependent evidence	—	55.8112/112 peersIndependent evidence	84.460/60 peersIndependent evidence	56.4114/114 peersIndependent evidence	—	26.4198/198 peersIndependent evidence	—	7.9171/171 peersIndependent evidence	34.2169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—

Behind the ranking

273 entries with published results · 112 ranked · 0 provisional estimates.

Explore seven capabilities, the original results, and gaps in the evidence.

Coding ranking Reasoning ranking Agentic ranking Compare capabilities ↗Published benchmarks ↗Evidence coverage ↗

Cite this ranking

Include the model and effort setting, the selected profile, and the dated data downloads. A shared link uses the latest data; it does not freeze a ranking in time.

UnifyBench ranking
Data updated: 12 Sept 2026
Mode: custom; evidence: documented; configurations: best
Weights: v3;agentic:34,hard_reasoning:33,coding:33,human_pref:0,knowledge:0,multimodal:0,long_context:0
https://unifybench.ai/?mode=custom&page=7&w=v3

Catalog data · Effort measurements · Configuration scoring rules · Methodology

Catalog dated 12 Sept 2026. Effort evidence collected 12 Sept 2026. Collection dates are not evaluation dates.

What does the score mean?

The adjusted comparison score estimates performance against the same reference panel from matched published comparisons. Capability pools matched comparisons across families and checks aggregate breadth and independent corroboration. Custom profiles require support in every selected capability. Missing results never count as losses.

Family details show observed win shares against available reference peers. Those descriptive values are supporting evidence, not adjusted capability scores. Provider reports and independent results remain labeled. Matching reported settings do not establish equal inference effort, and score differences do not establish statistical significance.

Read the full methodology →