The leaders, at a glance

AI reasoning model ranking

Compare AI reasoning models and measured effort settings across published reasoning benchmarks.

See the full ranking ↓How configurations are ranked

Reasoning 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

217 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
151	Gemini 2.5 Flash-Lite · ReasoningGoogle Measured effort: Reasoning	4.1	Eligible · 100%15 published · 5 families · 1 selected capabilities	—	—	51.5108/108 peersIndependent evidence	—	42.5198/198 peersIndependent evidence	—	25.2200/200 peersIndependent evidence	—	—	—	—	33.1212/212 peersIndependent evidence	—	41.1208/208 peersIndependent evidence	60.8178/178 peersIndependent evidence	—	61.9112/112 peersIndependent evidence	79.760/60 peersIndependent evidence	46.6114/114 peersIndependent evidence	34.0114/114 peersIndependent evidence	43.9198/198 peersIndependent evidence	—	15.1171/171 peersIndependent evidence	26.8169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
152	NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 · ReasoningNVIDIA Measured effort: Reasoning	3.9	Eligible · 100%13 published · 4 families · 1 selected capabilities	—	—	73.9108/108 peersIndependent evidence	—	42.3197/197 peersIndependent evidence	—	25.2200/200 peersIndependent evidence	—	—	—	—	25.6212/212 peersIndependent evidence	—	34.2208/208 peersIndependent evidence	19.8178/178 peersIndependent evidence	—	71.9112/112 peersIndependent evidence	—	47.3114/114 peersIndependent evidence	23.9114/114 peersIndependent evidence	24.1198/198 peersIndependent evidence	—	21.2171/171 peersIndependent evidence	26.7169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
153	Gemma 4 E4B IT · Non-reasoningGoogle Measured effort: Non-reasoning	3.8	Eligible · 100%10 published · 3 families · 1 selected capabilities	—	—	—	—	28.3197/197 peersIndependent evidence	—	56.0200/200 peersIndependent evidence	—	—	—	—	23.0212/212 peersIndependent evidence	—	25.7208/208 peersIndependent evidence	42.8178/178 peersIndependent evidence	—	—	—	—	22.0114/114 peersIndependent evidence	7.4198/198 peersIndependent evidence	—	30.8171/171 peersIndependent evidence	40.7169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
154	DeepSeek-R1-0528-Qwen3-8B · ReasoningDeepSeek Measured effort: Reasoning	3.8	Eligible · 100%13 published · 5 families · 1 selected capabilities	—	—	62.3108/108 peersIndependent evidence	—	19.4197/197 peersIndependent evidence	—	25.5200/200 peersIndependent evidence	—	—	—	—	30.7212/212 peersIndependent evidence	—	36.4208/208 peersIndependent evidence	1.9178/178 peersIndependent evidence	—	53.7112/112 peersIndependent evidence	62.160/60 peersIndependent evidence	38.8114/114 peersIndependent evidence	—	15.4198/198 peersIndependent evidence	—	2.3171/171 peersIndependent evidence	12.4169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
155	DeepSeek-R1-Distill-Qwen-32B · ReasoningDeepSeek Measured effort: Reasoning	3.7	Eligible · 100%8 published · 4 families · 1 selected capabilities	—	—	61.3108/108 peersIndependent evidence	—	15.3197/197 peersIndependent evidence	—	—	—	—	—	—	31.5212/212 peersIndependent evidence	—	21.1208/208 peersIndependent evidence	6.9178/178 peersIndependent evidence	—	20.2112/112 peersIndependent evidence	68.560/60 peersIndependent evidence	39.2114/114 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
156	MiniMax-M1-40k · ReasoningMiniMax Measured effort: Reasoning	3.5	Eligible · 100%9 published · 4 families · 1 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	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
157	ERNIE-4.5-300B-A47B-PT · Non-reasoningBaidu Measured effort: Non-reasoning	3.4	Eligible · 100%12 published · 5 families · 1 selected capabilities	—	—	45.0108/108 peersIndependent evidence	—	—	—	25.4200/200 peersIndependent evidence	—	—	—	—	68.8212/212 peersIndependent evidence	—	5.1208/208 peersIndependent evidence	38.6178/178 peersIndependent evidence	—	47.3112/112 peersIndependent evidence	59.760/60 peersIndependent evidence	55.0114/114 peersIndependent evidence	—	50.9198/198 peersIndependent evidence	—	2.3171/171 peersIndependent evidence	34.3169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
158	Qwen3-14B · ReasoningQwen Measured effort: Reasoning	3.4	Eligible · 100%21 published · 5 families · 1 selected capabilities	—	3.987/87 peersIndependent evidence	54.8108/108 peersIndependent evidence	—	5.8197/197 peersIndependent evidence	3.089/89 peersIndependent evidence	25.2200/200 peersIndependent evidence	—	18.388/88 peersIndependent evidence	12.4123/123 peersIndependent evidence	—	29.7212/212 peersIndependent evidence	—	20.1208/208 peersIndependent evidence	43.7178/178 peersIndependent evidence	—	56.3112/112 peersIndependent evidence	75.660/60 peersIndependent evidence	53.4114/114 peersIndependent evidence	—	28.2198/198 peersIndependent evidence	14.291/91 peersIndependent evidence	31.9202/202 peersIndependent evidence	21.2201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
159	NVIDIA-Nemotron-Nano-9B-v2 · ReasoningNVIDIA Measured effort: Reasoning	3.3	Eligible · 100%12 published · 4 families · 1 selected capabilities	—	—	67.2108/108 peersIndependent evidence	—	28.1197/197 peersIndependent evidence	—	25.2200/200 peersIndependent evidence	—	—	—	—	24.7212/212 peersIndependent evidence	—	26.6208/208 peersIndependent evidence	11.2178/178 peersIndependent evidence	—	80.1112/112 peersIndependent evidence	—	40.9114/114 peersIndependent evidence	—	14.4198/198 peersIndependent evidence	—	23.4171/171 peersIndependent evidence	11.8169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
160	GPT-4.1 Mini · Non-reasoningOpenAI Measured effort: Non-reasoning	3.2	Eligible · 100%17 published · 5 families · 1 selected capabilities	—	—	48.3108/108 peersIndependent evidence	—	45.1197/197 peersIndependent evidence	—	25.4200/200 peersIndependent evidence	—	—	25.5123/123 peersIndependent evidence	—	37.0212/212 peersIndependent evidence	—	30.1208/208 peersIndependent evidence	37.2178/178 peersIndependent evidence	—	51.3112/112 peersIndependent evidence	56.860/60 peersIndependent evidence	57.7114/114 peersIndependent evidence	36.2114/114 peersIndependent evidence	54.3198/198 peersIndependent evidence	—	38.7202/202 peersIndependent evidence	33.6201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
161	Qwen3-Coder-480B-A35B-Instruct · Non-reasoningQwen Measured effort: Non-reasoning	3.1	Eligible · 100%13 published · 5 families · 1 selected capabilities	—	—	43.5108/108 peersIndependent evidence	—	46.8197/197 peersIndependent evidence	—	25.5200/200 peersIndependent evidence	—	—	—	—	32.3212/212 peersIndependent evidence	—	21.2208/208 peersIndependent evidence	43.9178/178 peersIndependent evidence	—	60.6112/112 peersIndependent evidence	69.860/60 peersIndependent evidence	59.1114/114 peersIndependent evidence	—	30.9198/198 peersIndependent evidence	—	53.0171/171 peersIndependent evidence	62.4169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
162	Qwen3-Omni-30B-A3B-Instruct · Non-reasoningQwen Measured effort: Non-reasoning	3.0	Eligible · 100%13 published · 4 families · 1 selected capabilities	—	—	51.3108/108 peersIndependent evidence	—	5.6197/197 peersIndependent evidence	—	25.5200/200 peersIndependent evidence	—	—	—	—	32.8212/212 peersIndependent evidence	—	24.1208/208 peersIndependent evidence	16.8178/178 peersIndependent evidence	—	44.0112/112 peersIndependent evidence	—	36.5114/114 peersIndependent evidence	29.5114/114 peersIndependent evidence	23.1198/198 peersIndependent evidence	—	14.0171/171 peersIndependent evidence	12.4169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
163	EXAONE 4.0 1.2B · ReasoningLG AI Research Measured effort: Reasoning	3.0	Eligible · 100%12 published · 4 families · 1 selected capabilities	—	—	48.7108/108 peersIndependent evidence	—	5.7197/197 peersIndependent evidence	—	25.2200/200 peersIndependent evidence	—	—	—	—	20.5212/212 peersIndependent evidence	—	37.0208/208 peersIndependent evidence	7.4178/178 peersIndependent evidence	—	55.0112/112 peersIndependent evidence	—	17.2114/114 peersIndependent evidence	—	4.0198/198 peersIndependent evidence	—	12.2171/171 peersIndependent evidence	3.3169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
164	DeepSeek-R1-Distill-Llama-70B · ReasoningDeepSeek Measured effort: Reasoning	3.0	Eligible · 100%13 published · 5 families · 1 selected capabilities	—	—	53.3108/108 peersIndependent evidence	—	15.6197/197 peersIndependent evidence	—	25.5200/200 peersIndependent evidence	—	—	—	—	10.2212/212 peersIndependent evidence	—	31.1208/208 peersIndependent evidence	10.6178/178 peersIndependent evidence	—	18.8112/112 peersIndependent evidence	65.360/60 peersIndependent evidence	62.9114/114 peersIndependent evidence	—	52.2198/198 peersIndependent evidence	—	23.8171/171 peersIndependent evidence	12.4169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
165	DeepSeek-R1-Distill-Qwen-14B · ReasoningDeepSeek Measured effort: Reasoning	2.8	Eligible · 100%8 published · 4 families · 1 selected capabilities	—	—	54.5108/108 peersIndependent evidence	—	17.0197/197 peersIndependent evidence	—	—	—	—	—	—	17.7212/212 peersIndependent evidence	—	13.2208/208 peersIndependent evidence	6.2178/178 peersIndependent evidence	—	35.5112/112 peersIndependent evidence	72.360/60 peersIndependent evidence	40.7114/114 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
166	Qwen3-VL-8B-Thinking · ReasoningQwen Measured effort: Reasoning	2.8	Eligible · 100%13 published · 4 families · 1 selected capabilities	—	—	32.8108/108 peersIndependent evidence	—	36.5197/197 peersIndependent evidence	—	56.4200/200 peersIndependent evidence	—	—	—	—	27.6212/212 peersIndependent evidence	—	10.4208/208 peersIndependent evidence	43.0178/178 peersIndependent evidence	—	34.5112/112 peersIndependent evidence	—	45.0114/114 peersIndependent evidence	32.7114/114 peersIndependent evidence	55.4198/198 peersIndependent evidence	—	25.7171/171 peersIndependent evidence	24.2169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
167	Mistral Large 3 · Non-reasoningMistral Measured effort: Non-reasoning	2.7	Eligible · 100%22 published · 4 families · 1 selected capabilities	—	22.587/87 peersIndependent evidence	41.8108/108 peersIndependent evidence	—	38.3197/197 peersIndependent evidence	27.289/89 peersIndependent evidence	25.2200/200 peersIndependent evidence	—	18.688/88 peersIndependent evidence	33.1123/123 peersIndependent evidence	46.863/63 peersIndependent evidence	41.2212/212 peersIndependent evidence	—	13.9208/208 peersIndependent evidence	30.4178/178 peersIndependent evidence	—	47.6112/112 peersIndependent evidence	—	67.9114/114 peersIndependent evidence	31.3114/114 peersIndependent evidence	69.3198/198 peersIndependent evidence	29.091/91 peersIndependent evidence	24.5202/202 peersIndependent evidence	36.3201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
168	Mistral Medium 3.1 · Non-reasoningMistral Measured effort: Non-reasoning	2.6	Eligible · 100%20 published · 4 families · 1 selected capabilities	—	40.487/87 peersIndependent evidence	42.5108/108 peersIndependent evidence	—	—	40.189/89 peersIndependent evidence	25.2200/200 peersIndependent evidence	—	18.088/88 peersIndependent evidence	32.1123/123 peersIndependent evidence	—	28.4212/212 peersIndependent evidence	—	25.2208/208 peersIndependent evidence	42.1178/178 peersIndependent evidence	—	42.9112/112 peersIndependent evidence	—	27.1114/114 peersIndependent evidence	27.9114/114 peersIndependent evidence	55.7198/198 peersIndependent evidence	18.591/91 peersIndependent evidence	40.1202/202 peersIndependent evidence	34.2201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
169	Qwen3-4B-Instruct-2507 · Non-reasoningQwen Measured effort: Non-reasoning	2.6	Eligible · 100%13 published · 4 families · 1 selected capabilities	—	—	51.3108/108 peersIndependent evidence	—	17.2197/197 peersIndependent evidence	—	25.5200/200 peersIndependent evidence	—	—	—	11.863/63 peersIndependent evidence	22.0212/212 peersIndependent evidence	—	20.1208/208 peersIndependent evidence	27.6178/178 peersIndependent evidence	—	36.9112/112 peersIndependent evidence	—	23.1114/114 peersIndependent evidence	—	12.8198/198 peersIndependent evidence	—	33.2171/171 peersIndependent evidence	28.0169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
170	GPT-4.1 · Non-reasoningOpenAI Measured effort: Non-reasoning	2.6	Eligible · 100%14 published · 5 families · 1 selected capabilities	—	—	36.1108/108 peersIndependent evidence	—	70.6197/197 peersIndependent evidence	—	25.5200/200 peersIndependent evidence	—	—	—	—	37.9212/212 peersIndependent evidence	—	15.1208/208 peersIndependent evidence	50.2178/178 peersIndependent evidence	—	45.8112/112 peersIndependent evidence	55.060/60 peersIndependent evidence	66.7114/114 peersIndependent evidence	39.2114/114 peersIndependent evidence	76.2198/198 peersIndependent evidence	—	56.9171/171 peersIndependent evidence	53.6169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
171	NVIDIA-Nemotron-3-Nano-4B-BF16 · ReasoningNVIDIA Measured effort: Reasoning	2.4	Eligible · 100%11 published · 3 families · 1 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	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
172	Llama 4 Maverick · Non-reasoningMeta Measured effort: Non-reasoning	2.3	Eligible · 100%24 published · 5 families · 1 selected capabilities	—	4.187/87 peersIndependent evidence	18.6108/108 peersIndependent evidence	—	36.3198/198 peersIndependent evidence	7.989/89 peersIndependent evidence	25.1200/200 peersIndependent evidence	—	9.088/88 peersIndependent evidence	4.6123/123 peersIndependent evidence	59.763/63 peersIndependent evidence	39.6212/212 peersIndependent evidence	—	28.1208/208 peersIndependent evidence	49.6178/178 peersIndependent evidence	—	39.3112/112 peersIndependent evidence	47.660/60 peersIndependent evidence	70.7114/114 peersIndependent evidence	42.6114/114 peersIndependent evidence	68.7198/198 peersIndependent evidence	15.791/91 peersIndependent evidence	11.9202/202 peersIndependent evidence	28.0201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
173	Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 · ReasoningNVIDIA Measured effort: Reasoning	2.2	Eligible · 100%12 published · 3 families · 1 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	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
174	Ministral 3 14B · Non-reasoningMistral Measured effort: Non-reasoning	2.2	Eligible · 100%22 published · 4 families · 1 selected capabilities	—	17.887/87 peersIndependent evidence	31.5108/108 peersIndependent evidence	—	28.9197/197 peersIndependent evidence	15.189/89 peersIndependent evidence	25.2200/200 peersIndependent evidence	—	18.688/88 peersIndependent evidence	23.5123/123 peersIndependent evidence	13.963/63 peersIndependent evidence	25.1212/212 peersIndependent evidence	—	24.1208/208 peersIndependent evidence	20.6178/178 peersIndependent evidence	—	33.9112/112 peersIndependent evidence	—	29.9114/114 peersIndependent evidence	19.8114/114 peersIndependent evidence	19.9198/198 peersIndependent evidence	6.691/91 peersIndependent evidence	29.8202/202 peersIndependent evidence	24.9201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
175	Mistral Medium 3 · Non-reasoningMistral Measured effort: Non-reasoning	2.1	Eligible · 100%14 published · 5 families · 1 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	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—

About this ranking

This profile gives hard reasoning all the weight. It compares identified configurations using their own measured results, rather than borrowing results from another effort setting. Rankings require support in this capability. Matching effort labels across providers do not imply equal compute budgets.

View the Capability ranking →

Behind the ranking

273 entries with published results · 217 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:0,hard_reasoning:100,coding:0,human_pref:0,knowledge:0,multimodal:0,long_context:0
https://unifybench.ai/rankings/reasoning?page=7

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 →