The leaders, at a glance

Agentic AI model ranking

Compare AI models and effort settings for agentic work using sourced task evaluations and visible evidence coverage.

See the full ranking ↓How configurations are ranked

Agentic 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

127 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
51	Solar Open2 250B · ReasoningUpstage Measured effort: Reasoning	27.2	Eligible · 100%10 published · 2 families · 1 selected capabilities	—	—	—	—	77.7197/197 peersIndependent evidence	—	85.9200/200 peersIndependent evidence	—	—	63.7123/123 peersIndependent evidence	—	82.0212/212 peersIndependent evidence	—	83.9208/208 peersIndependent evidence	—	—	—	—	—	—	49.2198/198 peersIndependent evidence	65.391/91 peersIndependent evidence	65.0112/112 peersIndependent evidence	55.7125/125 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
52	Solar Pro 4 · ReasoningUpstage Measured effort: Reasoning	26.3	Eligible · 100%13 published · 4 families · 1 selected capabilities	—	—	—	—	82.9197/197 peersIndependent evidence	49.489/89 peersIndependent evidence	84.6200/200 peersIndependent evidence	—	43.988/88 peersIndependent evidence	80.5123/123 peersIndependent evidence	—	88.7212/212 peersIndependent evidence	—	84.9208/208 peersIndependent evidence	—	—	—	—	—	—	49.7198/198 peersIndependent evidence	51.891/91 peersIndependent evidence	69.7112/112 peersIndependent evidence	58.7125/125 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
53	Qwen3.6-27B · ReasoningQwen Measured effort: Reasoning	25.8	Eligible · 100%19 published · 6 families · 1 selected capabilities	—	53.487/87 peersIndependent evidence	—	—	89.1197/197 peersIndependent evidence	52.989/89 peersIndependent evidence	70.7200/200 peersIndependent evidence	—	64.188/88 peersIndependent evidence	66.8123/123 peersIndependent evidence	—	77.3212/212 peersIndependent evidence	56.237/37 peersIndependent evidence	77.6208/208 peersIndependent evidence	81.2178/178 peersIndependent evidence	—	—	—	—	78.0114/114 peersIndependent evidence	52.8198/198 peersIndependent evidence	45.691/91 peersIndependent evidence	76.9202/202 peersIndependent evidence	58.5201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
54	Gemini 3 Flash Preview · ReasoningGoogle Measured effort: Reasoning	24.7	Eligible · 100%17 published · 2 families · 1 selected capabilities	—	—	99.7108/108 peersIndependent evidence	76.226/26 peersIndependent evidence	79.2198/198 peersIndependent evidence	—	88.5200/200 peersIndependent evidence	—	—	—	98.563/63 peersIndependent evidence	92.0212/212 peersIndependent evidence	—	91.6208/208 peersIndependent evidence	96.7178/178 peersIndependent evidence	—	100.0112/112 peersIndependent evidence	—	99.4114/114 peersIndependent evidence	93.3114/114 peersIndependent evidence	97.3198/198 peersIndependent evidence	—	70.2202/202 peersIndependent evidence	90.9169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
55	GPT-5 · HighOpenAI Measured effort: High	23.6	Eligible · 100%23 published · 2 families · 1 selected capabilities	—	—	96.6108/108 peersIndependent evidence	—	88.3197/197 peersIndependent evidence	—	85.2200/200 peersIndependent evidence	—	—	59.6123/123 peersIndependent evidence	95.363/63 peersIndependent evidence	81.1212/212 peersIndependent evidence	—	83.2208/208 peersIndependent evidence	89.3178/178 peersIndependent evidence	—	94.9112/112 peersIndependent evidence	100.060/60 peersIndependent evidence	96.1114/114 peersIndependent evidence	75.8114/114 peersIndependent evidence	89.9198/198 peersIndependent evidence	—	72.7202/202 peersIndependent evidence	60.5201/201 peersIndependent evidence	47.038/38 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	58.82/2 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
56	GLM-5 · ReasoningZ.ai Measured effort: Reasoning	23.6	Eligible · 100%10 published · 2 families · 1 selected capabilities	—	—	—	31.026/26 peersIndependent evidence	87.3197/197 peersIndependent evidence	—	76.6200/200 peersIndependent evidence	—	—	—	—	72.3212/212 peersIndependent evidence	—	86.3208/208 peersIndependent evidence	87.6178/178 peersIndependent evidence	—	—	—	—	—	73.5198/198 peersIndependent evidence	—	97.4171/171 peersIndependent evidence	94.6169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
57	MiMo-V2.5-Pro · ReasoningXiaomi Measured effort: Reasoning	21.9	Eligible · 100%22 published · 9 families · 1 selected capabilities	70.228/28 peersIndependent evidence	63.087/87 peersIndependent evidence	—	9.926/26 peersIndependent evidence	74.0198/198 peersIndependent evidence	56.789/89 peersIndependent evidence	81.2200/200 peersIndependent evidence	—	39.988/88 peersIndependent evidence	78.8123/123 peersIndependent evidence	—	84.0212/212 peersIndependent evidence	36.637/37 peersIndependent evidence	90.8208/208 peersIndependent evidence	98.4178/178 peersIndependent evidence	75.428/28 peersIndependent evidence	—	—	—	—	62.3198/198 peersIndependent evidence	75.691/91 peersIndependent evidence	65.4202/202 peersIndependent evidence	65.4201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
58	GPT-5.3 Codex · XHighOpenAI Measured effort: XHigh	20.9	Eligible · 100%12 published · 2 families · 1 selected capabilities	—	59.587/87 peersIndependent evidence	—	—	99.2197/197 peersIndependent evidence	—	92.6200/200 peersIndependent evidence	—	—	—	—	92.6212/212 peersIndependent evidence	—	95.2208/208 peersIndependent evidence	91.7178/178 peersIndependent evidence	—	—	—	—	85.0114/114 peersIndependent evidence	96.0198/198 peersIndependent evidence	—	79.2171/171 peersIndependent evidence	98.5169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.03/3 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
59	Qwen3.5-397B-A17B · ReasoningQwen Measured effort: Reasoning	20.4	Eligible · 100%23 published · 9 families · 1 selected capabilities	—	42.487/87 peersIndependent evidence	—	50.326/26 peersIndependent evidence	88.5197/197 peersIndependent evidence	51.189/89 peersIndependent evidence	75.3200/200 peersIndependent evidence	29.941/41 peersIndependent evidence	70.788/88 peersIndependent evidence	56.6123/123 peersIndependent evidence	89.663/63 peersIndependent evidence	89.5212/212 peersIndependent evidence	27.937/37 peersIndependent evidence	84.6208/208 peersIndependent evidence	97.3178/178 peersIndependent evidence	58.028/28 peersIndependent evidence	—	—	—	84.5114/114 peersIndependent evidence	80.7198/198 peersIndependent evidence	54.791/91 peersIndependent evidence	74.0202/202 peersIndependent evidence	58.8201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
60	Claude Sonnet 4.5 · ReasoningAnthropic Measured effort: Reasoning	19.8	Eligible · 100%22 published · 5 families · 1 selected capabilities	—	48.587/87 peersIndependent evidence	90.2108/108 peersIndependent evidence	—	80.0197/197 peersIndependent evidence	58.289/89 peersIndependent evidence	70.5200/200 peersIndependent evidence	—	45.088/88 peersIndependent evidence	60.9123/123 peersIndependent evidence	87.463/63 peersIndependent evidence	74.7212/212 peersIndependent evidence	—	70.8208/208 peersIndependent evidence	67.5178/178 peersIndependent evidence	—	77.6112/112 peersIndependent evidence	—	96.9114/114 peersIndependent evidence	60.0114/114 peersIndependent evidence	83.7198/198 peersIndependent evidence	58.891/91 peersIndependent evidence	72.9202/202 peersIndependent evidence	58.9201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
61	MiMo-V2.5 · ReasoningXiaomi Measured effort: Reasoning	19.6	Eligible · 100%18 published · 5 families · 1 selected capabilities	—	50.987/87 peersIndependent evidence	—	—	79.1197/197 peersIndependent evidence	60.789/89 peersIndependent evidence	79.9200/200 peersIndependent evidence	—	38.888/88 peersIndependent evidence	67.8123/123 peersIndependent evidence	—	79.8212/212 peersIndependent evidence	—	79.2208/208 peersIndependent evidence	79.4178/178 peersIndependent evidence	—	—	—	—	79.6114/114 peersIndependent evidence	38.5198/198 peersIndependent evidence	50.491/91 peersIndependent evidence	61.2202/202 peersIndependent evidence	64.9201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
62	Amazon Nova 2 Pro Preview · MediumAmazon Measured effort: Medium	18.9	Eligible · 100%16 published · 2 families · 1 selected capabilities	—	—	91.2108/108 peersIndependent evidence	—	49.8198/198 peersIndependent evidence	—	24.9200/200 peersIndependent evidence	—	—	37.3123/123 peersIndependent evidence	—	64.8212/212 peersIndependent evidence	—	50.8208/208 peersIndependent evidence	97.7178/178 peersIndependent evidence	—	80.9112/112 peersIndependent evidence	—	84.0114/114 peersIndependent evidence	48.6114/114 peersIndependent evidence	60.9198/198 peersIndependent evidence	—	87.5171/171 peersIndependent evidence	58.8201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
63	GPT-5.1 · HighOpenAI Measured effort: High	18.5	Eligible · 100%18 published · 2 families · 1 selected capabilities	—	—	96.5108/108 peersIndependent evidence	—	94.2197/197 peersIndependent evidence	—	82.4200/200 peersIndependent evidence	—	—	57.6123/123 peersIndependent evidence	92.963/63 peersIndependent evidence	84.7212/212 peersIndependent evidence	—	82.2208/208 peersIndependent evidence	88.9178/178 peersIndependent evidence	—	96.6112/112 peersIndependent evidence	—	96.3114/114 peersIndependent evidence	80.3114/114 peersIndependent evidence	86.7198/198 peersIndependent evidence	—	66.5202/202 peersIndependent evidence	78.1201/201 peersIndependent evidence	56.138/38 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
64	Step 3.7 Flash · ReasoningStepFun Measured effort: Reasoning	18.1	Eligible · 100%18 published · 6 families · 1 selected capabilities	—	—	—	46.126/26 peersIndependent evidence	80.6197/197 peersIndependent evidence	—	75.4200/200 peersIndependent evidence	23.141/41 peersIndependent evidence	—	59.7123/123 peersIndependent evidence	—	67.0212/212 peersIndependent evidence	31.037/37 peersIndependent evidence	74.7208/208 peersIndependent evidence	79.9178/178 peersIndependent evidence	36.828/28 peersIndependent evidence	—	—	—	78.2114/114 peersIndependent evidence	71.5198/198 peersIndependent evidence	50.691/91 peersIndependent evidence	75.7202/202 peersIndependent evidence	68.4201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
65	Qwen3.6-35B-A3B · ReasoningQwen Measured effort: Reasoning	17.9	Eligible · 100%18 published · 5 families · 1 selected capabilities	—	45.487/87 peersIndependent evidence	—	—	78.1197/197 peersIndependent evidence	43.389/89 peersIndependent evidence	55.7200/200 peersIndependent evidence	—	49.888/88 peersIndependent evidence	60.1123/123 peersIndependent evidence	—	76.6212/212 peersIndependent evidence	—	76.8208/208 peersIndependent evidence	77.1178/178 peersIndependent evidence	—	—	—	—	80.4114/114 peersIndependent evidence	48.6198/198 peersIndependent evidence	27.891/91 peersIndependent evidence	69.0202/202 peersIndependent evidence	55.0201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
66	DeepSeek-V3.2 · ReasoningDeepSeek Measured effort: Reasoning	17.6	Eligible · 100%16 published · 3 families · 1 selected capabilities	—	—	95.5108/108 peersIndependent evidence	38.826/26 peersIndependent evidence	82.1197/197 peersIndependent evidence	—	78.2200/200 peersIndependent evidence	—	—	49.5123/123 peersIndependent evidence	78.363/63 peersIndependent evidence	76.1212/212 peersIndependent evidence	—	79.4208/208 peersIndependent evidence	72.6178/178 peersIndependent evidence	—	95.5112/112 peersIndependent evidence	—	94.4114/114 peersIndependent evidence	—	84.1198/198 peersIndependent evidence	—	85.3171/171 peersIndependent evidence	72.2201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
67	NVIDIA Nemotron 3 Ultra · ReasoningNVIDIA Measured effort: Reasoning	16.4	Eligible · 100%21 published · 8 families · 1 selected capabilities	7.628/28 peersIndependent evidence	61.387/87 peersIndependent evidence	—	—	75.9198/198 peersIndependent evidence	33.589/89 peersIndependent evidence	78.0200/200 peersIndependent evidence	18.941/41 peersIndependent evidence	43.388/88 peersIndependent evidence	71.2123/123 peersIndependent evidence	—	82.7212/212 peersIndependent evidence	46.037/37 peersIndependent evidence	81.4208/208 peersIndependent evidence	99.3178/178 peersIndependent evidence	—	—	—	—	—	62.3198/198 peersIndependent evidence	39.291/91 peersIndependent evidence	65.4202/202 peersIndependent evidence	68.6201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
68	K EXAONE 2.0 750B A37B · ReasoningLG AI Research Measured effort: Reasoning	16.2	Eligible · 100%10 published · 2 families · 1 selected capabilities	—	—	—	—	60.1197/197 peersIndependent evidence	—	66.8200/200 peersIndependent evidence	—	—	56.3123/123 peersIndependent evidence	—	73.8212/212 peersIndependent evidence	—	71.7208/208 peersIndependent evidence	—	—	—	—	—	—	17.9198/198 peersIndependent evidence	41.591/91 peersIndependent evidence	38.0112/112 peersIndependent evidence	51.1125/125 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
69	Mistral Medium 3.5 · ReasoningMistral Measured effort: Reasoning	16.1	Eligible · 100%22 published · 8 families · 1 selected capabilities	41.528/28 peersIndependent evidence	39.487/87 peersIndependent evidence	—	—	46.9198/198 peersIndependent evidence	47.989/89 peersIndependent evidence	25.2200/200 peersIndependent evidence	43.641/41 peersIndependent evidence	33.388/88 peersIndependent evidence	53.6123/123 peersIndependent evidence	—	55.1212/212 peersIndependent evidence	22.537/37 peersIndependent evidence	62.5208/208 peersIndependent evidence	81.2178/178 peersIndependent evidence	—	—	—	—	51.8114/114 peersIndependent evidence	67.4198/198 peersIndependent evidence	37.791/91 peersIndependent evidence	75.6202/202 peersIndependent evidence	55.6201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
70	Qwen3.5-35B-A3B · ReasoningQwen Measured effort: Reasoning	15.9	Eligible · 100%12 published · 2 families · 1 selected capabilities	—	—	—	—	80.4197/197 peersIndependent evidence	—	67.1200/200 peersIndependent evidence	—	—	—	74.463/63 peersIndependent evidence	79.4212/212 peersIndependent evidence	—	76.4208/208 peersIndependent evidence	88.9178/178 peersIndependent evidence	14.428/28 peersIndependent evidence	—	—	—	73.5114/114 peersIndependent evidence	54.1198/198 peersIndependent evidence	—	83.6171/171 peersIndependent evidence	70.1169/169 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
71	GPT-5 Mini · HighOpenAI Measured effort: High	15.6	Eligible · 100%25 published · 5 families · 1 selected capabilities	—	30.187/87 peersIndependent evidence	93.1108/108 peersIndependent evidence	—	77.0197/197 peersIndependent evidence	46.389/89 peersIndependent evidence	25.3200/200 peersIndependent evidence	—	51.188/88 peersIndependent evidence	50.8123/123 peersIndependent evidence	81.063/63 peersIndependent evidence	71.7212/212 peersIndependent evidence	—	74.4208/208 peersIndependent evidence	92.0178/178 peersIndependent evidence	—	94.9112/112 peersIndependent evidence	—	87.0114/114 peersIndependent evidence	63.7114/114 peersIndependent evidence	69.5198/198 peersIndependent evidence	31.591/91 peersIndependent evidence	60.6202/202 peersIndependent evidence	37.3201/201 peersIndependent evidence	33.338/38 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	37.23/3 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
72	Qwen3.5-122B-A10B · ReasoningQwen Measured effort: Reasoning	15.5	Eligible · 100%19 published · 5 families · 1 selected capabilities	—	35.687/87 peersIndependent evidence	—	—	87.7197/197 peersIndependent evidence	45.389/89 peersIndependent evidence	63.2200/200 peersIndependent evidence	—	35.888/88 peersIndependent evidence	56.9123/123 peersIndependent evidence	86.263/63 peersIndependent evidence	82.2212/212 peersIndependent evidence	—	79.8208/208 peersIndependent evidence	94.2178/178 peersIndependent evidence	—	—	—	—	79.2114/114 peersIndependent evidence	67.3198/198 peersIndependent evidence	35.191/91 peersIndependent evidence	74.5202/202 peersIndependent evidence	53.2201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
73	Grok-4.3 · HighxAI Measured effort: High	15.3	Eligible · 100%38 published · 13 families · 1 selected capabilities	14.328/28 peersIndependent evidence	52.187/87 peersIndependent evidence	69.948/48 peersIndependent evidence	45.126/26 peersIndependent evidence	61.8198/198 peersIndependent evidence	25.689/89 peersIndependent evidence	86.4200/200 peersIndependent evidence	8.441/41 peersIndependent evidence	45.688/88 peersIndependent evidence	61.8123/123 peersIndependent evidence	—	75.5213/213 peersIndependent evidence	25.350/50 peersIndependent evidence	90.2208/208 peersIndependent evidence	99.0178/178 peersIndependent evidence	47.928/28 peersIndependent evidence	—	—	17.531/31 peersIndependent evidence	84.8114/114 peersIndependent evidence	84.8198/198 peersIndependent evidence	65.391/91 peersIndependent evidence	73.7202/202 peersIndependent evidence	26.4201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	73.550/50 peersIndependent evidence	32.739/39 peersIndependent evidence	17.925/25 peersIndependent evidence	5.530/30 peersIndependent evidence	13.433/33 peersIndependent evidence	17.632/32 peersIndependent evidence	5.132/32 peersIndependent evidence	5.032/32 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—
74	MiniMax-M2.7 · ReasoningMiniMax Measured effort: Reasoning	15.0	Eligible · 100%21 published · 8 families · 1 selected capabilities	35.028/28 peersIndependent evidence	49.287/87 peersIndependent evidence	—	18.526/26 peersIndependent evidence	62.1198/198 peersIndependent evidence	41.589/89 peersIndependent evidence	62.8200/200 peersIndependent evidence	—	48.688/88 peersIndependent evidence	69.3123/123 peersIndependent evidence	—	84.7212/212 peersIndependent evidence	—	84.4208/208 peersIndependent evidence	93.6178/178 peersIndependent evidence	26.328/28 peersIndependent evidence	—	—	—	—	74.2198/198 peersIndependent evidence	72.291/91 peersIndependent evidence	59.7202/202 peersIndependent evidence	60.9201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
75	MiMo-V2-Flash · Non-reasoningXiaomi Measured effort: Non-reasoning	14.4	Eligible · 100%15 published · 2 families · 1 selected capabilities	—	—	66.2108/108 peersIndependent evidence	—	39.5197/197 peersIndependent evidence	—	25.4200/200 peersIndependent evidence	—	—	48.4123/123 peersIndependent evidence	8.563/63 peersIndependent evidence	35.8212/212 peersIndependent evidence	—	48.4208/208 peersIndependent evidence	42.5178/178 peersIndependent evidence	—	40.0112/112 peersIndependent evidence	—	43.8114/114 peersIndependent evidence	—	30.7198/198 peersIndependent evidence	—	75.7171/171 peersIndependent evidence	71.6201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—

About this ranking

This profile gives agentic work all the weight. Published agent-task evaluations contribute through matched benchmark families. Harnesses and reported settings remain attached to the evidence. These results describe the evaluated configurations; they do not establish how a model will perform in every workflow.

View the Capability ranking →

Behind the ranking

273 entries with published results · 127 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:100,hard_reasoning:0,coding:0,human_pref:0,knowledge:0,multimodal:0,long_context:0
https://unifybench.ai/rankings/agentic?page=3

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 →