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
76	GLM-4.6 · ReasoningZ.ai Measured effort: Reasoning	14.4	Eligible · 100%16 published · 2 families · 1 selected capabilities	—	—	88.6108/108 peersIndependent evidence	—	56.0197/197 peersIndependent evidence	—	70.8200/200 peersIndependent evidence	—	—	52.6123/123 peersIndependent evidence	73.163/63 peersIndependent evidence	63.1212/212 peersIndependent evidence	—	66.3208/208 peersIndependent evidence	50.3178/178 peersIndependent evidence	—	72.8112/112 peersIndependent evidence	—	83.0114/114 peersIndependent evidence	—	75.1198/198 peersIndependent evidence	—	60.2202/202 peersIndependent evidence	64.6201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
77	Gemma 4 31B IT · ReasoningGoogle Measured effort: Reasoning	13.4	Eligible · 100%21 published · 8 families · 1 selected capabilities	—	27.887/87 peersIndependent evidence	—	—	72.8197/197 peersIndependent evidence	43.289/89 peersIndependent evidence	73.8200/200 peersIndependent evidence	14.641/41 peersIndependent evidence	48.988/88 peersIndependent evidence	46.3123/123 peersIndependent evidence	—	82.0212/212 peersIndependent evidence	5.937/37 peersIndependent evidence	78.2208/208 peersIndependent evidence	93.4178/178 peersIndependent evidence	69.828/28 peersIndependent evidence	—	—	—	74.6114/114 peersIndependent evidence	53.5198/198 peersIndependent evidence	57.591/91 peersIndependent evidence	57.8202/202 peersIndependent evidence	55.1201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
78	Claude Haiku 4.5 · ReasoningAnthropic Measured effort: Reasoning	12.7	Eligible · 100%27 published · 9 families · 1 selected capabilities	46.228/28 peersIndependent evidence	43.387/87 peersIndependent evidence	84.0108/108 peersIndependent evidence	—	64.1198/198 peersIndependent evidence	37.789/89 peersIndependent evidence	25.4200/200 peersIndependent evidence	25.841/41 peersIndependent evidence	37.288/88 peersIndependent evidence	51.3123/123 peersIndependent evidence	64.063/63 peersIndependent evidence	40.8212/212 peersIndependent evidence	17.837/37 peersIndependent evidence	54.0208/208 peersIndependent evidence	66.3178/178 peersIndependent evidence	29.928/28 peersIndependent evidence	64.0112/112 peersIndependent evidence	—	49.2114/114 peersIndependent evidence	34.9114/114 peersIndependent evidence	44.2198/198 peersIndependent evidence	43.991/91 peersIndependent evidence	47.6202/202 peersIndependent evidence	50.2201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
79	MiniCPM5-2B · ReasoningOpenBMB Measured effort: Reasoning	11.2	Eligible · 100%14 published · 5 families · 1 selected capabilities	—	28.487/87 peersIndependent evidence	—	—	58.9197/197 peersIndependent evidence	27.089/89 peersIndependent evidence	56.4200/200 peersIndependent evidence	—	20.688/88 peersIndependent evidence	50.3123/123 peersIndependent evidence	—	46.3212/212 peersIndependent evidence	—	48.6208/208 peersIndependent evidence	—	—	—	—	—	—	6.8198/198 peersIndependent evidence	8.391/91 peersIndependent evidence	62.0112/112 peersIndependent evidence	21.5125/125 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
80	EXAONE 4.5 33B · ReasoningLG AI Research Measured effort: Reasoning	10.7	Eligible · 100%12 published · 2 families · 1 selected capabilities	—	—	—	—	56.0197/197 peersIndependent evidence	—	56.0200/200 peersIndependent evidence	—	—	37.7123/123 peersIndependent evidence	—	65.7212/212 peersIndependent evidence	—	61.1208/208 peersIndependent evidence	69.4178/178 peersIndependent evidence	—	—	—	—	57.6114/114 peersIndependent evidence	34.0198/198 peersIndependent evidence	—	71.0171/171 peersIndependent evidence	50.9201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
81	Gemini 2.5 Pro · ReasoningGoogle Measured effort: Reasoning	10.7	Eligible · 100%23 published · 5 families · 1 selected capabilities	—	25.387/87 peersIndependent evidence	89.7108/108 peersIndependent evidence	—	69.3197/197 peersIndependent evidence	32.789/89 peersIndependent evidence	75.3200/200 peersIndependent evidence	—	60.688/88 peersIndependent evidence	37.0123/123 peersIndependent evidence	90.963/63 peersIndependent evidence	76.3212/212 peersIndependent evidence	—	75.1208/208 peersIndependent evidence	58.9178/178 peersIndependent evidence	—	91.0112/112 peersIndependent evidence	77.060/60 peersIndependent evidence	94.5114/114 peersIndependent evidence	75.1114/114 peersIndependent evidence	87.9198/198 peersIndependent evidence	61.591/91 peersIndependent evidence	49.1202/202 peersIndependent evidence	45.8201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
82	Qwen3.5-9B · ReasoningQwen Measured effort: Reasoning	10.1	Eligible · 100%13 published · 2 families · 1 selected capabilities	—	—	—	—	74.8197/197 peersIndependent evidence	—	56.1200/200 peersIndependent evidence	—	—	33.4123/123 peersIndependent evidence	—	68.3212/212 peersIndependent evidence	—	68.3208/208 peersIndependent evidence	79.9178/178 peersIndependent evidence	—	—	—	—	62.6114/114 peersIndependent evidence	36.5198/198 peersIndependent evidence	—	54.8202/202 peersIndependent evidence	58.7201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
83	Gemma 4 26B-A4B IT · ReasoningGoogle Measured effort: Reasoning	9.9	Eligible · 100%14 published · 3 families · 1 selected capabilities	—	—	—	—	70.1197/197 peersIndependent evidence	—	25.2200/200 peersIndependent evidence	—	—	44.3123/123 peersIndependent evidence	—	66.4212/212 peersIndependent evidence	—	73.8208/208 peersIndependent evidence	88.4178/178 peersIndependent evidence	22.128/28 peersIndependent evidence	—	—	—	62.5114/114 peersIndependent evidence	51.6198/198 peersIndependent evidence	—	49.7202/202 peersIndependent evidence	51.5201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
84	Gemini 3.1 Flash-Lite · ReasoningGoogle Measured effort: Reasoning	9.3	Eligible · 100%23 published · 9 families · 1 selected capabilities	18.728/28 peersIndependent evidence	21.187/87 peersIndependent evidence	—	24.826/26 peersIndependent evidence	61.2198/198 peersIndependent evidence	49.889/89 peersIndependent evidence	69.2200/200 peersIndependent evidence	10.541/41 peersIndependent evidence	52.788/88 peersIndependent evidence	35.9123/123 peersIndependent evidence	—	70.1212/212 peersIndependent evidence	1.437/37 peersIndependent evidence	68.9208/208 peersIndependent evidence	95.8178/178 peersIndependent evidence	—	—	—	—	80.2114/114 peersIndependent evidence	84.8198/198 peersIndependent evidence	48.991/91 peersIndependent evidence	38.5202/202 peersIndependent evidence	55.1201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
85	K EXAONE 236B A23B · ReasoningLG AI Research Measured effort: Reasoning	8.9	Eligible · 100%15 published · 2 families · 1 selected capabilities	—	—	92.2108/108 peersIndependent evidence	—	62.4197/197 peersIndependent evidence	—	68.8200/200 peersIndependent evidence	—	—	30.9123/123 peersIndependent evidence	32.563/63 peersIndependent evidence	64.0212/212 peersIndependent evidence	—	65.0208/208 peersIndependent evidence	78.1178/178 peersIndependent evidence	—	86.6112/112 peersIndependent evidence	—	87.4114/114 peersIndependent evidence	—	35.2198/198 peersIndependent evidence	—	68.7171/171 peersIndependent evidence	55.4201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
86	NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 · ReasoningNVIDIA Measured effort: Reasoning	8.9	Eligible · 100%16 published · 6 families · 1 selected capabilities	—	36.087/87 peersIndependent evidence	—	—	41.0198/198 peersIndependent evidence	17.689/89 peersIndependent evidence	25.5200/200 peersIndependent evidence	0.041/41 peersIndependent evidence	33.688/88 peersIndependent evidence	47.3123/123 peersIndependent evidence	—	54.3212/212 peersIndependent evidence	—	54.8208/208 peersIndependent evidence	—	—	—	—	—	—	23.7198/198 peersIndependent evidence	15.991/91 peersIndependent evidence	28.9112/112 peersIndependent evidence	41.7125/125 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
87	Devstral 2 · Non-reasoningMistral Measured effort: Non-reasoning	8.6	Eligible · 100%21 published · 5 families · 1 selected capabilities	—	33.887/87 peersIndependent evidence	39.0108/108 peersIndependent evidence	—	34.0197/197 peersIndependent evidence	36.589/89 peersIndependent evidence	25.2200/200 peersIndependent evidence	—	28.688/88 peersIndependent evidence	43.4123/123 peersIndependent evidence	32.163/63 peersIndependent evidence	29.2212/212 peersIndependent evidence	—	6.0208/208 peersIndependent evidence	36.1178/178 peersIndependent evidence	—	45.5112/112 peersIndependent evidence	—	49.9114/114 peersIndependent evidence	—	56.6198/198 peersIndependent evidence	20.891/91 peersIndependent evidence	35.3202/202 peersIndependent evidence	43.5201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
88	Qwen3-Coder-Next · Non-reasoningQwen Measured effort: Non-reasoning	8.3	Eligible · 100%18 published · 5 families · 1 selected capabilities	—	27.887/87 peersIndependent evidence	—	—	48.8197/197 peersIndependent evidence	24.389/89 peersIndependent evidence	25.4200/200 peersIndependent evidence	—	29.588/88 peersIndependent evidence	40.9123/123 peersIndependent evidence	38.363/63 peersIndependent evidence	51.8212/212 peersIndependent evidence	—	51.5208/208 peersIndependent evidence	29.7178/178 peersIndependent evidence	—	—	—	—	—	32.4198/198 peersIndependent evidence	24.991/91 peersIndependent evidence	45.5202/202 peersIndependent evidence	44.0201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
89	Mistral Medium 3.1 · Non-reasoningMistral Measured effort: Non-reasoning	8.1	Eligible · 100%20 published · 5 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	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
90	Amazon Nova 2 Lite · HighAmazon Measured effort: High	7.9	Eligible · 100%15 published · 2 families · 1 selected capabilities	—	—	96.4108/108 peersIndependent evidence	—	61.0197/197 peersIndependent evidence	—	54.6200/200 peersIndependent evidence	—	—	29.0123/123 peersIndependent evidence	—	69.9212/212 peersIndependent evidence	—	59.9208/208 peersIndependent evidence	83.8178/178 peersIndependent evidence	—	76.9112/112 peersIndependent evidence	—	77.4114/114 peersIndependent evidence	45.7114/114 peersIndependent evidence	49.8198/198 peersIndependent evidence	—	67.1171/171 peersIndependent evidence	42.2201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
91	Qwen3-235B-A22B-Thinking-2507 · ReasoningQwen Measured effort: Reasoning	7.7	Eligible · 100%22 published · 5 families · 1 selected capabilities	—	19.787/87 peersIndependent evidence	94.5108/108 peersIndependent evidence	—	76.3197/197 peersIndependent evidence	31.389/89 peersIndependent evidence	25.2200/200 peersIndependent evidence	—	42.288/88 peersIndependent evidence	26.8123/123 peersIndependent evidence	71.663/63 peersIndependent evidence	63.7212/212 peersIndependent evidence	—	67.0208/208 peersIndependent evidence	63.0178/178 peersIndependent evidence	—	89.4112/112 peersIndependent evidence	95.660/60 peersIndependent evidence	89.2114/114 peersIndependent evidence	—	62.5198/198 peersIndependent evidence	42.091/91 peersIndependent evidence	44.8202/202 peersIndependent evidence	34.8201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
92	Command A Plus 05 2026 · ReasoningCohere Measured effort: Reasoning	7.3	Eligible · 100%19 published · 5 families · 1 selected capabilities	—	24.887/87 peersIndependent evidence	—	—	34.0198/198 peersIndependent evidence	29.189/89 peersIndependent evidence	56.1200/200 peersIndependent evidence	—	12.088/88 peersIndependent evidence	39.9123/123 peersIndependent evidence	—	58.1212/212 peersIndependent evidence	—	58.9208/208 peersIndependent evidence	91.0178/178 peersIndependent evidence	—	—	—	—	45.4114/114 peersIndependent evidence	8.0198/198 peersIndependent evidence	29.991/91 peersIndependent evidence	49.2202/202 peersIndependent evidence	52.6201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
93	Devstral Small 2 · Non-reasoningMistral Measured effort: Non-reasoning	7.2	Eligible · 100%22 published · 5 families · 1 selected capabilities	—	35.487/87 peersIndependent evidence	35.9108/108 peersIndependent evidence	—	30.7197/197 peersIndependent evidence	35.489/89 peersIndependent evidence	25.2200/200 peersIndependent evidence	—	13.088/88 peersIndependent evidence	42.1123/123 peersIndependent evidence	15.663/63 peersIndependent evidence	22.3212/212 peersIndependent evidence	—	5.3208/208 peersIndependent evidence	16.3178/178 peersIndependent evidence	—	33.0112/112 peersIndependent evidence	—	24.7114/114 peersIndependent evidence	14.1114/114 peersIndependent evidence	31.3198/198 peersIndependent evidence	19.091/91 peersIndependent evidence	34.3202/202 peersIndependent evidence	41.6201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
94	Qwen3.5-2B · Non-reasoningQwen Measured effort: Non-reasoning	7.1	Eligible · 100%13 published · 2 families · 1 selected capabilities	—	—	—	—	19.0197/197 peersIndependent evidence	—	25.3200/200 peersIndependent evidence	—	—	3.6123/123 peersIndependent evidence	—	14.1212/212 peersIndependent evidence	—	28.4208/208 peersIndependent evidence	14.5178/178 peersIndependent evidence	—	—	—	—	9.2114/114 peersIndependent evidence	4.7198/198 peersIndependent evidence	—	73.7171/171 peersIndependent evidence	14.0201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	5.650/50 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
95	NVIDIA-Nemotron-3-Super-120B-A12B-BF16 · ReasoningNVIDIA Measured effort: Reasoning	6.4	Eligible · 100%21 published · 8 families · 1 selected capabilities	—	3.887/87 peersIndependent evidence	—	3.126/26 peersIndependent evidence	49.0198/198 peersIndependent evidence	38.789/89 peersIndependent evidence	78.0200/200 peersIndependent evidence	4.341/41 peersIndependent evidence	30.488/88 peersIndependent evidence	39.1123/123 peersIndependent evidence	—	65.5212/212 peersIndependent evidence	—	73.7208/208 peersIndependent evidence	85.9178/178 peersIndependent evidence	0.028/28 peersIndependent evidence	—	—	—	—	65.8198/198 peersIndependent evidence	25.791/91 peersIndependent evidence	53.7202/202 peersIndependent evidence	49.5201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
96	gpt-oss-120b · HighOpenAI Measured effort: High	6.2	Eligible · 100%28 published · 9 families · 1 selected capabilities	—	4.287/87 peersIndependent evidence	96.2108/108 peersIndependent evidence	13.326/26 peersIndependent evidence	30.5198/198 peersIndependent evidence	7.089/89 peersIndependent evidence	67.9200/200 peersIndependent evidence	5.641/41 peersIndependent evidence	36.288/88 peersIndependent evidence	44.9123/123 peersIndependent evidence	60.463/63 peersIndependent evidence	60.5212/212 peersIndependent evidence	0.037/37 peersIndependent evidence	70.4208/208 peersIndependent evidence	81.1178/178 peersIndependent evidence	4.128/28 peersIndependent evidence	97.6112/112 peersIndependent evidence	—	68.9114/114 peersIndependent evidence	—	58.1198/198 peersIndependent evidence	20.591/91 peersIndependent evidence	56.8202/202 peersIndependent evidence	41.3201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.02/2 peersIndependent evidence	0.040/40 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
97	Solar Pro 3 · ReasoningUpstage Measured effort: Reasoning	6.0	Eligible · 100%18 published · 5 families · 1 selected capabilities	—	14.887/87 peersIndependent evidence	—	—	24.2198/198 peersIndependent evidence	10.789/89 peersIndependent evidence	25.5200/200 peersIndependent evidence	—	23.888/88 peersIndependent evidence	24.4123/123 peersIndependent evidence	—	49.4212/212 peersIndependent evidence	—	53.0208/208 peersIndependent evidence	85.2178/178 peersIndependent evidence	—	—	—	—	—	46.1198/198 peersIndependent evidence	6.891/91 peersIndependent evidence	58.2202/202 peersIndependent evidence	30.7201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
98	Gemma 4 12B IT · ReasoningGoogle Measured effort: Reasoning	5.6	Eligible · 100%12 published · 2 families · 1 selected capabilities	—	—	—	—	65.2197/197 peersIndependent evidence	—	25.1200/200 peersIndependent evidence	—	—	34.7123/123 peersIndependent evidence	—	57.3212/212 peersIndependent evidence	—	69.3208/208 peersIndependent evidence	90.9178/178 peersIndependent evidence	—	—	—	—	63.9114/114 peersIndependent evidence	29.9198/198 peersIndependent evidence	—	45.8171/171 peersIndependent evidence	50.5201/201 peersIndependent evidence	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
99	GPT-4.1 Mini · Non-reasoningOpenAI Measured effort: Non-reasoning	5.6	Eligible · 100%17 published · 2 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	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—
100	Mistral Large 3 · Non-reasoningMistral Measured effort: Non-reasoning	5.3	Eligible · 100%22 published · 5 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	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—

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=4

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 →