Weighted consensus · Public benchmarks

Agentic AI leaderboard

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

Looking for which LLM is best? UnifyBench is a first stop: source-balanced consensus across many published benchmarks (not one board). Shortlist here, then validate on Artificial Analysis, check Arena for preference, and finish with task-specific evals.

Agentic leaders

Comparison score · 0–100

Experimental scores for the selected profile and sources. Small gaps may not be meaningful. How scoring works · Effort evidence collected

Reviewed retained observations are in use. October 2026 Real-SWE board has no 95% confidence whisker, so these scores stay at the 2026-10-18 retrieval. Original source retrieval 2026-10-18; source updated 2026-10-18.

Explore all 137 source pages Independent evaluations and lab reports

Each model is counted once across effort levels. Configurations count documented model + effort settings, including unranked.

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

One entry per model, using its highest-scoring eligible effort setting. How effort ranking works.

Customize ranking Sources, profiles and evidence details

Evidence only MultimodalLong contextHuman prefAll capabilitiesThese profiles do not yet have enough comparable evidence for a ranking.

Adjust weights

Full ranking

174 entries

Custom capability ranking of measured model configurations. Scores are experimental; missing results remain unknown.
RankModelScoreCapability coverage
76Kimi-K2.7-Code · ReasoningMoonshot28.8Eligible · 100%6 families · 1 selected capabilities
77Qwen3.7-plus · ReasoningQwen27.6Eligible · 100%7 families · 1 selected capabilities
78GLM-5 · ReasoningZ.ai27.4Eligible · 100%2 families · 1 selected capabilities
79GLM-4.7 · ReasoningZ.ai26.4Eligible · 100%2 families · 1 selected capabilities
80Gemini 3.5 Flash-Lite · ReasoningGoogle26.3Eligible · 100%8 families · 1 selected capabilities
81Gemini 3 Flash Preview · ReasoningGoogle26.0Eligible · 100%2 families · 1 selected capabilities
82MiniMax-M3 · ReasoningMiniMax25.9Eligible · 100%9 families · 1 selected capabilities
83Solar Pro 4 · ReasoningUpstage25.3Eligible · 100%6 families · 1 selected capabilities
84Solar Open2 250B · ReasoningUpstage25.2Eligible · 100%2 families · 1 selected capabilities
85GPT-5.5 Instant · ReasoningOpenAI24.9Eligible · 100%5 families · 1 selected capabilities
86Nemotron 3.5 Super VL · ReasoningNVIDIA24.4Eligible · 100%5 families · 1 selected capabilities
87Qwen3.6-27B · ReasoningQwen23.6Eligible · 100%5 families · 1 selected capabilities
88Solar Mini 4 · ReasoningUpstage23.5Eligible · 100%4 families · 1 selected capabilities
89GPT-5 · HighOpenAI22.9Eligible · 100%2 families · 1 selected capabilities
90Muse Spark · ReasoningMeta22.9Eligible · 100%3 families · 1 selected capabilities
91Qwen3.5-397B-A17B · ReasoningQwen21.6Eligible · 100%8 families · 1 selected capabilities

More models on this page

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

416 entries with published results · 174 ranked · 0 provisional estimates.

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

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: 22 Nov 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?evidence=documented&page=4&view=shortlist

Catalog data, effort measurements, and scoring rules · Methodology

Catalog dated 22 Nov 2026. Effort evidence collected 22 Nov 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 source coverage. 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 →