Arena ranking
Agent Task Outcome Explicit Leaderboard
Browse Agent Task Outcome Explicit results, model ratings and supporting selection context.
Data as of 2026-09-08
Agent Task Outcome Explicit Ranking
This source leaderboard ranking orders models by their original Arena rank rather than an aggregated benchmark score.
Sort by
Rank | Model | Source Agent score | LLMBoard Score | Observations | Official input / 1M | Output speed |
|---|
| Rank01 | ModelAN | Source Agent score22.45% | LLMBoard ScoreN/A | Observations2.5K | Official input / 1M$10 | Output speed7.67 tok/s |
| Rank02 | ModelMA | Source Agent score16.58% | LLMBoard ScoreN/A | Observations74.2K | Official input / 1M$3 | Output speedN/A |
| Rank03 | ModelAN | Source Agent score14.89% | LLMBoard ScoreN/A | Observations12.5K | Official input / 1M$5 | Output speed62.88 tok/s |
| Rank04 | ModelZA | Source Agent score14.14% | LLMBoard ScoreN/A | Observations13.5K | Official input / 1M$0.075 | Output speed74.28 tok/s |
| Rank05 | ModelTE | Source Agent score13.56% | LLMBoard ScoreN/A | Observations6.5K | Official input / 1MN/A | Output speedN/A |
| Rank06 | ModelAC | Source Agent score12.46% | LLMBoard ScoreN/A | Observations9.5K | Official input / 1MN/A | Output speedN/A |
| Rank07 | ModelZA | Source Agent score12.10% | LLMBoard ScoreN/A | Observations34.9K | Official input / 1M$1.4 | Output speed472.69 tok/s |
| Rank08 | ModelDE | Source Agent score11.75% | LLMBoard ScoreN/A | Observations20.4K | Official input / 1MN/A | Output speed45.48 tok/s |
| Rank09 | ModelGO | Source Agent score10.42% | LLMBoard ScoreN/A | Observations4.6K | Official input / 1M$0.75 | Output speed51.56 tok/s |
| Rank10 | ModelAC | Source Agent score10.37% | LLMBoard ScoreN/A | Observations14K | Official input / 1M$2 | Output speed60.87 tok/s |
| Rank11 | ModelGO | Source Agent score9.54% | LLMBoard ScoreN/A | Observations19.6K | Official input / 1M$0.75 | Output speed117.86 tok/s |
| Rank12 | ModelZA | Source Agent score8.63% | LLMBoard ScoreN/A | Observations42.5K | Official input / 1M$1.4 | Output speed3.96 tok/s |
| Rank13 | ModelDE | Source Agent score8.46% | LLMBoard ScoreN/A | Observations35.4K | Official input / 1M$0.14 | Output speed15.91 tok/s |
| Rank14 | ModelXA | Source Agent score7.83% | LLMBoard ScoreN/A | Observations12.9K | Official input / 1M$2 | Output speed132.69 tok/s |
| Rank15 | ModelAN | Source Agent score7.37% | LLMBoard ScoreN/A | Observations27.5K | Official input / 1M$10 | Output speed43.18 tok/s |
| Rank16 | ModelAC | Source Agent score6.98% | LLMBoard ScoreN/A | Observations13.9K | Official input / 1MN/A | Output speedN/A |
| Rank17 | ModelOP | Source Agent score6.68% | LLMBoard ScoreN/A | Observations22.8K | Official input / 1M$4 | Output speed2.36 tok/s |
| Rank18 | ModelME | Source Agent score6.60% | LLMBoard ScoreN/A | Observations12.9K | Official input / 1M$1.25 | Output speed28.44 tok/s |
| Rank19 | ModelXA | Source Agent score6.30% | LLMBoard ScoreN/A | Observations23.8K | Official input / 1M$2 | Output speed80.00 tok/s |
| Rank20 | ModelAN | Source Agent score5.93% | LLMBoard ScoreN/A | Observations21.1K | Official input / 1M$5 | Output speed42.00 tok/s |
| Rank21 | ModelME | Source Agent score5.01% | LLMBoard ScoreN/A | Observations56.5K | Official input / 1M$1.25 | Output speed14.00 tok/s |
| Rank22 | ModelAN | Source Agent score3.51% | LLMBoard ScoreN/A | Observations25.8K | Official input / 1M$5 | Output speed42.00 tok/s |
| Rank23 | ModelAN | Source Agent score2.80% | LLMBoard ScoreN/A | Observations19.4K | Official input / 1M$2 | Output speed42.00 tok/s |
| Rank24 | ModelAN | Source Agent score2.50% | LLMBoard ScoreN/A | Observations27.8K | Official input / 1M$5 | Output speed123.15 tok/s |
| Rank25 | ModelOP | Source Agent score2.07% | LLMBoard ScoreN/A | Observations39.1K | Official input / 1M$5 | Output speed134.94 tok/s |
| Rank26 | ModelMA | Source Agent score1.15% | LLMBoard ScoreN/A | Observations5.7K | Official input / 1M$0.95 | Output speedN/A |
| Rank27 | ModelOP | Source Agent score1.14% | LLMBoard ScoreN/A | Observations53.9K | Official input / 1M$2.5 | Output speed50.00 tok/s |
| Rank28 | ModelOP | Source Agent score0.83% | LLMBoard ScoreN/A | Observations15K | Official input / 1M$0.20 | Output speed41.87 tok/s |
| Rank29 | ModelZA | Source Agent score0.17% | LLMBoard ScoreN/A | Observations45.3K | Official input / 1M$1.4 | Output speedN/A |
| Rank30 | ModelGO | Source Agent score-1.62% | LLMBoard ScoreN/A | Observations68.3K | Official input / 1M$1.5 | Output speed210.94 tok/s |
Source leaderboard overview
This leaderboard overview compares the source ranking, score gaps and observed task volume.
Ranked models49
SignalAgent score
Agent score and confidence
Use confidence and observed task volume to judge how firmly each leaderboard position is supported; these source proportions remain separate from benchmark coverage.
16.58%
14.89%
14.14%
13.56%
12.10%
11.75%
10.42%
8.63%
Agent Task Outcome Explicit Leaderboard Vendor Mix
Vendor representation among the top-ranked models in this leaderboard.
Top-entry vendor mix
25 modelsThe Top AI Models for Agent Task Outcome Explicit
A practical summary of the first five entries in this agent task outcome explicit AI model leaderboard, with benchmark evidence and pricing kept in context.
About this leaderboard ranking
Common questions about the Agent Task Outcome Explicit Leaderboard.
What is the top model on Agent Task Outcome Explicit Leaderboard?
Claude Fable 5.1 is currently ranked first with 22.45 Agent score.
What are the top three models on Agent Task Outcome Explicit Leaderboard?
The current leaders are Claude Fable 5.1 (rank #1), Kimi K3 (rank #2), and Claude Opus 5 (rank #3).
Which ranked model has the lowest official input price?
GLM 5.3 Flash has the lowest matched official input price at $0.075 per 1M tokens.
Which models are fastest on this leaderboard?
The fastest matched records are GLM 5.3 (472.69 tok/s via FriendliAI), Gemini 3.5 Flash (210.94 tok/s via Google), and GPT-5.5 (134.94 tok/s via OpenAI).
Does the top source result mean the model is best at every task?
No. Source Arena results describe a particular task or preference signal. Capability benchmarks, prices and runtime can produce different rankings.