Agentic Index benchmark
160 AI models ranked on Agentic Index. Each row shows the model’s score next to its cheapest API price per 1M tokens where it has one, so you can weigh quality against cost.
Scores frozen
Claude Fable 5.1 (Anthropic) leads at 58.0
Models ranked
160
on this benchmark
Top score
58.0
on the frozen board
Type
Composite
index
Frozen
Sep 9, 2026
benchmark scores
Cost vs Agentic Index
109 priced modelsEach labelled name links to that model’s page. Curated to the cost-efficiency frontier, top scorers and cheapest so labels stay readable; the full field is in the leaderboard table below (and via “select all”). Reasoning models (extended “thinking” before answering) carry a ring around the dot.
Models ranked on Agentic Index
highest score first · 160 models| # | ||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Claude Fable 5.1 |  Anthropic | 58.0 | $10.00 via Anthropic | $50.00 via Anthropic | |||||||||||||||||||||||||||||
| 2 | Qwen3.8-Flash-Next |  Alibaba | 56.4 | n/a | n/a | |||||||||||||||||||||||||||||
| 3 | Claude Opus 5 | Anthropic | 56.2 | $5.00 via Anthropic | $25.00 via Anthropic | |||||||||||||||||||||||||||||
| 4 | Muse Spark 1.3 | Other | 55.7 | $1.25 via Azure | $4.25 via Azure | |||||||||||||||||||||||||||||
| 5 | GLM 5.3 |  Zhipu | 53.4 | $0.079 Routed quote | $3.08 via Sail | |||||||||||||||||||||||||||||
| 6 | Grok 4.6 |  xAI | 53.4 | $2.00 via xAI | $6.00 via xAI | |||||||||||||||||||||||||||||
| 7 | GPT-6 Astra |  OpenAI | 51.5 | $10.00 via OpenAI | $50.00 via OpenAI | |||||||||||||||||||||||||||||
| 8 | GLM 5.3 Flash | Zhipu | 51.2 | $0.11 via Sail | $0.35 via Sail | |||||||||||||||||||||||||||||
| 9 | Claude Fable 5 | Anthropic | 51.0 | $10.00 via Anthropic | $50.00 via Anthropic | |||||||||||||||||||||||||||||
| 10 | Kimi K3 |  Moonshot | 50.6 | $0.70 Routed quote | $12.50 via Sail | |||||||||||||||||||||||||||||
| 11 | GPT-5.6 Sol | OpenAI | 50.5 | $2.00 Routed quote | $10.00 Routed quote | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||
| 12 | Qwen3.8 2.4T A95B | Alibaba | 50.4 | $2.00 via Aihubmix | $6.00 via Aihubmix | |||||||||||||||||||||||||||||
| 13 | DeepSeek V4 Flash Vision (Reasoning, Max Effort) |  DeepSeek | 48.1 | n/a | n/a | |||||||||||||||||||||||||||||
| 14 | Qwen3.8 27B | Alibaba | 46.5 | $0.04 Routed quote | $1.49 via Cerebras | |||||||||||||||||||||||||||||
| 15 | Claude Sonnet 5 | Anthropic | 44.3 | $2.00 via Anthropic | $10.00 via Anthropic | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||
| 16 | GPT-5.4 | OpenAI | 44.2 | $2.50 via Databricks | $15.00 via OpenAI | |||||||||||||||||||||||||||||
| 17 | Muse Spark 1.2 | Other | 44.0 | $1.25 via Meta | $4.25 via Meta | |||||||||||||||||||||||||||||
| 18 | Agnes 2.5 Pro Beta | Sapiens-ai | 43.8 | n/a | n/a | |||||||||||||||||||||||||||||
| 19 | GPT-5.6 Terra | OpenAI | 43.7 | $2.00 via OpenAI | $12.00 via OpenAI | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||
| 20 | GPT-5.6 Luna | OpenAI | 42.7 | $0.20 via OpenAI | $1.20 via OpenAI | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||
| 21 | Claude Opus 4.8 | Anthropic | 42.6 | $5.00 via Anthropic | $25.00 via Anthropic | |||||||||||||||||||||||||||||
| 22 | Grok 4.5 | xAI | 42.1 | $2.00 via xAI | $6.00 via xAI | |||||||||||||||||||||||||||||
| 23 | Gemini 3.8 Flash |  Google | 41.1 | $0.75 via Google | $3.75 via Google | |||||||||||||||||||||||||||||
| 24 | K2 Horizon 375B A23B | Mbzuai-institute-of-foundation-models | 40.9 | n/a | n/a | |||||||||||||||||||||||||||||
| 25 | Claude Opus 4.7 | Anthropic | 39.5 | $5.00 via Anthropic | $25.00 via Anthropic | |||||||||||||||||||||||||||||
| 26 | GLM 5.2 | Zhipu | 39.4 | $0.05 Routed quote | $1.98 via Scx AI | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||
| 27 | Motif 3 | Motif-technologies | 37.6 | n/a | n/a | |||||||||||||||||||||||||||||
| 28 | GPT-5.5 | OpenAI | 37.3 | $5.00 via OpenAI | $30.00 via OpenAI | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||
| 29 | Apodex 1.1 | Apodex | 36.6 | n/a | n/a | |||||||||||||||||||||||||||||
| 30 | Gemini 3.7 Flash | Google | 36.4 | $0.75 via Google | $3.75 via Google | |||||||||||||||||||||||||||||
| 31 | Motif 3 (Beta) (0714) | Motif-technologies | 34.9 | n/a | n/a | |||||||||||||||||||||||||||||
| 32 | JT-4.1 Flash 236B A21B | China-mobile | 34.9 | n/a | n/a | |||||||||||||||||||||||||||||
| 33 | Solar Pro 4 | Other | 33.6 | $0.09 Routed quote | $0.36 Routed quote | |||||||||||||||||||||||||||||
| 34 | Claude Sonnet 4.6 | Anthropic | 33.1reasoning: adaptive | $3.00 via Databricks | $15.00 via Anthropic | |||||||||||||||||||||||||||||
| 35 | G9v3-39A5B | Ai9stars | 32.9 | n/a | n/a | |||||||||||||||||||||||||||||
| 36 | Quasar 438B | Multiverse-computing | 32.7 | n/a | n/a | |||||||||||||||||||||||||||||
| 37 | Nex-N2-Pro | Other | 31.2 | $0.25 Routed quote | $1.00 Routed quote | |||||||||||||||||||||||||||||
| 38 | MiniMax M3 |  MiniMax | 30.8 | $0.23 via Wandb | $0.96 via Wandb | |||||||||||||||||||||||||||||
| 39 | Gemini 3.6 Flash | Google | 30.2 | $0.75 via Google | $3.75 via Google | |||||||||||||||||||||||||||||
| 40 | Agnes 2.5 Pro Alpha | Sapiens-ai | 29.4 | n/a | n/a | |||||||||||||||||||||||||||||
| 41 | Qwen3.6 Plus | Alibaba | 29.0 | $0.325 Routed quote | $1.95 Routed quote | |||||||||||||||||||||||||||||
| 42 | Grok Build 0.1 0616 | Spacexai | 28.9 | n/a | n/a | |||||||||||||||||||||||||||||
| 43 | Muse Spark |  Meta | 28.7 | n/a | n/a | |||||||||||||||||||||||||||||
| 44 | Solar Open2 250B | Upstage | 27.8 | n/a | n/a | |||||||||||||||||||||||||||||
| 45 | Muse Spark 1.1 | Other | 27.5 | $1.25 via Meta | $4.25 via Meta | |||||||||||||||||||||||||||||
| 46 | Gemini 3.5 Flash | Google | 27.3 | $1.50 via Google | $9.00 via Google | |||||||||||||||||||||||||||||
| 47 | GPT-5 | OpenAI | 26.5 | $1.25 via Databricks | $10.00 via Databricks | |||||||||||||||||||||||||||||
| 48 | GLM 4.7 | Zhipu | 26.2 | $0.40 via DeepInfra | $1.75 via DeepInfra | |||||||||||||||||||||||||||||
| 49 | A.X-K2 | Sk-telecom | 25.7 | n/a | n/a | |||||||||||||||||||||||||||||
| 50 | Hy3 | Tencent | 25.6 | $0.132 Routed quote | $0.528 Routed quote | |||||||||||||||||||||||||||||
Frequently asked questions
What is the Agentic Index benchmark?
Artificial Analysis's composite agentic score (0 to 100) measuring tool use, planning, autonomy and multi-step problem solving, computed by averaging its underlying agentic evaluations and normalising to a 0 to 100 scale.
Which AI model scores highest on Agentic Index?
Claude Fable 5.1 (Anthropic) leads with 58.0, from $10.00 per 1M input tokens from Anthropic. Artificial Analysis last published scores for this benchmark on Sep 9, 2026. Scores here are frozen at that date, and models released since are not on it.
How many models are ranked on Agentic Index?
160 models carry an Agentic Index score. Scores come from Artificial Analysis; where a model has a listed API price it is drawn from LiteLLM and OpenRouter, and models with no current price are listed without one.
Other benchmarks
compare the same models on a different evalEvery weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI