Find the right AI for you

Search by name or tell us what you want to do
API servicesChoose how to access modelsAI modelsCapabilities, specifications, and pricingAI toolsFind useful tools by taskMCP directoryConnect tools, data, and workflowsAgent skillsFind reusable skills for AI agentsBenchmarksCompare model performanceOnline toolsConvert accounts, format JSON, estimate costs and test APIsModel timelineExplore model releasesUse casesStart with a practical task
EnterSearch · ↑↓Choose a resultEscClose
Submit中文
Project benchmark

ARC-AGI-2 · Abstract reasoning

ARC Prize · 290 configurations with published scores. Review each metric and its test conditions separately.

Report identity & conditions

Data as of2026-11-03· Report published—. See individual records for run dates and test conditions.

Leaderboard updated

  • Run configurations remain separate, including different reasoning settings.
  • Individual test dates are not given. Update dates and model release dates from the report remain separate and do not substitute for actual test dates.
  • Costs follow the report’s run scope and dollar amounts; they are not model API unit prices.
  • ARC-AGI-2 · Semi-private evaluation set. Benchmark versions are compared separately.
  • Task score on the semi-private evaluation set, as a percentage. It is not ranked across benchmark versions or evaluation scopes.
  • Cost per task as reported, in USD/task. Total costs and task counts are not invented. This is neither cost per successful task nor a current API quote.
  • Human reference results are shown separately and excluded from model/system rankings and cost comparisons.
Read the original report ↗

Compare metrics within the same report. Each chart explains its direction and scope.
See the details for full values and run conditions.

Task score

Task score on the semi-private evaluation set, as a percentage. It is not ranked across benchmark versions or evaluation scopes.: showing 8 of 290 records with values. See details for configurations and dates.

Chart data · 8 entries
Name%
GPT-6 Astra (Max)95
GPT-6.1 Sol (Max)94.167
Claude Opus 5.5 (High)93.333
GPT-6 Astra (XHigh)93.333
Claude Opus 5.5 (XHigh)92.5
GPT-5.6 Sol (Max)92.5
GPT-6 Astra (High)92.083
GPT-6 Astra (Medium)92.083

Cost per task

Cost per task as reported, in USD/task. Total costs and task counts are not invented. This is neither cost per successful task nor a current API quote.: showing 8 of 290 records with values. See details for configurations and dates.

Chart data · 8 entries
NameUSD / Task
GPT-5 Nano (Minimal)0.003
GPT-5 Nano (Low)0.003
GPT-4.1-Nano0.004
GPT-6 Luna (None)0.004
DeepSeek V4 Flash 0731 (None)0.004
Gemini 2.0 Flash0.004
Qwen3-235b-a22b Instruct (25/07)0.004
GPT-6 Luna (Low)0.005

Human reference

Human baselines are shown separately and are not ranked alongside models and systems.

Human Panel

Task score
100%
Cost per task
17 USD / Task

Full results & model versions

290 / 290configurations have published scores in this scope. Scored configurations are listed; missing values remain “Not provided.” Different run configurations of the same model are listed separately.

Grok 4.6 (Medium)

Model reported by the benchmark

As reportedOrganization: xAI

xai-grok-4-6 · CoT

Release time reported by the benchmark:

Task score
61.25%
Cost per task
0.658697 USD / Task

Gemini 3.8 Flash (Medium)

Model reported by the benchmark

As reportedOrganization: Google

google-gemini-3-8-flash · CoT

Release time reported by the benchmark:

Task score
82.91666666666667%
Cost per task
0.247788 USD / Task

GPT-5.2 (XHigh)

Model reported by the benchmark

As reportedOrganization: OpenAI

gpt-5-2-2025-12-11-thinking · CoT

Release time reported by the benchmark:

Task score
52.91%
Cost per task
1.8982 USD / Task

Nemotron 3.5 Super VL (Medium)

Model reported by the benchmark

As reportedOrganization: NVIDIA

nvidia-nemotron-3-5-super-vl-120b-a12b · CoT

Release time reported by the benchmark:

Task score
1.9444444444444444%
Cost per task
0.01731 USD / Task

GPT-5.6 Luna (XHigh)

Model reported by the benchmark

As reportedOrganization: OpenAI

openai-gpt-5-6-luna · CoT

Release time reported by the benchmark:

Task score
47.64%
Cost per task
0.54 USD / Task

Gemini 3.6 Flash (Medium)

Model reported by the benchmark

As reportedOrganization: Google

gemini-3-6-flash · CoT

Release time reported by the benchmark:

Task score
50.41666666666667%
Cost per task
0.455509 USD / Task

GPT-5.6 Luna (Max)

Model reported by the benchmark

As reportedOrganization: OpenAI

openai-gpt-5-6-luna · CoT

Release time reported by the benchmark:

Task score
59.54%
Cost per task
0.67 USD / Task

GPT-6 Sol (Max)

Model reported by the benchmark

As reportedOrganization: OpenAI

openai-gpt-6-sol · CoT

Release time reported by the benchmark:

Task score
89.58333333333334%
Cost per task
0.438898 USD / Task

GPT-6 Luna (XHigh)

Model reported by the benchmark

As reportedOrganization: OpenAI

openai-gpt-6-luna · CoT

Release time reported by the benchmark:

Task score
41.94444444444444%
Cost per task
0.032298 USD / Task

Kimi K3 (High)

Model reported by the benchmark

As reportedOrganization: Moonshot AI

moonshot-kimi-k3 · CoT

Release time reported by the benchmark:

Task score
55%
Cost per task
0.947223 USD / Task

Magistral Medium (Thinking)

Model reported by the benchmark

As reportedOrganization: Mistral

CoT

Release time reported by the benchmark:

Task score
0%
Cost per task
0.123 USD / Task

Claude Opus 5.5 (Medium)

Model reported by the benchmark

As reportedOrganization: Anthropic

anthropic-claude-opus-5-5 · CoT

Release time reported by the benchmark:

Task score
87.5%
Cost per task
0.336919 USD / Task

Claude Fable 5 (Max)

Model reported by the benchmark

As reportedOrganization: Anthropic

anthropic-claude-fable-5 · CoT

Release time reported by the benchmark:

Task score
89.16666666666667%
Cost per task
5.449076 USD / Task

DeepSeek V4 Flash 0731 (None)

Model reported by the benchmark

As reportedOrganization: DeepSeek

deepseek-v4-flash-0731 · CoT

Release time reported by the benchmark:

Task score
2.083333333333333%
Cost per task
0.003761 USD / Task

Claude Opus 4.6 (120K, Medium)

Model reported by the benchmark

As reportedOrganization: Anthropic

claude-opus-4-6-thinking · CoT

Release time reported by the benchmark:

Task score
66.25%
Cost per task
2.7209 USD / Task

GPT-5.6 Luna 2026-07-30 (High)

Model reported by the benchmark

As reportedOrganization: OpenAI

openai-gpt-5-6-luna-2026-07-30 · CoT

Release time reported by the benchmark:

Task score
33.33333333333333%
Cost per task
0.062539 USD / Task

Claude Sonnet 4.5 (Thinking 16K)

Model reported by the benchmark

As reportedOrganization: Anthropic

claude-sonnet-4-5-20250929 · CoT

Release time reported by the benchmark:

Task score
6.94%
Cost per task
0.3499 USD / Task

DeepSeek V4 Flash 0731 (Low)

Model reported by the benchmark

As reportedOrganization: DeepSeek

deepseek-v4-flash-0731 · CoT

Release time reported by the benchmark:

Task score
45.97222222222222%
Cost per task
0.020628 USD / Task

Claude Haiku 4.5 (Thinking 8K)

Model reported by the benchmark

As reportedOrganization: Anthropic

claude-haiku-4-5-20251001 · CoT

Release time reported by the benchmark:

Task score
1.67%
Cost per task
0.0909 USD / Task

GPT-6 Astra (None)

Model reported by the benchmark

As reportedOrganization: OpenAI

openai-gpt-6-astra · CoT

Release time reported by the benchmark:

Task score
59.58333333333333%
Cost per task
0.369674 USD / Task