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 (Refine.)

Model reported by the benchmark

As reportedOrganization: J. Berman

Refinement

Release time reported by the benchmark:

Task score
29.44%
Cost per task
30.4 USD / Task

GPT-5.6 Terra (Max)

Model reported by the benchmark

As reportedOrganization: OpenAI

openai-gpt-5-6-terra · CoT

Release time reported by the benchmark:

Task score
83.9%
Cost per task
1.09 USD / Task

Minimax M2.5

Model reported by the benchmark

As reportedOrganization: Minimax

CoT

Release time reported by the benchmark:

Task score
4.86%
Cost per task
0.17 USD / Task

GPT-5 Nano (High)

Model reported by the benchmark

As reportedOrganization: OpenAI

gpt-5-nano-reasoning · CoT

Release time reported by the benchmark:

Task score
2.61%
Cost per task
0.0295 USD / Task

GPT-5.5 (XHigh)

Model reported by the benchmark

As reportedOrganization: OpenAI

gpt-5-5-2026-04-22-thinking · CoT

Release time reported by the benchmark:

Task score
85%
Cost per task
1.87 USD / Task

Gemini 2.5 Flash (Preview) (Thinking 16K)

Model reported by the benchmark

As reportedOrganization: Google

gemini-2-5-flash-preview-05-20-thinking · CoT

Release time reported by the benchmark:

Task score
1.98%
Cost per task
0.3173 USD / Task

Kimi K3 (Low)

Model reported by the benchmark

As reportedOrganization: Moonshot AI

moonshot-kimi-k3 · CoT

Release time reported by the benchmark:

Task score
12.361111111111112%
Cost per task
0.254139 USD / Task

Magistral Small

Model reported by the benchmark

As reportedOrganization: Mistral

CoT

Release time reported by the benchmark:

Task score
0%
Cost per task
0.0488 USD / Task

GPT-4.5

Model reported by the benchmark

As reportedOrganization: OpenAI

Base LLM

Release time reported by the benchmark:

Task score
0.8%
Cost per task
2.1 USD / Task

GPT-5.4 (XHigh)

Model reported by the benchmark

As reportedOrganization: OpenAI

gpt-5-4 · CoT

Release time reported by the benchmark:

Task score
73.95%
Cost per task
1.52 USD / Task

Claude Fable 5.1 (Low)

Model reported by the benchmark

As reportedOrganization: Anthropic

anthropic-claude-fable-5-1 · CoT

Release time reported by the benchmark:

Task score
78.33333333333333%
Cost per task
0.952327 USD / Task

GPT-6.1 Sol (XHigh)

Model reported by the benchmark

As reportedOrganization: OpenAI

openai-gpt-6-1-sol · CoT

Release time reported by the benchmark:

Task score
91.66666666666666%
Cost per task
0.17809 USD / Task

Gemini 2.5 Pro (Thinking 1K)

Model reported by the benchmark

As reportedOrganization: Google

gemini-2-5-pro-2025-06-17-thinking · CoT

Release time reported by the benchmark:

Task score
0%
Cost per task
0.0885 USD / Task

GPT-5.6 Luna (Low)

Model reported by the benchmark

As reportedOrganization: OpenAI

openai-gpt-5-6-luna · CoT

Release time reported by the benchmark:

Task score
5.14%
Cost per task
0.07 USD / Task

Claude Opus 4.8 (Low)

Model reported by the benchmark

As reportedOrganization: Anthropic

anthropic-opus-4-8 · CoT

Release time reported by the benchmark:

Task score
62.22%
Cost per task
1.6818 USD / Task

DeepSeek V4 Flash 0731 (Max)

Model reported by the benchmark

As reportedOrganization: DeepSeek

deepseek-v4-flash-0731 · CoT

Release time reported by the benchmark:

Task score
61.38888888888888%
Cost per task
0.04163 USD / Task

GPT-5.6 Terra (Low)

Model reported by the benchmark

As reportedOrganization: OpenAI

openai-gpt-5-6-terra · CoT

Release time reported by the benchmark:

Task score
18.75%
Cost per task
0.17 USD / Task

Claude Haiku 5.5 (XHigh)

Model reported by the benchmark

As reportedOrganization: Anthropic

anthropic-claude-haiku-5-5 · CoT

Release time reported by the benchmark:

Task score
61.25%
Cost per task
0.084989 USD / Task

DeepSeek V4.1 Flash 1017 (High)

Model reported by the benchmark

As reportedOrganization: DeepSeek

deepseek-v4-1-flash-1017 · CoT

Release time reported by the benchmark:

Task score
68.61111111111111%
Cost per task
0.146938 USD / Task

Beam 1.0 (Low)

Model reported by the benchmark

As reportedOrganization: Reflection

reflection-beam-1-0 · CoT

Release time reported by the benchmark:

Task score
2.777777777777778%
Cost per task
0.100106 USD / Task