ARC-AGI-2 · ARC Prize Results Across LLMs

Independent evaluator ARC-AGI-2 · ARC Prize results across showcased LLMs. Recorded ARC-AGI-2 measurements from ARC Prize, with source links, evaluation dates and available effort or harness records. Vendor results remain separate.

Independent evaluator Higher is better · unit: %

What this table contains

Recorded ARC-AGI-2 measurements from ARC Prize, with source links, evaluation dates and available effort or harness records. Vendor results remain separate.

10 models with results · 20 missing · 30 showcased models. Missing scores are not zero or failed tests. Headline selection is the default; source dates and setups can differ.

Interactive results & effort preference → · Results over time → · Methodology

ARC-AGI-2 · ARC Prize: independent evaluator results only
Model	Headline score	Source/record date	Evidence
GPT-6 AstraOpenAI	95%max effort	2026-10-03	All 6 recorded results & sources 95% · raw 95 % Headline · max effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. Headline: best verified value; source matrix effort order breaks ties. https://arcprize.org/results/openai-gpt-6-astra 93.3% · raw 93.3 % Alternative · xhigh effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/openai-gpt-6-astra 92.1% · raw 92.1 % Alternative · high effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/openai-gpt-6-astra 92.1% · raw 92.1 % Alternative · medium effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/openai-gpt-6-astra 85.4% · raw 85.4 % Alternative · low effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/openai-gpt-6-astra 59.6% · raw 59.6 % Alternative · none effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/openai-gpt-6-astra
GPT-6.1 SolOpenAI	94.2%max effort	2026-10-03	All 5 recorded results & sources 94.2% · raw 94.2 % Headline · max effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. Headline: best verified value; source matrix effort order breaks ties. https://arcprize.org/results/openai-gpt-6-1-sol 91.7% · raw 91.7 % Alternative · xhigh effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/openai-gpt-6-1-sol 91.7% · raw 91.7 % Alternative · high effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/openai-gpt-6-1-sol 86.7% · raw 86.7 % Alternative · medium effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/openai-gpt-6-1-sol 76.7% · raw 76.7 % Alternative · low effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/openai-gpt-6-1-sol
Claude Opus 5.5Anthropic	93.3%high effort	2026-10-03	All 5 recorded results & sources 91.7% · raw 91.7 % Alternative · max effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/anthropic-claude-opus-5-5 92.5% · raw 92.5 % Alternative · xhigh effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/anthropic-claude-opus-5-5 93.3% · raw 93.3 % Headline · high effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. Headline: best verified value; source matrix effort order breaks ties. https://arcprize.org/results/anthropic-claude-opus-5-5 87.5% · raw 87.5 % Alternative · medium effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/anthropic-claude-opus-5-5 70.1% · raw 70.1 % Alternative · low effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/anthropic-claude-opus-5-5
Claude Fable 5.1Anthropic	90%max effort	2026-10-03	All 5 recorded results & sources 90% · raw 90 % Headline · max effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. Headline: best verified value; source matrix effort order breaks ties. https://arcprize.org/results/anthropic-claude-fable-5-1 90% · raw 90 % Alternative · xhigh effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/anthropic-claude-fable-5-1 88.8% · raw 88.8 % Alternative · high effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/anthropic-claude-fable-5-1 86.3% · raw 86.3 % Alternative · medium effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/anthropic-claude-fable-5-1 78.3% · raw 78.3 % Alternative · low effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/anthropic-claude-fable-5-1
Gemini 3.8 FlashGoogle	89.2%high effort	2026-10-03	All 3 recorded results & sources 89.2% · raw 89.2 % Headline · high effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. Headline: best verified value; source matrix effort order breaks ties. https://arcprize.org/results/google-gemini-3-8-flash 82.9% · raw 82.9 % Alternative · medium effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/google-gemini-3-8-flash 77.5% · raw 77.5 % Alternative · low effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/google-gemini-3-8-flash
GPT-5.6 TerraOpenAI	83.9%max effort	2026-10-03	All 5 recorded results & sources 83.9% · raw 83.9 % Headline · max effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. Headline: best verified value; source matrix effort order breaks ties. https://arcprize.org/results/openai-gpt-5-6-terra 74.2% · raw 74.2 % Alternative · xhigh effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/openai-gpt-5-6-terra 67.1% · raw 67.1 % Alternative · high effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/openai-gpt-5-6-terra 37.5% · raw 37.5 % Alternative · medium effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/openai-gpt-5-6-terra 18.8% · raw 18.8 % Alternative · low effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/openai-gpt-5-6-terra
GLM-5.3-FlashZ.ai	65.8%max effort	2026-10-03	All 3 recorded results & sources 65.8% · raw 65.8 % Headline · max effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. Headline: best verified value; source matrix effort order breaks ties. https://arcprize.org/results/zai-glm-5-3-flash 50.1% · raw 50.1 % Alternative · high effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/zai-glm-5-3-flash 27.9% · raw 27.9 % Alternative · low effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/zai-glm-5-3-flash
Kimi K3Moonshot AI	60.4%max effort	2026-10-03	All 3 recorded results & sources 60.4% · raw 60.4 % Headline · max effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. Headline: best verified value; source matrix effort order breaks ties. https://arcprize.org/results/moonshot-kimi-k3 55% · raw 55 % Alternative · high effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/moonshot-kimi-k3 12.4% · raw 12.4 % Alternative · low effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/moonshot-kimi-k3
GPT-6 LunaOpenAI	59.3%max effort	2026-10-03	All 6 recorded results & sources 59.3% · raw 59.3 % Headline · max effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. Headline: best verified value; source matrix effort order breaks ties. https://arcprize.org/results/openai-gpt-6-luna 41.9% · raw 41.9 % Alternative · xhigh effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/openai-gpt-6-luna 31.4% · raw 31.4 % Alternative · high effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/openai-gpt-6-luna 18.1% · raw 18.1 % Alternative · medium effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/openai-gpt-6-luna 4.6% · raw 4.6 % Alternative · low effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/openai-gpt-6-luna 0% · raw 0 % Alternative · none effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/openai-gpt-6-luna
Qwen3.8 27BAlibaba (Qwen)	42.4%xhigh effort	2026-10-03	All 4 recorded results & sources 42.4% · raw 42.4 % Headline · xhigh effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. Headline: best verified value; source matrix effort order breaks ties. https://arcprize.org/results/alibaba-qwen3-8-27b 13.2% · raw 13.2 % Alternative · medium effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/alibaba-qwen3-8-27b 22.8% · raw 22.8 % Alternative · low effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/alibaba-qwen3-8-27b 1.5% · raw 1.5 % Alternative · none effort · Independent evaluator Source/record date: 2026-10-03 Semi-Private verified matrix. Published verified configuration. https://arcprize.org/results/alibaba-qwen3-8-27b
Claude Sonnet 5.5Anthropic	—	—	No recorded result
DeepSeek V4.1 FlashDeepSeek	—	—	No recorded result
Gemini 4 ArgonGoogle	—	—	No recorded result
GLM-5.3Z.ai	—	—	No recorded result
Grok 4.7xAI	—	—	No recorded result
Hy4 previewTencent	—	—	No recorded result
Kolibri-1Aleph Alpha	—	—	No recorded result
Ling 3.0 Flash VLinclusionAI	—	—	No recorded result
Ling 3.1 FlashinclusionAI	—	—	No recorded result
Mercury 2.5Inception	—	—	No recorded result
MiMo-V2.6-Distill-Qwen-9BXiaomi	—	—	No recorded result
MiMo-V2.6-FlashXiaomi	—	—	No recorded result
MiMo-V2.6-ProXiaomi	—	—	No recorded result
Muse Spark 1.3Meta	—	—	No recorded result
Naive-N0.5-FlashNaiveAI	—	—	No recorded result
Nex-N2.5-ProNex AGI	—	—	No recorded result
Pareto 26.10 PreviewUnbiased	—	—	No recorded result
Qwen3.8 FlashAlibaba (Qwen)	—	—	No recorded result
Qwen3.8 Max (0902)Alibaba (Qwen)	—	—	No recorded result
Qwen3.8 Omni FlashAlibaba (Qwen)	—	—	No recorded result

Use the fair-comparison guide before interpreting results from different configurations.