A task with its own rules.
A second-generation abstract reasoning benchmark based on novel grid transformation tasks.
- Organisation
- ARC Prize Foundation
- Version
- 2
Loading benchmark header
Loading benchmark registry
Reasoning / Benchmark profile
A second-generation abstract reasoning benchmark based on novel grid transformation tasks.
Observed results
16 ranked models · higher is better · labels show rank and score
| Model | Rank | Model ID | Provider | Score | Unit |
|---|---|---|---|---|---|
| GPT-5.6 Sol | #1 | gpt-5-6-sol | OpenAI | 92.5 | percent |
| Claude Opus 5 | #2 | claude-opus-5 | Anthropic | 90.4 | percent |
| GPT-5.5 | #3 | gpt-5-5 | OpenAI | 85 | percent |
| GPT-5.6 Terra | #4 | gpt-5-6-terra | OpenAI | 83.9 | percent |
| GPT-5.4 | #5 | gpt-5-4 | OpenAI | 83.3 | percent |
| Gemini 3.1 Pro Preview | #6 | gemini-3-1-pro-preview | 77.1 | percent | |
| Claude Opus 4.7 | #7 | claude-opus-4-7 | Anthropic | 75.8 | percent |
| Gemini 3.5 Flash | #8 | gemini-3-5-flash | 72.1 | percent | |
| Claude Opus 4.8 | #9 | claude-opus-4-8 | Anthropic | 72.08 | percent |
| GPT-5.6 Luna | #10 | gpt-5-6-luna | OpenAI | 59.54 | percent |
| GPT-5.2 | #11 | gpt-5-2 | OpenAI | 54.2 | percent |
| Grok 4.20 | #12 | grok-4-20 | xAI | 53.3 | percent |
| Grok 4.5 | #13 | grok-4-5 | xAI | 52.64 | percent |
| Muse Spark | #14 | muse-spark | Meta | 42.5 | percent |
| Inkling-Small | #15 | inkling-small | Thinking Machines Lab | 40.1 | percent |
| Claude Sonnet 4.5 | #16 | claude-sonnet-4-5 | Anthropic | 13.6 | percent |
One best compatible score per canonical product · higher is better
| Rank | Model | Weights | Evidence | Score |
|---|---|---|---|---|
| 01 | GPT-5.6 SolOpenAI | Closed weights | Source carrier | 92.5% |
| 02 | Claude Opus 5Anthropic | Closed weights | Source carrier | 90.4% |
| 03 | GPT-5.5OpenAI | Closed weights | Source carrier | 85% |
| 04 | GPT-5.6 TerraOpenAI | Closed weights | Source carrier | 83.9% |
| 05 | GPT-5.4OpenAI | Closed weights | Source carrier | 83.3% |
| 06 | Gemini 3.1 Pro PreviewGoogle | Closed weights | Public reference | 77.1% |
| 07 | Claude Opus 4.7Anthropic | Closed weights | Source carrier | 75.8% |
| 08 | Gemini 3.5 FlashGoogle | Closed weights | Direct source result | 72.1% |
| 09 | Claude Opus 4.8Anthropic | Closed weights | Source carrier | 72.1% |
| 10 | GPT-5.6 LunaOpenAI | Closed weights | Source carrier | 59.5% |
Each distinct published measurement is retained. Same-snapshot canonical and configuration projections appear once.
| Published model / configuration | Score | Evidence & protocol | Source & dates |
|---|---|---|---|
Exact BenchLM registry variant GPT-5.6 Sol; bulk export does not retain a complete upstream harness configuration.GPT-5.6 SolExact identitySource label without a registered configuration ID Canonical product: gpt-5-6-sol | 92.5% | Source carriersource-checkedVersion & system2025 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant Claude Opus 5; bulk export does not retain a complete upstream harness configuration.Claude Opus 5Exact identitySource label without a registered configuration ID Canonical product: claude-opus-5 | 90.4% | Source carriersource-checkedVersion & system2025 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant GPT-5.5; bulk export does not retain a complete upstream harness configuration.GPT-5.5Exact identitySource label without a registered configuration ID Canonical product: gpt-5-5 | 85% | Source carriersource-checkedVersion & system2025 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant GPT-5.6 Terra; bulk export does not retain a complete upstream harness configuration.GPT-5.6 TerraExact identitySource label without a registered configuration ID Canonical product: gpt-5-6-terra | 83.9% | Source carriersource-checkedVersion & system2025 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant GPT-5.4 Pro; bulk export does not retain a complete upstream harness configuration.GPT-5.4Exact identitygpt-5-4-pro-default-medium Canonical product: gpt-5-4 | 83.3% | Source carriersource-checkedVersion & system2025 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant Claude Opus 4.7 (Adaptive); bulk export does not retain a complete upstream harness configuration.Claude Opus 4.7Exact identityclaude-opus-4-7-max Canonical product: claude-opus-4-7 | 75.8% | Source carriersource-checkedVersion & system2025 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant GPT-5.4; bulk export does not retain a complete upstream harness configuration.GPT-5.4Exact identitySource label without a registered configuration ID Canonical product: gpt-5-4 | 74.0% | Source carriersource-checkedVersion & system2025 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant Gemini 3.5 Flash; bulk export does not retain a complete upstream harness configuration.Gemini 3.5 FlashExact identitySource label without a registered configuration ID Canonical product: gemini-3-5-flash | 72.1% | Source carriersource-checkedVersion & system2025 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant Claude Opus 4.8; bulk export does not retain a complete upstream harness configuration.Claude Opus 4.8Exact identitySource label without a registered configuration ID Canonical product: claude-opus-4-8 | 72.1% | Source carriersource-checkedVersion & system2025 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant GPT-5.6 Luna; bulk export does not retain a complete upstream harness configuration.GPT-5.6 LunaExact identitySource label without a registered configuration ID Canonical product: gpt-5-6-luna | 59.5% | Source carriersource-checkedVersion & system2025 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
From result to context
A second-generation abstract reasoning benchmark based on novel grid transformation tasks.
The summary shows one best compatible source result per canonical product. Versions, effort settings and execution systems remain attached to the underlying records.
Scores from different versions or harnesses may not be interchangeable. The published source rows preserve those distinctions and their original units. A source result is not automatically an input to a current index.
This catalogue entry preserves available source evidence. Current indices admit only their specifically reviewed tracks and configurations.
Contamination risk: Low. Lifecycle: Active.