Benchmark
ARC-AGI v2
Scores are percentages.
All reasoning benchmarksScores from LLM Stats data.
- Models measured
- 20
- Scores recorded
- 20
- Sources
- 1
- IQ weight
- 1.37
Score distribution
- 45.4%
- Mean
- 49.3%
- Median
- 27.5%
- Std dev
- 6.5%
- 10th percentile
- 77.1%
- 90th percentile
- 1.5%
- Min
This benchmark has a weight of 1.37 for chat models, measured over 20 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | GPT-6 Astra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 95% |
| 2 | GPT 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 85% |
| 3 | Gemini 3.1 Pro Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 77.1% |
| 4 | GPT 5.4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 73.3% |
| 5 | Gemini 3.5 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 72.1% |
| 6 | Claude Opus 4.6· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 68.8% |
| 7 | Claude Sonnet 4.6· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 58.3% |
| 8 | GPT-5.2 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 54.2% |
| 9 | GPT 5.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 52.9% |
| 10 | Inkling 2 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 49.3% |
| 11 | Muse Spark· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 42.5% |
| 12 | Inkling Small· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 40.1% |
| 13 | Claude Opus 4.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 37.6% |
| 14 | Gemini 3 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 33.6% |
| 15 | Gemini 3 Pro Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 31.1% |
| 16 | Grok 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 15.9% |
| 17 | Claude Opus 4· LLM Stats data | 8.6% |
| 18 | OpenAI o3· LLM Stats data | 6.5% |
| 19 | Gemini 2.5 Pro· LLM Stats data | 4.9% |
| 20 | Seed 2.0 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 1.5% |
Data credits: Data by LLM Stats