LingOly-TOO
Linguistics reasoning benchmark evaluating models on baseline and obfuscated questions to separate reasoning ability from memorization.
16rows
obfuscated_scoreprimary metric
2026-05-06sampled
Metadata
Metrics
Obfuscated Score, Baseline Score
| Rank | Subject | Obfuscated Score | Model Match | Provenance | Sampled |
|---|---|---|---|---|---|
| 1 | GPT-5 | 0.47 |  GPT-5 openai-gpt-5 | Imported | 2026-05-06 |
| 2 | Claude Opus 4.1 | 0.46 |  Claude Opus 4.1 anthropic-claude-opus-4.1 | Imported | 2026-05-06 |
| 3 | Claude 3.7 Sonnet | 0.43 | Claude 3.7 Sonnet anthropic-claude-3.7-sonnet | Imported | 2026-05-06 |
| 4 | Gemini 2.5 Pro | 0.42 |  Gemini 2.5 Pro google-gemini-2.5-pro | Imported | 2026-05-06 |
| 5 | DeepSeek-V3.1-Terminus | 0.42 |  DeepSeek V3.1 Terminus deepseek-deepseek-v3.1-terminus | Imported | 2026-05-06 |
| 6 | o1-preview | 0.32 | o1-preview openai-o1-preview | Imported | 2026-05-06 |
| 7 | o3-mini (high) | 0.31 | o3 Mini High openai-o3-mini-high | Imported | 2026-05-06 |
| 8 | Claude 3.5 Sonnet | 0.28 | Claude 3.5 Sonnet anthropic-claude-3.5-sonnet | Imported | 2026-05-06 |
| 9 | DeepSeek R1 | 0.26 | R1 deepseek-r1 | Imported | 2026-05-06 |
| 10 | GPT 4.5 | 0.25 | GPT-4.5 openai-gpt-4.5-preview | Imported | 2026-05-06 |
| 11 | Gemini 1.5 Pro | 0.20 | — | Imported | 2026-05-06 |
| 12 | GPT 4o | 0.16 | GPT-4o openai-gpt-4o | Imported | 2026-05-06 |
| 13 | o3-mini (low) | 0.12 | o3-mini openai-o3-mini | Imported | 2026-05-06 |
| 14 | Phi4 | 0.11 |  Phi 4 microsoft-phi-4 | Imported | 2026-05-06 |
| 15 | Llama 3.3 70B-Instruct | 0.08 |  Llama 3.3 70B Instruct meta-llama-llama-3.3-70b-instruct | Imported | 2026-05-06 |
| 16 | Aya 23 35B | 0.06 | — | Imported | 2026-05-06 |
No matching rows.