Lech Mazur Writing
Writing quality and style evaluation benchmark tracked in Epoch AI's capabilities dataset.
27rows
scoreprimary metric
2026-05-06sampled
Metadata
Metrics
Score, Standard error (lower is better)
| Rank | Subject | Score | Model Match | Provenance | Sampled |
|---|---|---|---|---|---|
| 1 | GPT-5.2 | 8.72 | GPT-5.2 openai-gpt-5.2 | Imported | 2026-05-06 |
| 2 | Qwen3-Max-Instruct | 8.71 | Qwen3 Max qwen-qwen3-max | Imported | 2026-05-06 |
| 3 | kimi-k2-thinking (official) | 8.69 | MoonshotAI: Kimi K2 Thinking moonshotai-kimi-k2-thinking | Imported | 2026-05-06 |
| 4 | o3 | 8.63 | o3 openai-o3 | Imported | 2026-05-06 |
| 5 | Gemini 2.5 Pro (Jun 2025) | 8.60 | Gemini 2.5 Pro google-gemini-2.5-pro | Imported | 2026-05-06 |
| 6 | Claude Opus 4.5 | 8.54 | Claude Opus 4.5 anthropic-claude-opus-4.5 | Imported | 2026-05-06 |
| 7 | DeepSeek V3 | 8.52 | DeepSeek V3 deepseek-deepseek-chat | Imported | 2026-05-06 |
| 8 | Qwen 3 235B | 8.49 | Qwen3 235B A22B qwen-qwen3-235b-a22b | Imported | 2026-05-06 |
| 9 | Qwen3-235B-A22B | 8.30 | Qwen3 235B A22B qwen-qwen3-235b-a22b | Imported | 2026-05-06 |
| 10 | DeepSeek R1 | 8.30 | R1 deepseek-r1 | Imported | 2026-05-06 |
| 11 | GPT-4o | 8.18 | GPT-4o openai-gpt-4o | Imported | 2026-05-06 |
| 12 | Grok 4 | 8.11 | Grok 4 x-ai-grok-4 | Imported | 2026-05-06 |
| 13 | Claude 3.7 Sonnet | 8.11 | Claude 3.7 Sonnet anthropic-claude-3.7-sonnet | Imported | 2026-05-06 |
| 14 | QwQ-32B | 8.07 | — | Imported | 2026-05-06 |
| 15 | Gemma 3 27B | 7.99 | Gemma 3 27B google-gemma-3-27b-it | Imported | 2026-05-06 |
| 16 | GPT-OSS 120B | 7.73 | gpt-oss-120b openai-gpt-oss-120b | Imported | 2026-05-06 |
| 17 | Grok-3 mini | 7.64 | Grok 3 Mini x-ai-grok-3-mini | Imported | 2026-05-06 |
| 18 | GPT-4.1 | 7.56 | GPT-4.1 openai-gpt-4.1 | Imported | 2026-05-06 |
| 19 | o4-mini-2025-04-16 medium | 7.50 | o4 Mini openai-o4-mini | Imported | 2026-05-06 |
| 20 | Gemini 2.0 Flash Thinking Exp | 7.38 | Gemini 2.0 Flash google-gemini-2.0-flash | Imported | 2026-05-06 |
| 21 | Claude 3.5 Haiku | 7.35 | Claude 3.5 Haiku anthropic-claude-3.5-haiku | Imported | 2026-05-06 |
| 22 | Qwen2.5-Max | 7.29 | — | Imported | 2026-05-06 |
| 23 | o1 | 7.02 | o1 openai-o1 | Imported | 2026-05-06 |
| 24 | Mistral Large | 6.90 | Mistral Large mistralai-mistral-large | Imported | 2026-05-06 |
| 25 | gpt-4o-mini-2024-07-18 | 6.72 | GPT-4o-mini (2024-07-18) openai-gpt-4o-mini-2024-07-18 | Imported | 2026-05-06 |
| 26 | Llama-4-Maverick-17B-128E-Instruct | 6.37 | Llama 4 Maverick meta-llama-4-maverick | Imported | 2026-05-06 |
| 27 | Phi-4 | 6.26 | Phi 4 microsoft-phi-4 | Imported | 2026-05-06 |
No matching rows.