293 models ranked for journalism and news. Scored with bonuses for web search (fact-checking), large context (source analysis), large output (long-form articles), streaming, and reasoning.
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 ProOpenAI | 91 |
| 2 | GPT-5.2 ProOpenAI | 90 |
| 3 | GPT-5 ProOpenAI | 90 |
| 4 | o3 ProOpenAI | 82 |
| 5 | Claude Opus 4.1Anthropic | 81 |
| 6 | Claude Opus 4Anthropic | 76 |
| 7 | o3 Deep ResearchOpenAI | 74 |
| 8 | Claude Opus 4.6Anthropic | 71 |
| 9 | Claude Opus 4.5Anthropic | 70 |
| 10 | GPT-5.4OpenAI | 70 |
| 11 | o1-proOpenAI | 77 |
| 12 | Claude Sonnet 4.5Anthropic | 69 |
| 13 | Qwen3 VL 30B A3B ThinkingAlibaba | 69 |
| 14 | Qwen3 VL 235B A22B ThinkingAlibaba | 69 |
| 15 | GPT-5.2OpenAI | 68 |
| 16 | Claude Sonnet 4.6Anthropic | 68 |
| 17 | GPT-5.1OpenAI | 67 |
| 18 | GPT-5.3-CodexOpenAI | 67 |
| 19 | GPT-5.2-CodexOpenAI | 67 |
| 20 | GPT-5OpenAI | 67 |
| 21 | o4 Mini Deep ResearchOpenAI | 66 |
| 22 | GPT-5.1-Codex-MaxOpenAI | 66 |
| 23 | GPT-5 MiniOpenAI | 65 |
| 24 | GPT-5 NanoOpenAI | 64 |
| 25 | Grok 4.1 FastxAI | 64 |
| 26 | Grok 4 FastxAI | 64 |
| 27 | Claude Haiku 4.5Anthropic | 63 |
| 28 | o3OpenAI | 62 |
| 29 | o4 Mini HighOpenAI | 61 |
| 30 | o4 MiniOpenAI | 61 |
Web search models cross-reference claims against multiple sources in real-time. Reasoning models evaluate conflicting information and identify potential misinformation patterns.
Large context windows process entire court filings, financial reports, and government documents. Web search pulls current context to supplement stored knowledge.
Large output models produce long-form investigative pieces, feature articles, and multi-part series. Streaming delivers real-time drafts for deadline-driven newsrooms.
Models analyze datasets, spot trends, and generate data-driven story angles. JSON mode outputs structured findings that integrate with visualization tools and CMS platforms.