Bertrande

Best model for writing articles

Which model should I use to write articles?

As of 18 September 2026, the model ranking first for this question is Claude Opus 4.7 on Anthropic, with intelligence index 55.0 and an output price of $25.00 per million tokens. Ranked by highest intelligence index, then lowest output price at equal index, across 117 models for which we hold both figures. This ranking ignores speed and reliability: it is a query on price and a relayed capability score, not a verdict on which model serves you best.

How this ranking is built

Criterion: highest intelligence index, then lowest output price at equal index. Long-form writing is a general reasoning task, so the ranking uses the general intelligence index. Price breaks ties, because two models that score the same are not worth the same.

This is a query, not an opinion. Both figures are shown on every row so you can check the order, and the table sorts on any column if you disagree with our criterion.

Two things to know before trusting this table. Capability scores are published by Artificial Analysis and relayed by the catalogue we read. They are not our measurement, and a score measures the model rather than the seller, so we apply it to every seller of that model. This ranking says nothing about speed or reliability, which we measure only in part: availability is published per upstream host in reliability.json and on the model pages, and we publish no latency at all, for reasons given on the data page. Prices are ours to observe, each carries the date we saw it, and we keep only the cheapest offer per model so that batch and free tiers do not crowd out the answer.

#ModelSellerIntelligence index/ 10040 of 40 heldScale from 3.8 to 55Input$ / 1M tokens40 of 40 heldScale from $0.0001 to $600Output$ / 1M tokens40 of 40 heldScale from $0.0001 to $600Contexttokens24 of 40 heldScale from 512 to 2MObserved
1Claude Opus 4.7Anthropic first party55.0$5.00$25.00n/a18 September 2026
2Qwen/Qwen3.8-MaxDeepInfra53.4$1.65$4.951256 00015 September 2026
3Claude Fable 5.1Anthropic first party53.4$10.00$50.001 000 00018 September 2026
4OpenAI: GPT-5.4OpenRouter53.1$2.50$15.001 050 00018 September 2026
5gpt-6-astraOpenAI first party52.8$10.00$50.00n/a18 September 2026
6Claude Opus 5Anthropic first party50.7$5.00$25.001 000 00018 September 2026
7Claude Fable 5Anthropic first party49.7$10.00$50.001 000 00018 September 2026
8gpt-5.6-solOpenAI first party47.1$4.00$20.00n/a18 September 2026
9Qwen: Qwen3.8 Max (0902)OpenRouter45.4$2.00$6.001 000 00016 September 2026
10GLM-5.3Z.ai first party44.9$1.40$4.40n/a18 September 2026
11grok-4.6xAI first party44.4$2.00$6.00500 00018 September 2026
12kimi-k3Moonshot AI first party43.8$3.00$15.001 048 57618 September 2026
13gpt-5.6-terraOpenAI first party42.3$2.00$12.00n/a18 September 2026
14Claude Opus 4.8Anthropic first party42.0$5.00$25.00n/a18 September 2026
15GLM-5.3-FlashZ.ai first party41.9$0.150$0.500n/a18 September 2026
16Nex AGI: Nex-N2-ProOpenRouter41.7$0.250$1.00262 1448 September 2026
17Upstage: Solar Pro 4OpenRouter41.6$0.090$0.360524 28818 September 2026
18Gemini 3.8 FlashGoogle first party41.2$0.750$3.75n/a18 September 2026
19grok-build-0.1xAI first party40.7$1.00$2.00256 00018 September 2026
20Qwen: Qwen3.6 PlusOpenRouter40.5$0.325$1.951 000 00018 September 2026
21Qwen/Qwen3.8-2.4T-A95BDeepInfra40.0$2.00$6.00262 14418 September 2026
22Meta: Muse Spark 1.2OpenRouter39.8$1.25$4.251 048 57618 September 2026
23deepseek-ai/DeepSeek-V4.1-FlashDeepInfra39.5$0.200$0.6001 048 57618 September 2026
24Gemini 3.7 FlashGoogle first party39.4$0.750$3.75n/a18 September 2026
25grok-4.5xAI first party39.1$2.00$6.00500 00018 September 2026
26OpenAI: GPT-5.5OpenRouter38.6$5.00$30.001 050 00018 September 2026
27Claude Sonnet 5Anthropic first party38.4$2.00$10.001 000 00018 September 2026
28gpt-5.6-lunaOpenAI first party37.5$0.200$1.20n/a18 September 2026
29gpt-5.1OpenAI first party37.5$1.25$10.00n/a18 September 2026
30DeepSeek: DeepSeek V4 Pro 0813OpenRouter36.3$0.57816$1.734481 048 57618 September 2026
31kimi-k2.5Moonshot AI first party36.0$0.600$3.00262 14418 September 2026
32gpt-5OpenAI first party35.3$1.25$10.00n/a18 September 2026
33DeepSeek: DeepSeek V4 Flash 0731OpenRouter34.5$0.060$0.1201 310 72018 September 2026
34GLM-4.7Z.ai first party34.5$0.600$2.20n/a11 September 2026
35Gemini 3.6 FlashGoogle first party34.3$0.750$3.75n/a18 September 2026
36Meta: Muse Spark 1.1OpenRouter34.3$1.25$4.251 048 57618 September 2026
37GLM-5.2Z.ai first party34.0$1.40$4.40n/a18 September 2026
38Qwen/Qwen3.8-27BCerebras first party33.9$0.990$1.4965 53618 September 2026
39Kwaipilot: KAT-Coder-Pro V2OpenRouter33.7$0.300$1.20262 14418 September 2026
40Gemini 3.5 FlashGoogle first party33.0$1.50$9.00n/a18 September 2026

117 models meet this criterion. The table shows the first 40, so 77 ranked below the cut are not listed here; the full catalogue holds them all.

A model missing from this table is missing one of the two figures, not judged. We would rather show a shorter list than fill it with guesses.

Other questions we can answer this way