cd /news/large-language-models/gpt-6-2-sol-is-a-regression-for-deep… · home › topics › large-language-models › article
[ARTICLE · art-172425] src=vincentschmalbach.com ↗ pub= topic=large-language-models verified=true sentiment=↓ negative

GPT-6.2 Sol Is a Regression for Deep Research

Vincent Schmalbach, who builds the article tool UnSpar, reverted UnSpar's deep research from GPT-6.2 Sol back to GPT-6.1 Sol after finding that OpenAI's November 17 release produced shorter, less detailed reports despite lower per-task cost. In a blind test across eight research topics graded by Claude Opus 5.5, GPT-6.2 Sol won 1 topic to GPT-6.1 Sol's 4 (plus 1 leaning), won 0 topics on depth to 6.1's 4, and averaged 1,390 words and 46 relevant details per report against 2,610 words and 51 details for 6.1. GPT-6.2 Sol is priced the same as 6.1 at $2 per million input tokens and $10 per million output tokens, and Artificial Analysis scores it 57 points at $1.01 per task versus 55 points at $1.27 for 6.1; Schmalbach wrote that raising reasoning effort to max still yielded about 1,200 words and 36 details per report, so "I don't count research that finds less for less money as cheaper.

recommendation

Judge model upgrades with blind, order-swapped pairwise comparisons that weigh depth and count concrete details, not just key-fact accuracy or index scores, before switching a production pipeline.

more in playbook: Evals and testing for LLM apps
read3 min views6 publishedNov 19, 2026
GPT-6.2 Sol Is a Regression for Deep Research
Image: Vincentschmalbach (auto-discovered)

Microsoft Shows How Not to Introduce AI in Your Business

Since Thursday afternoon I can't use my Outlook. On November 12 Microsoft 365 went down worldwide. Exchange Online, which runs the email,…

GPT-6.2 Sol is a clear regression from GPT-6.1 Sol for deep research. I switched deep research in UnSpar, the article tool I build, to 6.2 the day after OpenAI released it, and switched back the next morning. 6.2 writes research reports half as long as 6.1, with fewer details and fewer citations, and turning up the reasoning effort doesn't change that.

OpenAI released GPT-6.2 Sol on November 17 at the same price as 6.1, $2 per million input tokens and $10 per million output tokens. Artificial Analysis gives it 57 points on its index at $1.01 per task, against 55 points and $1.27 for 6.1. It looked smarter and cheaper, so I switched.

My first test agreed. I ran eight research topics, once through each model and had Claude Opus 5.5 grade the reports blind. Both models got nearly all of the five key questions per topic right. 6.2 won three topics head to head and 6.1 won one, and 6.2 was 18% cheaper and more than twice as fast. I deployed it. The same test also showed 6.2's reports at 1,370 words against 2,580, with 18 cited links instead of 26. I had built the test to check whether the key facts were right.

For the second test I had the judge list every concrete detail in each report and weigh depth as much as correctness, without counting length. Each pair was judged twice with the order swapped, and a topic only counts when both rounds agree. This time 6.2 also got a higher reasoning setting than 6.1.

|  | GPT-6.1 Sol | GPT-6.2 Sol (higher reasoning) | 
|---|---|---|

| Topics won (of 8) | 4, plus 1 leaning | 1 | | Topics won on depth | 4 | 0 | | Relevant details per report | 51 | 46 | | Words per report | 2,610 | 1,390 |

At the same reasoning setting, 6.2 used about 2,600 reasoning tokens per report where 6.1 used 7,100. With GPT-5.6 Sol I had the opposite problem, it used twice the tokens of the model before it. So I suspected the setting and turned it up. On two of the topics, 6.2 at max reasoned almost twice as much as 6.1 (10,600 tokens against 5,900), still wrote about 1,200 words, and listed 36 details per report, against 48 for 6.1 and 45 for itself one setting lower.

The price per token didn't change, so all of the savings come from 6.2 thinking and writing less. With the higher setting the saving shrinks to 8%. I don't count research that finds less for less money as cheaper.

So Deep research in UnSpar is back on 6.1.

Give Vroni a GitHub issue, bug report, spec, or rough idea. It reads the repo, plans the change, writes code, runs checks, and works toward a review-ready pull request.

Take a look at vroni.com

── more in #large-language-models 4 stories · sorted by recency
── more on @openai 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/gpt-6-2-sol-is-a-reg…] indexed:0 read:3min 2026-11-19 · —