ResearchLLM Verifications Leaderboard

Data as of · 78 models, 80 questions · reviewed by Suhas Bhairav · methodology

Head to head · tested 27 Oct 2026

GPT-6.1 Sol vs GPT-6 Astra: accuracy, speed and price

Similar accuracy; GPT-6.1 Sol costs less per question.

OpenAIGPT-6.1 Sol76.2% score · #12$0.0029 per question41 tok/sOpenAIGPT-6 Astra76.2% score · #12$0.013 per question49 tok/s

Verdict

Built from the measurements below

  • Accuracy is too close to call: GPT-6.1 Sol scored 76.2% and GPT-6 Astra 76.2% on the same 80 questions, a gap within what chance alone could produce.
  • GPT-6.1 Sol is 4.7× cheaper per question as billed ($0.0029 vs $0.013), reasoning tokens included.
  • GPT-6 Astra generates text 1.2× faster: 49 tokens per second against 41.
  • GPT-6 Astra starts answering sooner: 1.3 s to the first token, against 2.1 s for GPT-6.1 Sol.

Which should you choose?

Choose GPT-6.1 Sol for the lower cost per correct answer ($0.0037 against $0.017). Choose GPT-6 Astra for faster streaming and a quicker first token.

Accuracy gap +0.0 points (z = 0.00). A winner is called only when z is at least 1.96, the usual 95% threshold. Speed, latency and price need a 10% margin.

Head to head

Same questions, same prompt, same API

MeasureGPT-6.1 SolGPT-6 AstraEdge
Verification scoreHigher is better76.2%76.2%Too close to call
Cost per questionLower is better$0.0029$0.013GPT-6.1 Sol
Output speedHigher is better4149GPT-6 Astra
Time to first tokenLower is better2.1 s1.3 sGPT-6 Astra
End-to-end response timeLower is better10.8 s8.9 sGPT-6 Astra
Tokens per questionLower is better224205Similar
Context windowHigher is better1.1M1.1MSimilar

Side by side

Bars are scaled to the larger of the two values. The winner on each measure is marked in bold.

Every measure

GPT-6.1 Sol first, GPT-6 Astra second

Verification scorehigher is better
GPT-6.1 Sol76.2%
GPT-6 Astra76.2%
Cost per questionlower is better
GPT-6.1 Sol$0.0029
GPT-6 Astra$0.013
Output speedhigher is better
GPT-6.1 Sol41
GPT-6 Astra49
Time to first tokenlower is better
GPT-6.1 Sol2.1 s
GPT-6 Astra1.3 s
End-to-end response timelower is better
GPT-6.1 Sol10.8 s
GPT-6 Astra8.9 s
Tokens per questionlower is better
GPT-6.1 Sol224
GPT-6 Astra205
Context windowhigher is better
GPT-6.1 Sol1.1M
GPT-6 Astra1.1M

Score vs. cost per question

Both models in color, every other model in grey

Most attractive quadrant0255075100$0.00001$0.0001$0.001$0.01$0.10Cost per question (USD, log) →Verification score (%) →Qwen3.8 2.4T A95BCommand AReka Flash 3Gemma 4 26B A4BGemma 4 31BQwen3.5 397B A17BHermes 4 405BGPT-6 AstraGrok 4.7o3gpt-oss-20bMinistral 3 3B 2512Nova Micro 1.0Phi 4Granite 4.2 8BHy3GLM 5.3 FlashSolar Pro 4Trinity Large ThinkingMiniMax M3Mistral Large 4Claude Opus 5.5GPT-6.1 SolGemini 4 ArgonGPT-6 Lunagpt-oss-120bLlama 4 Maverick

Specifications and pricing

From OpenRouter's catalogue, plus the leaderboard's test dates

SpecificationGPT-6.1 SolGPT-6 Astra
CreatorOpenAIOpenAI
Released29 Sept 20264 Sept 2026
Weights——
ReasoningYesYes
Inputfile, image, textfile, image, text
Outputtexttext
Context window1.1M tokens1.1M tokens
Knowledge cutoff——
List price in / out per 1M$2 / $10$10 / $50
Blended price per 1M (3:1)$4.00$20.00
Cheapest hostOpenAI · $1 / $5OpenAI · $5 / $25
Hosts on OpenRouter33
Last tested25 Oct 202627 Oct 2026

Compare any two models →

GPT-6.1 Sol vs GPT-6 Astra: frequently asked questions

Is GPT-6.1 Sol better than GPT-6 Astra?
On accuracy they are statistically tied: GPT-6.1 Sol scored 76.2% and GPT-6 Astra 76.2% on the same 80 questions from open datasets. Similar accuracy; GPT-6.1 Sol costs less per question.
Which is cheaper, GPT-6.1 Sol or GPT-6 Astra?
GPT-6.1 Sol is cheaper: $0.0029 per question as billed, against $0.013. List prices: GPT-6.1 Sol $2 in / $10 out, GPT-6 Astra $10 in / $50 out per million tokens.
Which is faster, GPT-6.1 Sol or GPT-6 Astra?
GPT-6 Astra is faster at 49 output tokens per second, against 41. Time to first token: 2.1 s for GPT-6.1 Sol, 1.3 s for GPT-6 Astra.
Which has the larger context window, GPT-6.1 Sol or GPT-6 Astra?
Both accept about the same amount of context: 1.1M and 1.1M tokens.