ResearchLLM Verifications Leaderboard

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

Head to head · tested 27 Oct 2026

GPT-5.6 Terra vs Qwen3.8 Max (0902): accuracy, speed and price

Similar accuracy; GPT-5.6 Terra costs less per question.

OpenAIGPT-5.6 Terra75.0% score · #15$0.0063 per question101 tok/sQwenQwen3.8 Max (0902)75.0% score · #15$0.011 per question46 tok/s

Verdict

Built from the measurements below

  • Accuracy is too close to call: GPT-5.6 Terra scored 75.0% and Qwen3.8 Max (0902) 75.0% on the same 80 questions, a gap within what chance alone could produce.
  • GPT-5.6 Terra is 1.8× cheaper per question as billed ($0.0063 vs $0.011), reasoning tokens included.
  • GPT-5.6 Terra generates text 2.2× faster: 101 tokens per second against 46.

Which should you choose?

Choose GPT-5.6 Terra for the lower cost per correct answer ($0.0084 against $0.015), faster streaming, shorter outputs (about 472 tokens per question against 1,722) and more hosts to choose from on OpenRouter (3 against 1). The widest subject gap is in medicine: Qwen3.8 Max (0902) answered 6 of 11 correctly, GPT-5.6 Terra 4 of 11. With so few questions per subject, treat this as a lead to test on your own prompts, not a result.

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-5.6 TerraQwen3.8 Max (0902)Edge
Verification scoreHigher is better75.0%75.0%Too close to call
Cost per questionLower is better$0.0063$0.011GPT-5.6 Terra
Output speedHigher is better10146GPT-5.6 Terra
Time to first tokenLower is better1.1 s1.2 sSimilar
End-to-end response timeLower is better5.3 s12.2 sGPT-5.6 Terra
Tokens per questionLower is better4721,722GPT-5.6 Terra
Context windowHigher is better1.1M1MSimilar

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-5.6 Terra first, Qwen3.8 Max (0902) second

Verification scorehigher is better
GPT-5.6 Terra75.0%
Qwen3.8 Max (0902)75.0%
Cost per questionlower is better
GPT-5.6 Terra$0.0063
Qwen3.8 Max (0902)$0.011
Output speedhigher is better
GPT-5.6 Terra101
Qwen3.8 Max (0902)46
Time to first tokenlower is better
GPT-5.6 Terra1.1 s
Qwen3.8 Max (0902)1.2 s
End-to-end response timelower is better
GPT-5.6 Terra5.3 s
Qwen3.8 Max (0902)12.2 s
Tokens per questionlower is better
GPT-5.6 Terra472
Qwen3.8 Max (0902)1,722
Context windowhigher is better
GPT-5.6 Terra1.1M
Qwen3.8 Max (0902)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 405BGrok 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 MaverickQwen3.8 Max (0902)

Specifications and pricing

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

SpecificationGPT-5.6 TerraQwen3.8 Max (0902)
CreatorOpenAIQwen
Released9 Jul 20263 Sept 2026
Weights——
ReasoningYesYes
Inputfile, image, texttext, image, video
Outputtexttext
Context window1.1M tokens1M tokens
Knowledge cutoff16 Feb 2026—
List price in / out per 1M$2 / $12$2 / $6
Blended price per 1M (3:1)$4.50$3.00
Cheapest hostOpenAI · $1 / $6Alibaba · $2 / $6
Hosts on OpenRouter31
Last tested27 Oct 202625 Oct 2026

Compare any two models →

GPT-5.6 Terra vs Qwen3.8 Max (0902): frequently asked questions

Is GPT-5.6 Terra better than Qwen3.8 Max (0902)?
On accuracy they are statistically tied: GPT-5.6 Terra scored 75.0% and Qwen3.8 Max (0902) 75.0% on the same 80 questions from open datasets. Similar accuracy; GPT-5.6 Terra costs less per question.
Which is cheaper, GPT-5.6 Terra or Qwen3.8 Max (0902)?
GPT-5.6 Terra is cheaper: $0.0063 per question as billed, against $0.011. List prices: GPT-5.6 Terra $2 in / $12 out, Qwen3.8 Max (0902) $2 in / $6 out per million tokens.
Which is faster, GPT-5.6 Terra or Qwen3.8 Max (0902)?
GPT-5.6 Terra is faster at 101 output tokens per second, against 46. Time to first token: 1.1 s for GPT-5.6 Terra, 1.2 s for Qwen3.8 Max (0902).
Which has the larger context window, GPT-5.6 Terra or Qwen3.8 Max (0902)?
Both accept about the same amount of context: 1.1M and 1M tokens.