ResearchLLM Verifications Leaderboard

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

Head to head · tested 27 Oct 2026

Gemini 3.1 Pro Preview vs GPT-5.3-Codex: accuracy, speed and price

Similar accuracy; GPT-5.3-Codex costs less per question.

GoogleGemini 3.1 Pro Preview77.5% score · #9$0.017 per question124 tok/sOpenAIGPT-5.3-Codex82.5% score · #3$0.01 per question95 tok/s

Verdict

Built from the measurements below

  • Accuracy is too close to call: Gemini 3.1 Pro Preview scored 77.5% and GPT-5.3-Codex 82.5% on the same 80 questions, a gap within what chance alone could produce.
  • GPT-5.3-Codex is 1.7× cheaper per question as billed ($0.01 vs $0.017), reasoning tokens included.
  • Gemini 3.1 Pro Preview generates text 1.3× faster: 124 tokens per second against 95.
  • GPT-5.3-Codex starts answering sooner: 1.4 s to the first token, against 3.4 s for Gemini 3.1 Pro Preview.
  • Gemini 3.1 Pro Preview accepts more context: 1M tokens against 400k.

Which should you choose?

Choose Gemini 3.1 Pro Preview for faster streaming and a 1M-token context window. Choose GPT-5.3-Codex for the lower cost per correct answer ($0.013 against $0.022), a quicker first token and shorter outputs (about 699 tokens per question against 1,382).

Accuracy gap -5.0 points (z = -0.79). 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

MeasureGemini 3.1 Pro PreviewGPT-5.3-CodexEdge
Verification scoreHigher is better77.5%82.5%Too close to call
Cost per questionLower is better$0.017$0.01GPT-5.3-Codex
Output speedHigher is better12495Gemini 3.1 Pro Preview
Time to first tokenLower is better3.4 s1.4 sGPT-5.3-Codex
End-to-end response timeLower is better8.9 s5.2 sGPT-5.3-Codex
Tokens per questionLower is better1,382699GPT-5.3-Codex
Context windowHigher is better1M400kGemini 3.1 Pro Preview

Side by side

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

Every measure

Gemini 3.1 Pro Preview first, GPT-5.3-Codex second

Verification scorehigher is better
Gemini 3.1 Pro Preview77.5%
GPT-5.3-Codex82.5%
Cost per questionlower is better
Gemini 3.1 Pro Preview$0.017
GPT-5.3-Codex$0.01
Output speedhigher is better
Gemini 3.1 Pro Preview124
GPT-5.3-Codex95
Time to first tokenlower is better
Gemini 3.1 Pro Preview3.4 s
GPT-5.3-Codex1.4 s
End-to-end response timelower is better
Gemini 3.1 Pro Preview8.9 s
GPT-5.3-Codex5.2 s
Tokens per questionlower is better
Gemini 3.1 Pro Preview1,382
GPT-5.3-Codex699
Context windowhigher is better
Gemini 3.1 Pro Preview1M
GPT-5.3-Codex400k

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 405BMuse WonderGrok 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-5.4GPT-6 Lunagpt-oss-120bLlama 4 Maverick

Specifications and pricing

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

SpecificationGemini 3.1 Pro PreviewGPT-5.3-Codex
CreatorGoogleOpenAI
Released19 Feb 202624 Feb 2026
Weights——
ReasoningYesYes
Inputaudio, file, image, text, videotext, image, file
Outputtexttext
Context window1M tokens400k tokens
Knowledge cutoff——
List price in / out per 1M$2 / $12$1.75 / $14
Blended price per 1M (3:1)$4.50$4.81
Cheapest hostGoogle · $1 / $6Azure · $1.75 / $14
Hosts on OpenRouter22
Last tested26 Oct 202627 Oct 2026

Compare any two models →

Gemini 3.1 Pro Preview vs GPT-5.3-Codex: frequently asked questions

Is Gemini 3.1 Pro Preview better than GPT-5.3-Codex?
On accuracy they are statistically tied: Gemini 3.1 Pro Preview scored 77.5% and GPT-5.3-Codex 82.5% on the same 80 questions from open datasets. Similar accuracy; GPT-5.3-Codex costs less per question.
Which is cheaper, Gemini 3.1 Pro Preview or GPT-5.3-Codex?
GPT-5.3-Codex is cheaper: $0.01 per question as billed, against $0.017. List prices: Gemini 3.1 Pro Preview $2 in / $12 out, GPT-5.3-Codex $1.75 in / $14 out per million tokens.
Which is faster, Gemini 3.1 Pro Preview or GPT-5.3-Codex?
Gemini 3.1 Pro Preview is faster at 124 output tokens per second, against 95. Time to first token: 3.4 s for Gemini 3.1 Pro Preview, 1.4 s for GPT-5.3-Codex.
Which has the larger context window, Gemini 3.1 Pro Preview or GPT-5.3-Codex?
Gemini 3.1 Pro Preview, with 1M tokens against 400k.