ResearchLLM Verifications Leaderboard

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

Head to head · tested 27 Oct 2026

Claude Sonnet 5.5 vs GPT-5.3-Codex: accuracy, speed and price

Similar accuracy; Claude Sonnet 5.5 costs less per question.

AnthropicClaude Sonnet 5.578.8% score · #7$0.0054 per question126 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: Claude Sonnet 5.5 scored 78.8% and GPT-5.3-Codex 82.5% on the same 80 questions, a gap within what chance alone could produce.
  • Claude Sonnet 5.5 is 1.9× cheaper per question as billed ($0.0054 vs $0.01), reasoning tokens included.
  • Claude Sonnet 5.5 generates text 1.3× faster: 126 tokens per second against 95.
  • Claude Sonnet 5.5 starts answering sooner: 0.7 s to the first token, against 1.4 s for GPT-5.3-Codex.
  • Claude Sonnet 5.5 accepts more context: 1M tokens against 400k.

Which should you choose?

Choose Claude Sonnet 5.5 for the lower cost per correct answer ($0.0069 against $0.013), faster streaming, a quicker first token, shorter outputs (about 456 tokens per question against 699), a 1M-token context window and more hosts to choose from on OpenRouter (5 against 2).

Accuracy gap -3.7 points (z = -0.60). 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

MeasureClaude Sonnet 5.5GPT-5.3-CodexEdge
Verification scoreHigher is better78.8%82.5%Too close to call
Cost per questionLower is better$0.0054$0.01Claude Sonnet 5.5
Output speedHigher is better12695Claude Sonnet 5.5
Time to first tokenLower is better0.7 s1.4 sClaude Sonnet 5.5
End-to-end response timeLower is better6.2 s5.2 sGPT-5.3-Codex
Tokens per questionLower is better456699Claude Sonnet 5.5
Context windowHigher is better1M400kClaude Sonnet 5.5

Side by side

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

Every measure

Claude Sonnet 5.5 first, GPT-5.3-Codex second

Verification scorehigher is better
Claude Sonnet 5.578.8%
GPT-5.3-Codex82.5%
Cost per questionlower is better
Claude Sonnet 5.5$0.0054
GPT-5.3-Codex$0.01
Output speedhigher is better
Claude Sonnet 5.5126
GPT-5.3-Codex95
Time to first tokenlower is better
Claude Sonnet 5.50.7 s
GPT-5.3-Codex1.4 s
End-to-end response timelower is better
Claude Sonnet 5.56.2 s
GPT-5.3-Codex5.2 s
Tokens per questionlower is better
Claude Sonnet 5.5456
GPT-5.3-Codex699
Context windowhigher is better
Claude Sonnet 5.51M
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

SpecificationClaude Sonnet 5.5GPT-5.3-Codex
CreatorAnthropicOpenAI
Released28 Sept 202624 Feb 2026
Weights——
ReasoningYesYes
Inputtext, image, filetext, image, file
Outputtexttext
Context window1M tokens400k tokens
Knowledge cutoff——
List price in / out per 1M$2 / $10$1.75 / $14
Blended price per 1M (3:1)$4.00$4.81
Cheapest hostGoogle · $2 / $10Azure · $1.75 / $14
Hosts on OpenRouter52
Last tested25 Oct 202627 Oct 2026

Compare any two models →

Claude Sonnet 5.5 vs GPT-5.3-Codex: frequently asked questions

Is Claude Sonnet 5.5 better than GPT-5.3-Codex?
On accuracy they are statistically tied: Claude Sonnet 5.5 scored 78.8% and GPT-5.3-Codex 82.5% on the same 80 questions from open datasets. Similar accuracy; Claude Sonnet 5.5 costs less per question.
Which is cheaper, Claude Sonnet 5.5 or GPT-5.3-Codex?
Claude Sonnet 5.5 is cheaper: $0.0054 per question as billed, against $0.01. List prices: Claude Sonnet 5.5 $2 in / $10 out, GPT-5.3-Codex $1.75 in / $14 out per million tokens.
Which is faster, Claude Sonnet 5.5 or GPT-5.3-Codex?
Claude Sonnet 5.5 is faster at 126 output tokens per second, against 95. Time to first token: 0.7 s for Claude Sonnet 5.5, 1.4 s for GPT-5.3-Codex.
Which has the larger context window, Claude Sonnet 5.5 or GPT-5.3-Codex?
Claude Sonnet 5.5, with 1M tokens against 400k.