DataLearner logo

Claude Sonnet 4.6vsGPT-5.2

Across 9 shared benchmarks, Claude Sonnet 4.6 leads overall: Claude Sonnet 4.6 wins 8, GPT-5.2 wins 1, with 0 ties and an average score difference of +20.83.

Anthropic
Claude Sonnet 4.6

Anthropic · 2026-02-17 · Chat model

OpenAI
GPT-5.2

OpenAI · 2025-12-11 · Chat model

Claude Sonnet 4.68 wins(89%)(11%)1 winGPT-5.2

Benchmark scores

Grouped by capability, sorted by largest gap within each. 9 shared benchmarks.

Agent Level Benchmark

Claude Sonnet 4.6 2/2
BenchmarkClaude Sonnet 4.6GPT-5.2Diff
τ²-Bench - Telecom79.50115 / 264Normal (With Tools)46.50178 / 264Normal (With Tools)+33
Terminal Bench Hard46.2029 / 244Normal (With Tools)31.80100 / 244Normal (With Tools)+14.40

General Knowledge

Claude Sonnet 4.6 2/2
BenchmarkClaude Sonnet 4.6GPT-5.2Diff
HLE13.30355 / 563Normal (No Tools) · Text only8419 / 563Normal (No Tools) · Text only+5.30
CritPt0.90158 / 200Normal (No Tools)0.60168 / 200Normal (No Tools)+0.30

General Evaluation

Claude Sonnet 4.6 1/1
BenchmarkClaude Sonnet 4.6GPT-5.2Diff
GPQA Diamond79.90237 / 462Normal (No Tools)73.23298 / 462Normal (No Tools)+6.67

Instruction Following

GPT-5.2 1/1
BenchmarkClaude Sonnet 4.6GPT-5.2Diff
IF Bench42.40201 / 282Normal (No Tools)47.40168 / 282Normal (No Tools)-5

Long Context

Claude Sonnet 4.6 1/1
BenchmarkClaude Sonnet 4.6GPT-5.2Diff
AA-LCR69.30107 / 170Normal (No Tools)45.70144 / 170Normal (No Tools)+23.60

Multimodal Understanding

Claude Sonnet 4.6 1/1
BenchmarkClaude Sonnet 4.6GPT-5.2Diff
MMMU-Pro70.60123 / 227Normal (No Tools)65.80148 / 227Normal (No Tools)+4.80

Writing and Creative Capabilities

Claude Sonnet 4.6 1/1
BenchmarkClaude Sonnet 4.6GPT-5.2Diff
Creative Writing1,80418 / 106Normal (No Tools)1,70026 / 106Normal (No Tools)+104.40

Specs

FieldClaude Sonnet 4.6GPT-5.2
PublisherAnthropicOpenAI
Release date2026-02-172025-12-11
Model typeChat modelChat model
ArchitectureDenseDense
ParametersNot availableNot available
Context length1M400K
Max output8KNot available

API pricing

Prices use DataLearner records when available; missing fields are not inferred.

ItemClaude Sonnet 4.6GPT-5.2
Text input$3 / 1M tokens$1.75 / 1M tokens
Text output$15 / 1M tokens$14 / 1M tokens
Cache read$0.3 / 1M tokens$0.175 / 1M tokens
Cache write$3.75 / 1M tokens$1.75 / 1M tokens

Summary

  • Claude Sonnet 4.6leads in:Agent Level Benchmark (2/2), General Knowledge (2/2), General Evaluation (1/1), Long Context (1/1), Multimodal Understanding (1/1), Writing and Creative Capabilities (1/1)
  • GPT-5.2leads in:Instruction Following (1/1)

On average across the 9 shared benchmarks, Claude Sonnet 4.6 scores 20.83 higher.

Largest single-benchmark gap: Creative Writing — Claude Sonnet 4.6 1,804 vs GPT-5.2 1,700 (+104.40).

Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.