Skip to main content

Model comparison

Claude 4 Sonnet vs GPT-5.2-Codex

Data verified

Head-to-head evidence from 14 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

42.79/100
Margin
16.3pts
winning →
59.1/100
0 category wins0 category wins

Public leaderboard positions: Claude 4 Sonnet #158 (Supported); GPT-5.2-Codex #58 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Claude 4 Sonnet and GPT-5.2-Codex share 14 comparable benchmark results. 0 of 8 categories are comparable. 2 results are unique to Claude 4 Sonnet; 1 to GPT-5.2-Codex.

Updated July 20, 2026
Shared results
14
Claude 4 Sonnet only
2
GPT-5.2-Codex only
1
Comparable categories
0 / 8

Benchmark data for Claude 4 Sonnet and GPT-5.2-Codex is coming soon on BenchLM.

Confidence note. This is a partial-evidence comparison with 14 shared benchmark results across 6 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.

Claude 4 Sonnet is priced at $3.00 input / $15.00 output per 1M tokens, versus $1.75 input / $14.00 output per 1M tokens for GPT-5.2-Codex. GPT-5.2-Codex has the larger context window at 400K, compared with 200K for Claude 4 Sonnet.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for Claude 4 Sonnet and GPT-5.2-Codex
CategoryClaude 4 SonnetΔGPT-5.2-Codex
CodingClaude 4 Sonnet72.7MarginNo overlapGPT-5.2-CodexNot measured

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricClaude 4 SonnetGPT-5.2-CodexComparison
Input / output priceUSD per 1M tokensClaude 4 Sonnet$3 input / $15 outputGPT-5.2-Codex$1.75 input / $14 outputGPT-5.2-Codex has the lower combined listed price.
Generation speedtokens per secondClaude 4 Sonnet40 tok/sGPT-5.2-Codex123 tok/sGPT-5.2-Codex has the higher measured throughput.
First-answer latencyseconds to first tokenClaude 4 Sonnet1.33 sGPT-5.2-Codex87.34 sClaude 4 Sonnet reaches the first token sooner.
Context windowmaximum listed tokensClaude 4 Sonnet200KGPT-5.2-Codex400KGPT-5.2-Codex lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkClaude 4 SonnetGPT-5.2-CodexResult
τ²-bench resultsSource 52.3%92.1%GPT-5.2-Codex leads
Gert LabsSource 39.66%51.79%GPT-5.2-Codex leads
JobBenchSource 18.4%26.0%GPT-5.2-Codex leads
Coding
BenchmarkClaude 4 SonnetGPT-5.2-CodexResult
SWE-bench VerifiedSource 72.7%Not comparable
AA-SciCodeSource 37.3%54.6%GPT-5.2-Codex leads
Vibe Code BenchSource 37.91%Not comparable
Reasoning
BenchmarkClaude 4 SonnetGPT-5.2-CodexResult
AA-LCRSource 44.3%75.7%GPT-5.2-Codex leads
CritPtSource 1.1%8.7%GPT-5.2-Codex leads
Knowledge
BenchmarkClaude 4 SonnetGPT-5.2-CodexResult
Artificial Analysis Intelligence IndexSource 25.5%40.1%GPT-5.2-Codex leads
AA-GPQA DiamondSource 68.3%89.9%GPT-5.2-Codex leads
AA-HLESource 4.0%33.5%GPT-5.2-Codex leads
AA-Omniscience IndexSource -9.2%-2.5%GPT-5.2-Codex leads
AA-Omniscience AccuracySource 22.4%40.7%GPT-5.2-Codex leads
AA-Omniscience Hallucination RateSource 40.8%72.8%Claude 4 Sonnet leads
Multimodal
BenchmarkClaude 4 SonnetGPT-5.2-CodexResult
AA-MMMU-ProSource 62.4%76.3%GPT-5.2-Codex leads
Design Arena WebsiteSource 1178Not comparable
Inst. Following
BenchmarkClaude 4 SonnetGPT-5.2-CodexResult
AA-IFBenchSource 45.4%77.6%GPT-5.2-Codex leads
Frequently Asked Questions (3)

Can I compare Claude 4 Sonnet and GPT-5.2-Codex on BenchLM yet?

Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.

Why does this comparison show “coming soon”?

BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.

What data is available for Claude 4 Sonnet and GPT-5.2-Codex today?

Claude 4 Sonnet: $3.00 input / $15.00 output per 1M tokens GPT-5.2-Codex: $1.75 input / $14.00 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.

Related Comparisons

Last updated: July 20, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.