Skip to main content
BenchLM
Advertise

Model comparison

Claude Opus 4.6 vs GPT-5.2

Data verified

Head-to-head evidence from 23 shared benchmark results across 7 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

68.59/100
Margin
10.2pts
← winning
GPT-5.2
OpenAI
58.43/100
2 category wins3 category wins

Public leaderboard positions: Claude Opus 4.6 #16 (Supported); GPT-5.2 #64 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Claude Opus 4.6 and GPT-5.2 share 23 comparable benchmark results. 5 of 8 categories are comparable. 23 results are unique to Claude Opus 4.6; 5 to GPT-5.2.

Updated July 20, 2026
Shared results
23
Claude Opus 4.6 only
23
GPT-5.2 only
5
Comparable categories
5 / 8

Pick Claude Opus 4.6 if you want the stronger benchmark profile. GPT-5.2 only becomes the better choice if knowledge is the priority or you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 23 shared benchmark results across 7 evidence categories; 5 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Claude Opus 4.6 is clearly ahead on the BenchAlign aggregate, 68.59 to 58.43. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Claude Opus 4.6's sharpest advantage is in agentic, where it averages 73 against 55.7. The single biggest benchmark swing on the page is OSWorld-Verified, 72.7% to 47.3%. GPT-5.2 does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.

Claude Opus 4.6 is also the more expensive model on tokens at $5.00 input / $25.00 output per 1M tokens, versus $1.75 input / $14.00 output per 1M tokens for GPT-5.2. GPT-5.2 is the reasoning model in the pair, while Claude Opus 4.6 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. Claude Opus 4.6 gives you the larger context window at 1M, compared with 400K for GPT-5.2.

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 Opus 4.6 and GPT-5.2
CategoryClaude Opus 4.6ΔGPT-5.2
KnowledgeClaude Opus 4.669.1Margin→ 23.3GPT-5.292.4
AgenticClaude Opus 4.673.0Margin← 17.3GPT-5.255.7
MultimodalClaude Opus 4.677.3Margin→ 3.1GPT-5.280.4
CodingClaude Opus 4.668.1Margin→ 2.5GPT-5.270.6
MathClaude Opus 4.636.3Margin← 1.1GPT-5.235.2
ReasoningClaude Opus 4.6Not measuredMarginNo overlapGPT-5.252.9

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · Claude Opus 4.6B · GPT-5.2

  1. OSWorld-Verified

    Agentic
    Source ↗
    A 72.7%B 47.3%
    Winner: Claude Opus 4.6Δ 25.4
    OSWorld-Verified: Claude Opus 4.6 scored 72.7%; GPT-5.2 scored 47.3%. Claude Opus 4.6 wins this benchmark.

  2. BrowseComp

    Agentic
    Source ↗
    A 83.7%B 65.8%
    Winner: Claude Opus 4.6Δ 17.9
    BrowseComp: Claude Opus 4.6 scored 83.7%; GPT-5.2 scored 65.8%. Claude Opus 4.6 wins this benchmark.

  3. FrontierMath v2 (Tier 4)

    Math
    Source ↗
    A 22.900%B 18.800%
    Winner: Claude Opus 4.6Δ 4.1
    FrontierMath v2 (Tier 4): Claude Opus 4.6 scored 22.900%; GPT-5.2 scored 18.800%. Claude Opus 4.6 wins this benchmark.

  4. SWE-bench Pro

    Coding
    Source ↗
    A 53.4%B 55.6%
    Winner: GPT-5.2Δ 2.2
    SWE-bench Pro: Claude Opus 4.6 scored 53.4%; GPT-5.2 scored 55.6%. GPT-5.2 wins this benchmark.

  5. MMMU-Pro

    Multimodal
    Source ↗
    A 77.3%B 79.5%
    Winner: GPT-5.2Δ 2.2
    MMMU-Pro: Claude Opus 4.6 scored 77.3%; GPT-5.2 scored 79.5%. GPT-5.2 wins this benchmark.

Operational comparison

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

MetricClaude Opus 4.6GPT-5.2Comparison
Input / output priceUSD per 1M tokensClaude Opus 4.6$5 input / $25 outputGPT-5.2$1.75 input / $14 outputGPT-5.2 has the lower combined listed price.
Generation speedtokens per secondClaude Opus 4.640 tok/sGPT-5.273 tok/sGPT-5.2 has the higher measured throughput.
First-answer latencyseconds to first tokenClaude Opus 4.61.78 sGPT-5.2130.34 sClaude Opus 4.6 reaches the first token sooner.
Context windowmaximum listed tokensClaude Opus 4.61MGPT-5.2400KClaude Opus 4.6 lists the larger context window.

Benchmark Deep Dive

AgenticClaude Opus 4.6 wins
BenchmarkClaude Opus 4.6GPT-5.2Result
Terminal-Bench 2.0Source 65.4%—Not comparable
BrowseCompSource 83.7%65.8%Claude Opus 4.6 leads
OSWorld-VerifiedSource 72.7%47.3%Claude Opus 4.6 leads
τ²-bench resultsSource 84.8%84.8%Tie
Claw-EvalSource 70.4%—Not comparable
DeepSearchQASource 73.7%—Not comparable
CyberGymSource 66.6%—Not comparable
Gert LabsSource 61.85%46.54%Claude Opus 4.6 leads
ResearchClawBenchSource 19.9%—Not comparable
JobBenchSource 36.7%34.3%Claude Opus 4.6 leads
CodingGPT-5.2 wins
BenchmarkClaude Opus 4.6GPT-5.2Result
SWE-bench VerifiedSource 80.8%80%Claude Opus 4.6 leads
SWE-bench Verified*Source 75.6%—Not comparable
LiveCodeBench ProSource 70.7%—Not comparable
SWE-bench ProSource 53.4%55.6%GPT-5.2 leads
SWE-RebenchSource 65.3%—Not comparable
React Native EvalsSource 84.1%—Not comparable
Vibe Code BenchSource 57.57%53.50%Claude Opus 4.6 leads
AA-SciCodeSource 45.7%52.1%GPT-5.2 leads
FrontierCode 1.1 MainSource 26.9%—Not comparable
Reasoning
BenchmarkClaude Opus 4.6GPT-5.2Result
AA-LCRSource 58.3%72.7%GPT-5.2 leads
CritPtSource 2.8%11.6%GPT-5.2 leads
ARC-AGI-2Source —52.9%Not comparable
KnowledgeGPT-5.2 wins
BenchmarkClaude Opus 4.6GPT-5.2Result
GPQASource 91.3%92.4%GPT-5.2 leads
GPQA-DSource 89.2%—Not comparable
SuperGPQASource 95%—Not comparable
MMLU-ProSource 82%—Not comparable
MMLU-Pro (Arcee)Source 89.1%—Not comparable
HLESource 53%—Not comparable
HLE w/o toolsSource 40%—Not comparable
HealthBench HardSource 14.8%—Not comparable
MedXpertQA (Text)Source 52.1%—Not comparable
Artificial Analysis Intelligence IndexSource 37.8%42.2%GPT-5.2 leads
AA-GPQA DiamondSource 84.0%90.3%GPT-5.2 leads
AA-HLESource 18.6%35.4%GPT-5.2 leads
AA-Omniscience IndexSource 3.5%-1.0%Claude Opus 4.6 leads
AA-Omniscience AccuracySource 45.2%43.8%Claude Opus 4.6 leads
AA-Omniscience Hallucination RateSource 76.0%79.7%Claude Opus 4.6 leads
MathClaude Opus 4.6 wins
BenchmarkClaude Opus 4.6GPT-5.2Result
AIME25 (Arcee)Source 99.8%—Not comparable
FrontierMath v2 (Tiers 1-3)Source 40.700%40.700%Tie
FrontierMath v2 (Tier 4)Source 22.900%18.800%Claude Opus 4.6 leads
AA AIME 2025Source —99.0%Not comparable
MultimodalGPT-5.2 wins
BenchmarkClaude Opus 4.6GPT-5.2Result
MMMU-ProSource 77.3%79.5%GPT-5.2 leads
ERQASource 51.6%—Not comparable
ScreenSpot ProSource 83.1%—Not comparable
MedXpertQA (MM)Source 64.8%—Not comparable
AA-MMMU-ProSource 72.5%—Not comparable
Design Arena WebsiteSource 13281227Claude Opus 4.6 leads
MathVisionSource —83.0%Not comparable
CharXivSource —82.1%Not comparable
V*Source —75.9%Not comparable
Inst. Following
BenchmarkClaude Opus 4.6GPT-5.2Result
AA-IFBenchSource 44.6%75.4%GPT-5.2 leads
Frequently Asked Questions (6)

Which is better, Claude Opus 4.6 or GPT-5.2?

Claude Opus 4.6 is ahead on BenchLM's BenchAlign leaderboard, 68.59 to 58.43. The biggest single separator in this matchup is OSWorld-Verified, where the scores are 72.7% and 47.3%.

Which is better for knowledge tasks, Claude Opus 4.6 or GPT-5.2?

GPT-5.2 has the edge for knowledge tasks in this comparison, averaging 92.4 versus 69.1. Inside this category, AA-HLE is the benchmark that creates the most daylight between them.

Which is better for coding, Claude Opus 4.6 or GPT-5.2?

GPT-5.2 has the edge for coding in this comparison, averaging 70.6 versus 68.1. Inside this category, AA-SciCode is the benchmark that creates the most daylight between them.

Which is better for math, Claude Opus 4.6 or GPT-5.2?

Claude Opus 4.6 has the edge for math in this comparison, averaging 36.3 versus 35.2. Inside this category, FrontierMath v2 (Tier 4) is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Claude Opus 4.6 or GPT-5.2?

Claude Opus 4.6 has the edge for agentic tasks in this comparison, averaging 73 versus 55.7. Inside this category, OSWorld-Verified is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, Claude Opus 4.6 or GPT-5.2?

GPT-5.2 has the edge for multimodal and grounded tasks in this comparison, averaging 80.4 versus 77.3. Inside this category, Design Arena Website is the benchmark that creates the most daylight between them.

Related Comparisons

Explore More

Anthropic Compare Pricing Methodology Find Your Best LLM Overall Rankings
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.