Skip to main content
BenchLM
Advertise

Model comparison

Claude Opus 4.5 vs GPT-5.3 Codex

Data verified

Head-to-head evidence from 19 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

64.22/100
Margin
2.5pts
winning →
66.69/100
1 category wins1 category wins

Public leaderboard positions: Claude Opus 4.5 #34 (Supported); GPT-5.3 Codex #26 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Claude Opus 4.5 and GPT-5.3 Codex share 19 comparable benchmark results. 2 of 8 categories are comparable. 40 results are unique to Claude Opus 4.5; 2 to GPT-5.3 Codex.

Updated July 20, 2026
Shared results
19
Claude Opus 4.5 only
40
GPT-5.3 Codex only
2
Comparable categories
2 / 8

Pick GPT-5.3 Codex if you want the stronger benchmark profile. Claude Opus 4.5 only becomes the better choice if coding is the priority or you would rather avoid the extra latency and token burn of a reasoning model.

Confidence note. This is a partial-evidence comparison with 19 shared benchmark results across 6 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

GPT-5.3 Codex has the cleaner BenchAlign overall profile here, landing at 66.69 versus 64.22. It is a real lead, but still close enough that category-level strengths matter more than the headline number.

GPT-5.3 Codex's sharpest advantage is in agentic, where it averages 71.4 against 62.6. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 59.3% to 77.3%. Claude Opus 4.5 does hit back in coding, so the answer changes if that is the part of the workload you care about most.

Claude Opus 4.5 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-5.3 Codex. GPT-5.3 Codex is the reasoning model in the pair, while Claude Opus 4.5 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. GPT-5.3 Codex gives you the larger context window at 400K, compared with 200K for Claude Opus 4.5.

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 4.5 and GPT-5.3 Codex
CategoryClaude Opus 4.5ΔGPT-5.3 Codex
AgenticClaude Opus 4.562.6Margin→ 8.8GPT-5.3 Codex71.4
CodingClaude Opus 4.571.7Margin← 4.5GPT-5.3 Codex67.2
ReasoningClaude Opus 4.564.4MarginNo overlapGPT-5.3 CodexNot measured
KnowledgeClaude Opus 4.558.1MarginNo overlapGPT-5.3 CodexNot measured
MathClaude Opus 4.557.5MarginNo overlapGPT-5.3 CodexNot measured
MultilingualClaude Opus 4.585.7MarginNo overlapGPT-5.3 CodexNot measured
MultimodalClaude Opus 4.569.9MarginNo overlapGPT-5.3 CodexNot measured
Inst. FollowingClaude Opus 4.569.5MarginNo overlapGPT-5.3 CodexNot measured

Decisive benchmark drivers

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

More
A · Claude Opus 4.5B · GPT-5.3 Codex

  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 59.3%B 77.3%
    Winner: GPT-5.3 CodexΔ 18
    Terminal-Bench 2.0: Claude Opus 4.5 scored 59.3%; GPT-5.3 Codex scored 77.3%. GPT-5.3 Codex wins this benchmark.

  2. SWE-bench Verified

    Coding
    Source ↗
    A 80.9%B 85%
    Winner: GPT-5.3 CodexΔ 4.1
    SWE-bench Verified: Claude Opus 4.5 scored 80.9%; GPT-5.3 Codex scored 85%. GPT-5.3 Codex wins this benchmark.

  3. OSWorld-Verified

    Agentic
    Source ↗
    A 66.3%B 64.7%
    Winner: Claude Opus 4.5Δ 1.6
    OSWorld-Verified: Claude Opus 4.5 scored 66.3%; GPT-5.3 Codex scored 64.7%. Claude Opus 4.5 wins this benchmark.

  4. SWE-bench Pro

    Coding
    Source ↗
    A 57.1%B 56.8%
    Winner: Claude Opus 4.5Δ 0.3
    SWE-bench Pro: Claude Opus 4.5 scored 57.1%; GPT-5.3 Codex scored 56.8%. Claude Opus 4.5 wins this benchmark.

Operational comparison

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

MetricClaude Opus 4.5GPT-5.3 CodexComparison
Input / output priceUSD per 1M tokensClaude Opus 4.5$5 input / $25 outputGPT-5.3 Codex$1.75 input / $14 outputGPT-5.3 Codex has the lower combined listed price.
Generation speedtokens per secondClaude Opus 4.546 tok/sGPT-5.3 Codex79 tok/sGPT-5.3 Codex has the higher measured throughput.
First-answer latencyseconds to first tokenClaude Opus 4.51.01 sGPT-5.3 Codex88.26 sClaude Opus 4.5 reaches the first token sooner.
Context windowmaximum listed tokensClaude Opus 4.5200KGPT-5.3 Codex400KGPT-5.3 Codex lists the larger context window.

Benchmark Deep Dive

AgenticGPT-5.3 Codex wins
BenchmarkClaude Opus 4.5GPT-5.3 CodexResult
Terminal-Bench 2.0Source 59.3%77.3%GPT-5.3 Codex leads
OSWorld-VerifiedSource 66.3%64.7%Claude Opus 4.5 leads
OSWorldSource 66.3%—Not comparable
Claw-EvalSource 59.6%—Not comparable
QwenClawBenchSource 52.3%—Not comparable
τ³-bench resultsSource 70.2%—Not comparable
VITA-BenchSource 23.3%—Not comparable
DeepPlanningSource 26.4%—Not comparable
ToolathlonSource 43.5%—Not comparable
MCP AtlasSource 42.3%—Not comparable
MCP-TasksSource 71.8%—Not comparable
WideResearchSource 76.4%—Not comparable
CyberGymSource 50.6%—Not comparable
τ²-bench resultsSource 86.3%86%Claude Opus 4.5 leads
Gert LabsSource 64.23%57.47%Claude Opus 4.5 leads
JobBenchSource 32.3%33.7%GPT-5.3 Codex leads
CodingClaude Opus 4.5 wins
BenchmarkClaude Opus 4.5GPT-5.3 CodexResult
SWE-bench VerifiedSource 80.9%85%GPT-5.3 Codex leads
LiveCodeBench v6Source 84.8%—Not comparable
SWE-bench ProSource 57.1%56.8%Claude Opus 4.5 leads
SWE MultilingualSource 77.5%—Not comparable
NL2RepoSource 43.2%—Not comparable
AA-SciCodeSource 47.0%53.2%GPT-5.3 Codex leads
SWE-RebenchSource —58.2%Not comparable
Vibe Code BenchSource —61.77%Not comparable
Reasoning
BenchmarkClaude Opus 4.5GPT-5.3 CodexResult
LongBench v2Source 64.4%—Not comparable
AI-NeedleSource 74%—Not comparable
AA-LCRSource 65.3%74.0%GPT-5.3 Codex leads
CritPtSource 0.3%16.9%GPT-5.3 Codex leads
Knowledge
BenchmarkClaude Opus 4.5GPT-5.3 CodexResult
GPQASource 87%—Not comparable
SuperGPQASource 70.6%—Not comparable
MMLU-ProSource 89.5%—Not comparable
MMLU-ReduxSource 96.6%—Not comparable
C-EvalSource 92.2%—Not comparable
HLESource 30.8%—Not comparable
Artificial Analysis Intelligence IndexSource 34.7%44.3%GPT-5.3 Codex leads
AA-GPQA DiamondSource 81.0%91.5%GPT-5.3 Codex leads
AA-HLESource 12.9%39.9%GPT-5.3 Codex leads
AA-Omniscience IndexSource -3.9%9.9%GPT-5.3 Codex leads
AA-Omniscience AccuracySource 40.7%51.8%GPT-5.3 Codex leads
AA-Omniscience Hallucination RateSource 75.4%86.9%Claude Opus 4.5 leads
AA MMLU-ProSource 88.9%—Not comparable
Math
BenchmarkClaude Opus 4.5GPT-5.3 CodexResult
AIME26Source 95.1%—Not comparable
HMMT Feb 2025Source 92.9%—Not comparable
HMMT Nov 2025Source 93.3%—Not comparable
HMMT Feb 2026Source 85.3%—Not comparable
MMAnswerBenchSource 84.0%—Not comparable
FrontierMath v2 (Tiers 1-3)Source 20.690%—Not comparable
FrontierMath v2 (Tier 4)Source 4.167%—Not comparable
Multilingual
BenchmarkClaude Opus 4.5GPT-5.3 CodexResult
MMLU-ProXSource 85.7%—Not comparable
NOVA-63Source 56.7%—Not comparable
Multimodal
BenchmarkClaude Opus 4.5GPT-5.3 CodexResult
MMMU-ProSource 70.6%—Not comparable
MathVisionSource 74.3%—Not comparable
CharXivSource 68.5%—Not comparable
VideoMMMUSource 84.4%—Not comparable
ScreenSpot ProSource 45.7%—Not comparable
V*Source 67.0%—Not comparable
AA-MMMU-ProSource 71.2%78.5%GPT-5.3 Codex leads
Design Arena WebsiteSource 12791195Claude Opus 4.5 leads
Inst. Following
BenchmarkClaude Opus 4.5GPT-5.3 CodexResult
IFEvalSource 90.9%—Not comparable
IFBenchSource 58%—Not comparable
AA-IFBenchSource 43.0%75.4%GPT-5.3 Codex leads
Frequently Asked Questions (3)

Which is better, Claude Opus 4.5 or GPT-5.3 Codex?

GPT-5.3 Codex is ahead on BenchLM's BenchAlign leaderboard, 66.69 to 64.22. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 59.3% and 77.3%.

Which is better for coding, Claude Opus 4.5 or GPT-5.3 Codex?

Claude Opus 4.5 has the edge for coding in this comparison, averaging 71.7 versus 67.2. Inside this category, AA-SciCode is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Claude Opus 4.5 or GPT-5.3 Codex?

GPT-5.3 Codex has the edge for agentic tasks in this comparison, averaging 71.4 versus 62.6. Inside this category, Terminal-Bench 2.0 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.