Skip to main content
BenchLM

Model comparison

Claude Opus 4.8 vs GPT-5.4 mini

Data verified

Head-to-head evidence from 26 shared benchmark results across 6 categories. Overall scores shown here use BenchLM's provisional ranking lane.

85/100
Margin
20.0pts
← winning
65/100
4 category wins0 category wins

Verified leaderboard positions: Claude Opus 4.8 #3; GPT-5.4 mini unranked

Evidence parity. Claude Opus 4.8 and GPT-5.4 mini share 26 comparable benchmark results. 4 of 8 categories are comparable. 27 results are unique to Claude Opus 4.8; 5 to GPT-5.4 mini.

Updated July 12, 2026
Shared results
26
Claude Opus 4.8 only
27
GPT-5.4 mini only
5
Comparable categories
4 / 8

Pick Claude Opus 4.8 if you want the stronger benchmark profile. GPT-5.4 mini only becomes the better choice if you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 26 shared benchmark results across 6 evidence categories; 4 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 4.8 is clearly ahead on the provisional aggregate, 85 to 65. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Claude Opus 4.8's sharpest advantage is in mathematics, where it averages 53.9 against 21.7. The single biggest benchmark swing on the page is FrontierMath v2 (Tier 4), 31.250% to 2.080%.

Claude Opus 4.8 is also the more expensive model on tokens at $5.00 input / $25.00 output per 1M tokens, versus $0.75 input / $4.50 output per 1M tokens for GPT-5.4 mini. That is roughly 5.6x on output cost alone. Claude Opus 4.8 gives you the larger context window at 1M, compared with 400K for GPT-5.4 mini.

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 4.8 and GPT-5.4 mini
CategoryClaude Opus 4.8ΔGPT-5.4 mini
MathClaude Opus 4.853.9Margin← 32.2GPT-5.4 mini21.7
KnowledgeClaude Opus 4.862.7Margin← 14.9GPT-5.4 mini47.8
AgenticClaude Opus 4.880.3Margin← 14.6GPT-5.4 mini65.7
MultimodalClaude Opus 4.877.0Margin← 0.4GPT-5.4 mini76.6
CodingClaude Opus 4.876.4MarginNo overlapGPT-5.4 miniNot measured

Decisive benchmark drivers

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

More
A · Claude Opus 4.8B · GPT-5.4 mini

  1. FrontierMath v2 (Tier 4)

    Math
    Source ↗
    A 31.250%B 2.080%
    Winner: Claude Opus 4.8Δ 29.2
    FrontierMath v2 (Tier 4): Claude Opus 4.8 scored 31.250%; GPT-5.4 mini scored 2.080%. Claude Opus 4.8 wins this benchmark.

  2. FrontierMath v2 (Tiers 1-3)

    Math
    Source ↗
    A 47.241%B 28.280%
    Winner: Claude Opus 4.8Δ 19
    FrontierMath v2 (Tiers 1-3): Claude Opus 4.8 scored 47.241%; GPT-5.4 mini scored 28.280%. Claude Opus 4.8 wins this benchmark.

  3. HLE

    Knowledge
    Source ↗
    A 57.9%B 41.5%
    Winner: Claude Opus 4.8Δ 16.4
    HLE: Claude Opus 4.8 scored 57.9%; GPT-5.4 mini scored 41.5%. Claude Opus 4.8 wins this benchmark.

  4. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 74.6%B 60%
    Winner: Claude Opus 4.8Δ 14.6
    Terminal-Bench 2.0: Claude Opus 4.8 scored 74.6%; GPT-5.4 mini scored 60%. Claude Opus 4.8 wins this benchmark.

  5. OSWorld-Verified

    Agentic
    Source ↗
    A 83.4%B 72.1%
    Winner: Claude Opus 4.8Δ 11.3
    OSWorld-Verified: Claude Opus 4.8 scored 83.4%; GPT-5.4 mini scored 72.1%. Claude Opus 4.8 wins this benchmark.

Operational comparison

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

MetricClaude Opus 4.8GPT-5.4 miniComparison
Input / output priceUSD per 1M tokensClaude Opus 4.8$5 input / $25 outputGPT-5.4 mini$0.75 input / $4.5 outputGPT-5.4 mini has the lower combined listed price.
Generation speedtokens per secondClaude Opus 4.8Not availableGPT-5.4 mini201 tok/sA complete speed comparison is not available.
First-answer latencyseconds to first tokenClaude Opus 4.8Not availableGPT-5.4 mini3.85 sA complete latency comparison is not available.
Context windowmaximum listed tokensClaude Opus 4.81MGPT-5.4 mini400KClaude Opus 4.8 lists the larger context window.

Benchmark Deep Dive

AgenticClaude Opus 4.8 wins
BenchmarkClaude Opus 4.8GPT-5.4 miniResult
Terminal-Bench 2.0Source 74.6%60%Claude Opus 4.8 leads
BrowseCompSource 84.3%—Not comparable
DeepSearchQASource 93.1%—Not comparable
OSWorld-VerifiedSource 83.4%72.1%Claude Opus 4.8 leads
Finance Agent v2Source 53.9%—Not comparable
GDPval-AASource 16001170Claude Opus 4.8 leads
MCP AtlasSource 82.2%57.7%Claude Opus 4.8 leads
ToolathlonSource 59.9%42.9%Claude Opus 4.8 leads
Gert LabsSource 72.97%—Not comparable
AA Agentic IndexSource 47.2%30.2%Claude Opus 4.8 leads
Tau2-TelecomSource 94.4%83.3%Claude Opus 4.8 leads
GDPval-AASource 55.0%33.5%Claude Opus 4.8 leads
ResearchClawBenchSource 21.1%—Not comparable
OSWorld 2.0Source 20.6%—Not comparable
AA BriefcaseSource 1354—Not comparable
AA AutomationBenchSource 48.5%—Not comparable
AA EnterpriseOps-GymSource 44.0%—Not comparable
AA Harvey LABSource 7.5%—Not comparable
AA Tau3 BankingSource 27.6%—Not comparable
APEX-Agents-AASource —28.2%Not comparable
Coding
BenchmarkClaude Opus 4.8GPT-5.4 miniResult
SWE-bench VerifiedSource 88.6%—Not comparable
SWE-bench ProSource 69.2%—Not comparable
SWE MultilingualSource 84.4%—Not comparable
SWE MultimodalSource 38.4%—Not comparable
Terminal-Bench 2.0Source 74.6%—Not comparable
cursorBench31Source 58.4%—Not comparable
cursorBench32Source 62.3%—Not comparable
AA Coding IndexSource 74.3%56.1%Claude Opus 4.8 leads
Terminal-Bench HardSource 58.3%52.3%Claude Opus 4.8 leads
AA-SciCodeSource 53.5%49.9%Claude Opus 4.8 leads
FrontierCodeSource 46.5%27.0%Claude Opus 4.8 leads
AA Terminal-Bench 2.1Source 84.6%—Not comparable
Vibe Code BenchSource —47.97%Not comparable
Reasoning
BenchmarkClaude Opus 4.8GPT-5.4 miniResult
AA-LCRSource 67.7%69.3%GPT-5.4 mini leads
CritPtSource 20.9%10.0%Claude Opus 4.8 leads
KnowledgeClaude Opus 4.8 wins
BenchmarkClaude Opus 4.8GPT-5.4 miniResult
GPQASource 93.6%88%Claude Opus 4.8 leads
GPQA-DSource 93.6%—Not comparable
HLESource 57.9%41.5%Claude Opus 4.8 leads
HLE w/o toolsSource 49.8%28.2%Claude Opus 4.8 leads
Artificial Analysis Intelligence IndexSource 55.7%40.0%Claude Opus 4.8 leads
AA-GPQA DiamondSource 92.0%87.5%Claude Opus 4.8 leads
AA-HLESource 45.7%26.6%Claude Opus 4.8 leads
AA-Omniscience IndexSource 27.4%-18.7%Claude Opus 4.8 leads
AA-Omniscience AccuracySource 46.6%37.5%Claude Opus 4.8 leads
AA-Omniscience Hallucination RateSource 35.9%89.8%Claude Opus 4.8 leads
MathClaude Opus 4.8 wins
BenchmarkClaude Opus 4.8GPT-5.4 miniResult
USAMO 2026Source 96.7%—Not comparable
FrontierMath v2 (Tiers 1-3)Source 47.241%28.280%Claude Opus 4.8 leads
FrontierMath v2 (Tier 4)Source 31.250%2.080%Claude Opus 4.8 leads
Multilingual
BenchmarkClaude Opus 4.8GPT-5.4 miniResult
INCLUDESource 87.6%—Not comparable
MultimodalClaude Opus 4.8 wins
BenchmarkClaude Opus 4.8GPT-5.4 miniResult
OfficeQA ProSource 66.2%—Not comparable
ScreenSpot ProSource 87.9%—Not comparable
CharXivSource 89.9%—Not comparable
CharXiv w/o toolsSource 80.5%—Not comparable
Design Arena WebsiteSource 1281—Not comparable
MMMU-ProSource —76.6%Not comparable
MMMU-Pro w/ PythonSource —78%Not comparable
AA-MMMU-ProSource —73.3%Not comparable
Inst. Following
BenchmarkClaude Opus 4.8GPT-5.4 miniResult
AA-IFBenchSource 62.2%73.3%GPT-5.4 mini leads
Frequently Asked Questions (5)

Which is better, Claude Opus 4.8 or GPT-5.4 mini?

Claude Opus 4.8 is ahead on BenchLM's provisional leaderboard, 85 to 65. The biggest single separator in this matchup is FrontierMath v2 (Tier 4), where the scores are 31.250% and 2.080%.

Which is better for knowledge tasks, Claude Opus 4.8 or GPT-5.4 mini?

Claude Opus 4.8 has the edge for knowledge tasks in this comparison, averaging 62.7 versus 47.8. Inside this category, AA-Omniscience Hallucination Rate is the benchmark that creates the most daylight between them.

Which is better for math, Claude Opus 4.8 or GPT-5.4 mini?

Claude Opus 4.8 has the edge for math in this comparison, averaging 53.9 versus 21.7. 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 4.8 or GPT-5.4 mini?

Claude Opus 4.8 has the edge for agentic tasks in this comparison, averaging 80.3 versus 65.7. Inside this category, GDPval-AA is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, Claude Opus 4.8 or GPT-5.4 mini?

Claude Opus 4.8 has the edge for multimodal and grounded tasks in this comparison, averaging 77 versus 76.6. GPT-5.4 mini stays close enough that the answer can still flip depending on your workload.

Related Comparisons

Explore More

Anthropic Compare Pricing Methodology Find Your Best LLM Overall Rankings
Last updated: July 12, 2026

The AI models change fast. We track them for you.

A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.