Noometry

Model comparison

Claude Opus 4.8 vs GPT-5 Mini

Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 41.8 on the Noometry Index. GPT-5 Mini costs 15× less per token, which makes it the better buy when Claude Opus 4.8's lead doesn't matter for your workload.

Last verified . 42 shared benchmarks.

Claude Opus 4.8 Anthropic

60.7

Rank #13 Confirmed

GPT-5 Mini OpenAI

41.8

Rank #128 Confirmed

Summary

  • They share 42 benchmarks with published results for both. Claude Opus 4.8 scores higher in 10 categories and GPT-5 Mini in 0 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Opus 4.8 leads 64.7 to 23.9.
  • The biggest single-benchmark swing is ARC-AGI-2: 72.1% for Claude Opus 4.8 and 4.4% for GPT-5 Mini.
  • GPT-5 Mini is cheaper at $0.25 / $2 per million input/output tokens, against $5 / $25 for Claude Opus 4.8.
  • Claude Opus 4.8 accepts more context: 1M tokens versus 400K.

Side by side

Claude Opus 4.8GPT-5 Mini
ProviderAnthropicOpenAI
Noometry Index60.741.8
Released2026-05-282025-08-07
WeightsProprietaryProprietary
Context window1M400K
Max output128K128K
Input $ / M tokens$5$0.25
Output $ / M tokens$25$2
Results tracked6560

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Claude Opus 4.8 leads

Claude Opus 4.8: 59.9 (#12), GPT-5 Mini: 40.1 (#146)

BenchmarkClaude Opus 4.8GPT-5 Mini
SciCode53.5%39.2%
WeirdML82.9%52.7%
LMArena Coding14901406
ALE-Bench1,564799.77
SWE-bench Verified—64.7%
DeepSWE59%—
FrontierCode46.5%—
SWE-bench Verified (bash only)—59.8%
LMArena WebDev1556—
SWE-bench Multilingual—39.7%
GSO47.1%—
AlgoTune—1.38

Agentic & Tool Use Claude Opus 4.8 leads

Claude Opus 4.8: 47.6 (#11), GPT-5 Mini: 31.1 (#70)

BenchmarkClaude Opus 4.8GPT-5 Mini
Vending-Bench 25,787-31.18
Terminal-Bench—34.8%
APEX-Agents48.9%—
Berkeley Function Calling Leaderboard—55.5%
OSWorld 2.020.6%—
Remote Labor Index8.3%—
τ²-bench Banking39.7%—
DeepResearch Bench50.2%—
PostTrainBench33.8%—
GBAEval70.9%—
GDP.pdf24%—
LMArena Search1204—

Reasoning Claude Opus 4.8 leads

Claude Opus 4.8: 64.7 (#16), GPT-5 Mini: 23.9 (#168)

BenchmarkClaude Opus 4.8GPT-5 Mini
ARC-AGI-272.1%4.4%
Kagi LLM Benchmark88.8%70.3%
ARC-AGI-192.5%54.3%
CritPt20.9%0%
Chess Puzzles34%30%
EnigmaEval23.5%8.2%
LMArena Hard Prompts14821380
Mystery Game Puzzles36%10%
DTBench94.9%80.5%
LMCA57.5%34.2%
Epoch Capabilities Index158.21145.52
ForecastBench59.961
SimpleBench64.8%—
NYT Connections (extended)91.1%—
EBR-Bench28.6%—
Surface Evolver Bench87.5%—
Bench to the Future 30.14—

Math Claude Opus 4.8 leads

Claude Opus 4.8: 78.4 (#13), GPT-5 Mini: 46.7 (#69)

BenchmarkClaude Opus 4.8GPT-5 Mini
FrontierMath (Tiers 1-3)80%46.7%
FrontierMath Tier 456.1%12.2%
OTIS Mock AIME 2024-202598.3%86.7%
ProofBench69%9%
LMArena Math14871378
FrontierMath (Feb 2025 set)47.2%27.2%
FrontierMath Tier 4 (v1)31.3%6.3%
MathArena Final-Answer Competitions91.8%—
Omni-MATH—72.2%
MATH Level 5—97.8%

Knowledge Claude Opus 4.8 leads

Claude Opus 4.8: 61.3 (#29), GPT-5 Mini: 45.6 (#86)

BenchmarkClaude Opus 4.8GPT-5 Mini
GPQA Diamond91%75%
SimpleQA Verified53%21.6%
LMArena Expert15021379
Humanity's Last Exam—19.4%
MMLU-Pro—83.5%
Confabulations—13.3%
Vectara Hallucination Rate—12.9%
GPQA (HELM)—75.6%

Multimodal Claude Opus 4.8 leads

Claude Opus 4.8: 42.9 (#26), GPT-5 Mini: 35.6 (#85)

BenchmarkClaude Opus 4.8GPT-5 Mini
LMArena Vision12941202
VPCT—40.2%
Blueprint-Bench 214.5%—
Furniture Assembly42.5%—
LMArena Document1475—

Multilingual Claude Opus 4.8 leads

Claude Opus 4.8: 55.2 (#33), GPT-5 Mini: 48.9 (#137)

BenchmarkClaude Opus 4.8GPT-5 Mini
LMArena Non-English14501363
LMArena Chinese15071385
LMArena French14811386
LMArena German14721366
LMArena Japanese14401341
LMArena Korean14321308
LMArena Russian14741362
LMArena Spanish14661355

Instruction Following Claude Opus 4.8 leads

Claude Opus 4.8: 77.4 (#24), GPT-5 Mini: 76.2 (#46)

BenchmarkClaude Opus 4.8GPT-5 Mini
LMArena Instruction Following14761357
IFEval—92.7%

Long Context Claude Opus 4.8 leads

Claude Opus 4.8: 45.4 (#35), GPT-5 Mini: 41.9 (#132)

BenchmarkClaude Opus 4.8GPT-5 Mini
LMArena Longer Query14831355
Fiction.LiveBench—69.4%

Writing & Preference Claude Opus 4.8 leads

Claude Opus 4.8: 72.0 (#16), GPT-5 Mini: 55.2 (#148)

BenchmarkClaude Opus 4.8GPT-5 Mini
LMArena Text14611373
LMArena Creative Writing14541325
EQ-Bench Creative Writing18401313
LMArena Multi-Turn14761363
Short-Story Creative Writing—83.1%
WildBench—85.5%
EQ-Bench 41281—

Frequently asked questions

Is Claude Opus 4.8 better than GPT-5 Mini?

Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 41.8 on the Noometry Index. GPT-5 Mini costs 15× less per token, which makes it the better buy when Claude Opus 4.8's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 4.8 or GPT-5 Mini?

GPT-5 Mini is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; Claude Opus 4.8 lists at $5 and $25.

Is Claude Opus 4.8 or GPT-5 Mini better for coding?

Claude Opus 4.8 scores higher on coding benchmarks: 59.9 versus 40.1 in the Noometry coding category.

Which has the bigger context window?

Claude Opus 4.8 does, with 1M tokens against 400K.

How many benchmarks do Claude Opus 4.8 and GPT-5 Mini share?

42 benchmarks have published results for both models. Claude Opus 4.8 has 65 scored results on Noometry and GPT-5 Mini has 60.

Related comparisons

Go deeper