Noometry

Model comparison

Claude Opus 4.7 vs GPT-5 Mini

Claude Opus 4.7 is the stronger model overall, scoring 58.4 to 41.7 on the Noometry Index. GPT-5 Mini costs 15× less per token, which makes it the better buy when Claude Opus 4.7's lead doesn't matter for your workload.

Last verified . 45 shared benchmarks.

Claude Opus 4.7 Anthropic

58.4

Rank #17 Confirmed

GPT-5 Mini OpenAI

41.7

Rank #115 Confirmed

Summary

  • They share 45 benchmarks with published results for both. Claude Opus 4.7 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 4.7 leads 53.7 to 24.1.
  • The biggest single-benchmark swing is ARC-AGI-2: 75.8% for Claude Opus 4.7 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 4.7.
  • Claude Opus 4.7 accepts more context: 1M tokens versus 400K.

Side by side

Claude Opus 4.7GPT-5 Mini
ProviderAnthropicOpenAI
Noometry Index58.441.7
Released2026-04-142025-08-07
WeightsProprietaryProprietary
Context window1M400K
Max output128K128K
Input $ / M tokens$5$0.25
Output $ / M tokens$25$2
Results tracked6660

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

Category by category

Coding Claude Opus 4.7 leads

Claude Opus 4.7: 59.9 (#10), GPT-5 Mini: 40.0 (#134)

BenchmarkClaude Opus 4.7GPT-5 Mini
SWE-bench Verified83.5%64.7%
SciCode54.5%39.2%
WeirdML76.4%52.7%
LMArena Coding15191406
ALE-Bench1,323799.77
FrontierCode38.5%—
SWE-bench Verified (bash only)—59.8%
LMArena WebDev1557—
SWE-bench Multilingual—39.7%
GSO44.1%—
MirrorCode31.1%—
AlgoTune—1.38

Agentic & Tool Use Claude Opus 4.7 leads

Claude Opus 4.7: 47.9 (#8), GPT-5 Mini: 31.0 (#64)

BenchmarkClaude Opus 4.7GPT-5 Mini
Terminal-Bench80.2%34.8%
Vending-Bench 210,937-31.18
APEX-Agents49.2%—
Berkeley Function Calling Leaderboard—55.5%
OSWorld 2.018.2%—
τ²-bench Banking40.2%—
PostTrainBench28.6%—
ExploitBench26.5%—
GBAEval43.8%—
GDP.pdf21%—
LMArena Search1233—

Reasoning Claude Opus 4.7 leads

Claude Opus 4.7: 53.7 (#24), GPT-5 Mini: 24.1 (#153)

BenchmarkClaude Opus 4.7GPT-5 Mini
ARC-AGI-275.8%4.4%
Kagi LLM Benchmark80.7%70.3%
ARC-AGI-193.5%54.3%
CritPt12%0%
Chess Puzzles30%30%
LMArena Hard Prompts15071380
Mystery Game Puzzles28%10%
DTBench94.7%80.5%
LMCA52.2%34.2%
Epoch Capabilities Index156.39145.51
ForecastBench60.361
SimpleBench61.7%—
NYT Connections (extended)39%—
EnigmaEval—8.2%
Thematic Generalization72.8%—
EBR-Bench19%—

Math Claude Opus 4.7 leads

Claude Opus 4.7: 66.5 (#20), GPT-5 Mini: 46.3 (#59)

BenchmarkClaude Opus 4.7GPT-5 Mini
FrontierMath (Tiers 1-3)70.2%46.7%
FrontierMath Tier 431.7%12.2%
OTIS Mock AIME 2024-202597.8%86.7%
ProofBench54%9%
LMArena Math14991377
FrontierMath (Feb 2025 set)43.8%27.2%
FrontierMath Tier 4 (v1)22.9%6.3%
MathArena Final-Answer Competitions73.6%—
Omni-MATH—72.2%
MATH Level 5—97.8%

Knowledge Claude Opus 4.7 leads

Claude Opus 4.7: 62.6 (#20), GPT-5 Mini: 45.5 (#80)

BenchmarkClaude Opus 4.7GPT-5 Mini
GPQA Diamond90.2%75%
Humanity's Last Exam36.2%19.4%
SimpleQA Verified51.7%21.6%
Vectara Hallucination Rate12%12.9%
LMArena Expert15211377
MMLU-Pro—83.5%
Confabulations—13.3%
GPQA (HELM)—75.6%

Multimodal Claude Opus 4.7 leads

Claude Opus 4.7: 41.5 (#29), GPT-5 Mini: 35.0 (#80)

BenchmarkClaude Opus 4.7GPT-5 Mini
LMArena Vision13171202
VPCT—40.2%
Blueprint-Bench 224.5%—
Furniture Assembly33.3%—
LMArena Document1495—

Multilingual Claude Opus 4.7 leads

Claude Opus 4.7: 57.5 (#9), GPT-5 Mini: 49.1 (#131)

BenchmarkClaude Opus 4.7GPT-5 Mini
LMArena Non-English14811363
LMArena Chinese15301387
LMArena French15051385
LMArena German14941366
LMArena Japanese14721342
LMArena Korean14661306
LMArena Russian14941362
LMArena Spanish14971355

Instruction Following Claude Opus 4.7 leads

Claude Opus 4.7: 78.6 (#9), GPT-5 Mini: 76.4 (#43)

BenchmarkClaude Opus 4.7GPT-5 Mini
LMArena Instruction Following14981357
IFEval—92.7%

Long Context Claude Opus 4.7 leads

Claude Opus 4.7: 46.1 (#24), GPT-5 Mini: 41.9 (#127)

BenchmarkClaude Opus 4.7GPT-5 Mini
LMArena Longer Query15051355
Fiction.LiveBench—69.4%

Writing & Preference Claude Opus 4.7 leads

Claude Opus 4.7: 75.3 (#8), GPT-5 Mini: 55.4 (#143)

BenchmarkClaude Opus 4.7GPT-5 Mini
LMArena Text14911373
LMArena Creative Writing14861325
EQ-Bench Creative Writing19141313
LMArena Multi-Turn15061363
Short-Story Creative Writing—83.1%
WildBench—85.5%
EQ-Bench 41311—

Frequently asked questions

Is Claude Opus 4.7 better than GPT-5 Mini?

Claude Opus 4.7 is the stronger model overall, scoring 58.4 to 41.7 on the Noometry Index. GPT-5 Mini costs 15× less per token, which makes it the better buy when Claude Opus 4.7's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 4.7 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 4.7 lists at $5 and $25.

Is Claude Opus 4.7 or GPT-5 Mini better for coding?

Claude Opus 4.7 scores higher on coding benchmarks: 59.9 versus 40.0 in the Noometry coding category.

Which has the bigger context window?

Claude Opus 4.7 does, with 1M tokens against 400K.

How many benchmarks do Claude Opus 4.7 and GPT-5 Mini share?

45 benchmarks have published results for both models. Claude Opus 4.7 has 66 scored results on Noometry and GPT-5 Mini has 60.

Related comparisons

Go deeper