Noometry

Model comparison

Claude Opus 4.7 vs o4-mini

Claude Opus 4.7 is the stronger model overall, scoring 58.3 to 41.6 on the Noometry Index. o4-mini costs 5.2× less per token, which makes it the better buy when Claude Opus 4.7's lead doesn't matter for your workload.

Last verified . 41 shared benchmarks.

Claude Opus 4.7 Anthropic

58.3

Rank #19 Confirmed

o4-mini OpenAI

41.6

Rank #132 Confirmed

Summary

  • They share 41 benchmarks with published results for both. Claude Opus 4.7 scores higher in 10 categories and o4-mini in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Opus 4.7 leads 53.8 to 24.6.
  • The biggest single-benchmark swing is ARC-AGI-2: 75.8% for Claude Opus 4.7 and 6.1% for o4-mini.
  • o4-mini is cheaper at $1.10 / $4.40 per million input/output tokens, against $5 / $25 for Claude Opus 4.7.
  • Claude Opus 4.7 accepts more context: 1M tokens versus 200K.

Side by side

Claude Opus 4.7o4-mini
ProviderAnthropicOpenAI
Noometry Index58.341.6
Released2026-04-142025-04-16
WeightsProprietaryProprietary
Context window1M200K
Max output128K100K
Input $ / M tokens$5$1.10
Output $ / M tokens$25$4.40
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: 59.6 (#13), o4-mini: 40.9 (#127)

BenchmarkClaude Opus 4.7o4-mini
GSO44.1%3.6%
WeirdML76.4%52.6%
LMArena Coding15181368
ALE-Bench1,323826.17
SWE-bench Verified83.5%—
FrontierCode38.5%—
SWE-bench Verified (bash only)—45%
Aider Polyglot—72%
LMArena WebDev1558—
SciCode54.5%—
MirrorCode31.1%—
CadEval—62%
AlgoTune—1.72

Agentic & Tool Use Claude Opus 4.7 leads

Claude Opus 4.7: 47.9 (#10), o4-mini: 32.6 (#61)

BenchmarkClaude Opus 4.7o4-mini
Terminal-Bench80.2%—
APEX-Agents49.2%—
Berkeley Function Calling Leaderboard—53.2%
OSWorld 2.018.2%—
GDPval—25.3%
τ²-bench Banking40.2%—
PostTrainBench28.6%—
ExploitBench26.5%—
GBAEval43.8%—
GDP.pdf21%—
LMArena Search1233—
METR Time Horizons—63.9%
Vending-Bench 210,937—

Reasoning Claude Opus 4.7 leads

Claude Opus 4.7: 53.8 (#29), o4-mini: 24.6 (#162)

BenchmarkClaude Opus 4.7o4-mini
ARC-AGI-275.8%6.1%
SimpleBench61.7%38.7%
Kagi LLM Benchmark80.7%67.6%
ARC-AGI-193.5%58.7%
CritPt12%0.6%
Chess Puzzles30%26%
LMArena Hard Prompts15061351
Mystery Game Puzzles28%5%
DTBench94.7%77.6%
LMCA52.2%26.5%
Epoch Capabilities Index156.25145.64
ForecastBench60.361.8
NYT Connections (extended)39%—
EnigmaEval—9.2%
Thematic Generalization72.8%—
EBR-Bench19%—

Math Claude Opus 4.7 leads

Claude Opus 4.7: 66.7 (#26), o4-mini: 40.8 (#89)

BenchmarkClaude Opus 4.7o4-mini
FrontierMath (Tiers 1-3)70.2%36.1%
FrontierMath Tier 431.7%4.9%
OTIS Mock AIME 2024-202597.8%81.7%
LMArena Math14991389
FrontierMath (Feb 2025 set)43.8%24.8%
FrontierMath Tier 4 (v1)22.9%6.3%
MathArena Final-Answer Competitions73.6%—
ProofBench54%—
Omni-MATH—72%
MATH Level 5—97.8%

Knowledge Claude Opus 4.7 leads

Claude Opus 4.7: 62.6 (#23), o4-mini: 43.6 (#91)

BenchmarkClaude Opus 4.7o4-mini
GPQA Diamond90.2%79.6%
Humanity's Last Exam36.2%18.1%
SimpleQA Verified51.7%19.6%
Vectara Hallucination Rate12%18.6%
LMArena Expert15211343
MMLU-Pro—82%
Confabulations—15.8%
GPQA (HELM)—73.5%

Multimodal Claude Opus 4.7 leads

Claude Opus 4.7: 41.2 (#38), o4-mini: 40.2 (#49)

BenchmarkClaude Opus 4.7o4-mini
LMArena Vision13161194
GeoBench—64%
VPCT—57.5%
Blueprint-Bench 224.5%—
Furniture Assembly33.3%—
LMArena Document1495—

Multilingual Claude Opus 4.7 leads

Claude Opus 4.7: 57.3 (#10), o4-mini: 47.0 (#154)

BenchmarkClaude Opus 4.7o4-mini
LMArena Non-English14801337
LMArena Chinese15311354
LMArena French15031364
LMArena German14951336
LMArena Japanese14721308
LMArena Korean14641312
LMArena Russian14941334
LMArena Spanish14951347

Instruction Following Claude Opus 4.7 leads

Claude Opus 4.7: 78.4 (#10), o4-mini: 75.2 (#68)

BenchmarkClaude Opus 4.7o4-mini
LMArena Instruction Following14981321
IFEval—92.8%

Long Context Too close to call

Claude Opus 4.7: 46.2 (#25), o4-mini: 45.5 (#33)

BenchmarkClaude Opus 4.7o4-mini
LMArena Longer Query15051315
Fiction.LiveBench—77.8%

Writing & Preference Claude Opus 4.7 leads

Claude Opus 4.7: 75.1 (#8), o4-mini: 54.0 (#152)

BenchmarkClaude Opus 4.7o4-mini
LMArena Text14901353
LMArena Creative Writing14861294
LMArena Multi-Turn15051350
Short-Story Creative Writing—75%
EQ-Bench Creative Writing1914—
WildBench—85.4%
EQ-Bench 41311—

Frequently asked questions

Is Claude Opus 4.7 better than o4-mini?

Claude Opus 4.7 is the stronger model overall, scoring 58.3 to 41.6 on the Noometry Index. o4-mini costs 5.2× 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 o4-mini?

o4-mini is cheaper. It lists at $1.10 per million input tokens and $4.40 per million output tokens; Claude Opus 4.7 lists at $5 and $25.

Is Claude Opus 4.7 or o4-mini better for coding?

Claude Opus 4.7 scores higher on coding benchmarks: 59.6 versus 40.9 in the Noometry coding category.

Which has the bigger context window?

Claude Opus 4.7 does, with 1M tokens against 200K.

How many benchmarks do Claude Opus 4.7 and o4-mini share?

41 benchmarks have published results for both models. Claude Opus 4.7 has 66 scored results on Noometry and o4-mini has 60.

Related comparisons

Go deeper