Noometry

Model comparison

Claude Opus 4.7 vs o3

Claude Opus 4.7 is the stronger model overall, scoring 58.3 to 47.5 on the Noometry Index. o3 costs 2.9× less per token, which makes it the better buy when Claude Opus 4.7's lead doesn't matter for your workload.

Last verified . 42 shared benchmarks.

Claude Opus 4.7 Anthropic

58.3

Rank #19 Confirmed

o3 OpenAI

47.5

Rank #61 Confirmed

Summary

  • They share 42 benchmarks with published results for both. Claude Opus 4.7 scores higher in 8 categories and o3 in 2 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Opus 4.7 leads 53.8 to 32.0.
  • The biggest single-benchmark swing is ARC-AGI-2: 75.8% for Claude Opus 4.7 and 6.5% for o3.
  • o3 is cheaper at $2 / $8 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 4.7o3
ProviderAnthropicOpenAI
Noometry Index58.347.5
Released2026-04-142025-04-16
WeightsProprietaryProprietary
Context window1M200K
Max output128K100K
Input $ / M tokens$5$2
Output $ / M tokens$25$8
Results tracked6663

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), o3: 46.8 (#64)

BenchmarkClaude Opus 4.7o3
SWE-bench Verified83.5%62.3%
GSO44.1%8.8%
WeirdML76.4%52.4%
LMArena Coding15181408
ALE-Bench1,323933.55
FrontierCode38.5%—
SWE-bench Verified (bash only)—58.4%
Aider Polyglot—81.3%
LMArena WebDev1558—
SciCode54.5%—
MirrorCode31.1%—
CadEval—74%

Agentic & Tool Use Claude Opus 4.7 leads

Claude Opus 4.7: 47.9 (#10), o3: 34.5 (#44)

BenchmarkClaude Opus 4.7o3
LMArena Search12331144
Terminal-Bench80.2%—
APEX-Agents49.2%—
Berkeley Function Calling Leaderboard—63%
OSWorld 2.018.2%—
GDPval—30.8%
τ²-bench Banking40.2%—
DeepResearch Bench—45.2%
OSWorld—23%
PostTrainBench28.6%—
ExploitBench26.5%—
GBAEval43.8%—
GDP.pdf21%—
METR Time Horizons—65.4%
Vending-Bench 210,937—

Reasoning Claude Opus 4.7 leads

Claude Opus 4.7: 53.8 (#29), o3: 32.0 (#78)

BenchmarkClaude Opus 4.7o3
ARC-AGI-275.8%6.5%
SimpleBench61.7%53.1%
Kagi LLM Benchmark80.7%67.6%
ARC-AGI-193.5%60.8%
CritPt12%1.4%
Chess Puzzles30%38%
LMArena Hard Prompts15061402
Mystery Game Puzzles28%29%
DTBench94.7%84.8%
LMCA52.2%39.7%
Epoch Capabilities Index156.25146.86
ForecastBench60.362.5
NYT Connections (extended)39%—
EnigmaEval—13.1%
Thematic Generalization72.8%—
EBR-Bench19%—

Math Claude Opus 4.7 leads

Claude Opus 4.7: 66.7 (#26), o3: 50.2 (#58)

BenchmarkClaude Opus 4.7o3
FrontierMath (Tiers 1-3)70.2%33.3%
OTIS Mock AIME 2024-202597.8%84.4%
LMArena Math14991426
FrontierMath (Feb 2025 set)43.8%18.7%
FrontierMath Tier 4 (v1)22.9%2.1%
FrontierMath Tier 431.7%—
MathArena Final-Answer Competitions73.6%—
ProofBench54%—
Omni-MATH—71.4%
MATH Level 5—97.8%

Knowledge Claude Opus 4.7 leads

Claude Opus 4.7: 62.6 (#23), o3: 54.6 (#52)

BenchmarkClaude Opus 4.7o3
GPQA Diamond90.2%81.8%
Humanity's Last Exam36.2%20.3%
SimpleQA Verified51.7%49.4%
LMArena Expert15211402
MMLU-Pro—85.9%
Confabulations—14.4%
Vectara Hallucination Rate12%—
GPQA (HELM)—75.3%

Multimodal Too close to call

Claude Opus 4.7: 41.2 (#38), o3: 41.4 (#36)

BenchmarkClaude Opus 4.7o3
LMArena Vision13161214
GeoBench—74%
VPCT—52%
Blueprint-Bench 224.5%—
Furniture Assembly33.3%—
LMArena Document1495—

Multilingual Claude Opus 4.7 leads

Claude Opus 4.7: 57.3 (#10), o3: 51.7 (#105)

BenchmarkClaude Opus 4.7o3
LMArena Non-English14801401
LMArena Chinese15311437
LMArena French15031430
LMArena German14951420
LMArena Japanese14721403
LMArena Korean14641370
LMArena Russian14941406
LMArena Spanish14951395

Instruction Following Claude Opus 4.7 leads

Claude Opus 4.7: 78.4 (#10), o3: 72.8 (#127)

BenchmarkClaude Opus 4.7o3
LMArena Instruction Following14981368
IFEval—86.9%

Long Context o3 leads

Claude Opus 4.7: 46.2 (#25), o3: 53.3 (#6)

BenchmarkClaude Opus 4.7o3
LMArena Longer Query15051372
Fiction.LiveBench—88.9%
CL-bench—17.8%

Writing & Preference Claude Opus 4.7 leads

Claude Opus 4.7: 75.1 (#8), o3: 63.5 (#64)

BenchmarkClaude Opus 4.7o3
LMArena Text14901410
LMArena Creative Writing14861359
EQ-Bench Creative Writing19141676
LMArena Multi-Turn15051405
Short-Story Creative Writing—83.9%
WildBench—86.1%
EQ-Bench 41311—

Frequently asked questions

Is Claude Opus 4.7 better than o3?

Claude Opus 4.7 is the stronger model overall, scoring 58.3 to 47.5 on the Noometry Index. o3 costs 2.9× 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 o3?

o3 is cheaper. It lists at $2 per million input tokens and $8 per million output tokens; Claude Opus 4.7 lists at $5 and $25.

Is Claude Opus 4.7 or o3 better for coding?

Claude Opus 4.7 scores higher on coding benchmarks: 59.6 versus 46.8 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 o3 share?

42 benchmarks have published results for both models. Claude Opus 4.7 has 66 scored results on Noometry and o3 has 63.

Related comparisons

Go deeper