Noometry

Model comparison

Claude Opus 4.6 vs o3

Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 47.5 on the Noometry Index. o3 costs 2.9× less per token, which makes it the better buy when Claude Opus 4.6's lead doesn't matter for your workload.

Last verified . 46 shared benchmarks.

Claude Opus 4.6 Anthropic

58.2

Rank #20 Confirmed

o3 OpenAI

47.5

Rank #61 Confirmed

Summary

  • They share 46 benchmarks with published results for both. Claude Opus 4.6 scores higher in 8 categories and o3 in 2 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Opus 4.6 leads 57.8 to 32.0.
  • The biggest single-benchmark swing is ARC-AGI-2: 69.2% for Claude Opus 4.6 and 6.5% for o3.
  • o3 is cheaper at $2 / $8 per million input/output tokens, against $5 / $25 for Claude Opus 4.6.
  • Claude Opus 4.6 accepts more context: 1M tokens versus 200K.

Side by side

Claude Opus 4.6o3
ProviderAnthropicOpenAI
Noometry Index58.247.5
Released2026-02-042025-04-16
WeightsProprietaryProprietary
Context window1M200K
Max output128K100K
Input $ / M tokens$5$2
Output $ / M tokens$25$8
Results tracked6863

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

Category by category

Coding Claude Opus 4.6 leads

Claude Opus 4.6: 57.2 (#20), o3: 46.8 (#64)

BenchmarkClaude Opus 4.6o3
SWE-bench Verified78.7%62.3%
SWE-bench Verified (bash only)75.6%58.4%
GSO41.2%8.8%
WeirdML78%52.4%
LMArena Coding15361408
ALE-Bench996.5933.55
FrontierCode26.6%—
Aider Polyglot—81.3%
LMArena WebDev1547—
SWE-bench Multilingual72%—
CadEval—74%
AlgoTune1.47—

Agentic & Tool Use Claude Opus 4.6 leads

Claude Opus 4.6: 51.1 (#4), o3: 34.5 (#44)

BenchmarkClaude Opus 4.6o3
DeepResearch Bench55.3%45.2%
LMArena Search12531144
METR Time Horizons78.9%65.4%
Terminal-Bench79.8%—
APEX-Agents46.3%—
Berkeley Function Calling Leaderboard—63%
GDPval—30.8%
Remote Labor Index4.2%—
τ²-bench Banking27.3%—
Cybench93%—
OSWorld—23%
GBAEval44.1%—
Vending-Bench 28,018—

Reasoning Claude Opus 4.6 leads

Claude Opus 4.6: 57.8 (#23), o3: 32.0 (#78)

BenchmarkClaude Opus 4.6o3
ARC-AGI-269.2%6.5%
SimpleBench67.6%53.1%
Kagi LLM Benchmark83.6%67.6%
ARC-AGI-194%60.8%
Chess Puzzles17%38%
EnigmaEval7.6%13.1%
LMArena Hard Prompts15271402
Mystery Game Puzzles25%29%
DTBench91.2%84.8%
LMCA55.8%39.7%
Epoch Capabilities Index155.24146.86
ForecastBench6062.5
NYT Connections (extended)92.1%—
CritPt—1.4%
Thematic Generalization80.6%—
EBR-Bench12.7%—

Math Claude Opus 4.6 leads

Claude Opus 4.6: 63.0 (#31), o3: 50.2 (#58)

BenchmarkClaude Opus 4.6o3
FrontierMath (Tiers 1-3)66%33.3%
OTIS Mock AIME 2024-202594.4%84.4%
LMArena Math15191426
FrontierMath (Feb 2025 set)40.7%18.7%
FrontierMath Tier 4 (v1)22.9%2.1%
FrontierMath Tier 426.8%—
MathArena Final-Answer Competitions78.5%—
ProofBench50%—
Omni-MATH—71.4%
MATH Level 5—97.8%

Knowledge Claude Opus 4.6 leads

Claude Opus 4.6: 61.9 (#26), o3: 54.6 (#52)

BenchmarkClaude Opus 4.6o3
GPQA Diamond90.5%81.8%
Humanity's Last Exam34.4%20.3%
SimpleQA Verified47%49.4%
LMArena Expert15461402
MMLU-Pro—85.9%
Confabulations—14.4%
Vectara Hallucination Rate12.2%—
GPQA (HELM)—75.3%

Multimodal o3 leads

Claude Opus 4.6: 37.3 (#74), o3: 41.4 (#36)

BenchmarkClaude Opus 4.6o3
LMArena Vision13161214
GeoBench—74%
VPCT—52%
Furniture Assembly28.3%—
LMArena Document1507—

Multilingual Claude Opus 4.6 leads

Claude Opus 4.6: 57.9 (#6), o3: 51.7 (#105)

BenchmarkClaude Opus 4.6o3
LMArena Non-English14891401
LMArena Chinese15511437
LMArena French15131430
LMArena German15021420
LMArena Japanese14841403
LMArena Korean14641370
LMArena Russian14971406
LMArena Spanish15101395

Instruction Following Claude Opus 4.6 leads

Claude Opus 4.6: 79.5 (#4), o3: 72.8 (#127)

BenchmarkClaude Opus 4.6o3
LMArena Instruction Following15231368
IFEval—86.9%

Long Context o3 leads

Claude Opus 4.6: 48.1 (#13), o3: 53.3 (#6)

BenchmarkClaude Opus 4.6o3
CL-bench20.7%17.8%
LMArena Longer Query15201372
Fiction.LiveBench—88.9%
CL-bench Life17%—

Writing & Preference Claude Opus 4.6 leads

Claude Opus 4.6: 73.5 (#10), o3: 63.5 (#64)

BenchmarkClaude Opus 4.6o3
LMArena Text15031410
LMArena Creative Writing15051359
EQ-Bench Creative Writing18091676
LMArena Multi-Turn15131405
Short-Story Creative Writing—83.9%
WildBench—86.1%
EQ-Bench 41223—

Frequently asked questions

Is Claude Opus 4.6 better than o3?

Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 47.5 on the Noometry Index. o3 costs 2.9× less per token, which makes it the better buy when Claude Opus 4.6's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 4.6 or o3?

o3 is cheaper. It lists at $2 per million input tokens and $8 per million output tokens; Claude Opus 4.6 lists at $5 and $25.

Is Claude Opus 4.6 or o3 better for coding?

Claude Opus 4.6 scores higher on coding benchmarks: 57.2 versus 46.8 in the Noometry coding category.

Which has the bigger context window?

Claude Opus 4.6 does, with 1M tokens against 200K.

How many benchmarks do Claude Opus 4.6 and o3 share?

46 benchmarks have published results for both models. Claude Opus 4.6 has 68 scored results on Noometry and o3 has 63.

Related comparisons

Go deeper