Noometry

Model comparison

Claude Opus 4.6 vs GPT-5.2

Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 54.1 on the Noometry Index. GPT-5.2 costs 2.1× less per token, which makes it the better buy when Claude Opus 4.6's lead doesn't matter for your workload.

Last verified . 61 shared benchmarks.

Claude Opus 4.6 Anthropic

58.2

Rank #20 Confirmed

GPT-5.2 OpenAI

54.1

Rank #34 Confirmed

Summary

  • They share 61 benchmarks with published results for both. Claude Opus 4.6 scores higher in 9 categories and GPT-5.2 in 1 category; 10 gaps are clear of the uncertainty.
  • The widest gap is in multimodal, where GPT-5.2 leads 51.3 to 37.3.
  • The biggest single-benchmark swing is ProofBench: 50% for Claude Opus 4.6 and 15% for GPT-5.2.
  • GPT-5.2 is cheaper at $1.75 / $14 per million input/output tokens, against $5 / $25 for Claude Opus 4.6.
  • Claude Opus 4.6 accepts more context: 1M tokens versus 400K.

Side by side

Claude Opus 4.6GPT-5.2
ProviderAnthropicOpenAI
Noometry Index58.254.1
Released2026-02-042025-12-11
WeightsProprietaryProprietary
Context window1M400K
Max output128K128K
Input $ / M tokens$5$1.75
Output $ / M tokens$25$14
Results tracked6867

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), GPT-5.2: 51.6 (#37)

BenchmarkClaude Opus 4.6GPT-5.2
SWE-bench Verified78.7%73.8%
SWE-bench Verified (bash only)75.6%72.8%
LMArena WebDev15471416
SWE-bench Multilingual72%66.7%
GSO41.2%27.4%
WeirdML78%72.2%
LMArena Coding15361447
ALE-Bench996.51,294
AlgoTune1.472.05
FrontierCode26.6%—

Agentic & Tool Use Claude Opus 4.6 leads

Claude Opus 4.6: 51.1 (#4), GPT-5.2: 40.2 (#24)

BenchmarkClaude Opus 4.6GPT-5.2
Terminal-Bench79.8%64.9%
Remote Labor Index4.2%2.5%
τ²-bench Banking27.3%32.2%
DeepResearch Bench55.3%41.1%
LMArena Search12531207
METR Time Horizons78.9%75.3%
Vending-Bench 28,0183,591
APEX-Agents46.3%—
Berkeley Function Calling Leaderboard—55.9%
GDPval—49.7%
τ²-bench Airline—83%
τ²-bench Retail—81.6%
τ²-bench Telecom—89.7%
Cybench93%—
GBAEval44.1%—

Reasoning Claude Opus 4.6 leads

Claude Opus 4.6: 57.8 (#23), GPT-5.2: 50.2 (#35)

BenchmarkClaude Opus 4.6GPT-5.2
ARC-AGI-269.2%52.9%
SimpleBench67.6%45.8%
Kagi LLM Benchmark83.6%73.3%
NYT Connections (extended)92.1%83.6%
ARC-AGI-194%86.2%
Chess Puzzles17%49%
EnigmaEval7.6%10.4%
EBR-Bench12.7%23%
LMArena Hard Prompts15271445
Mystery Game Puzzles25%23%
DTBench91.2%90.9%
LMCA55.8%43.9%
Epoch Capabilities Index155.24153.45
ForecastBench6060.1
Thematic Generalization80.6%—

Math Claude Opus 4.6 leads

Claude Opus 4.6: 63.0 (#31), GPT-5.2: 60.0 (#38)

BenchmarkClaude Opus 4.6GPT-5.2
FrontierMath (Tiers 1-3)66%67.4%
FrontierMath Tier 426.8%31.7%
MathArena Final-Answer Competitions78.5%72%
OTIS Mock AIME 2024-202594.4%96.1%
ProofBench50%15%
LMArena Math15191440
FrontierMath (Feb 2025 set)40.7%40.7%
FrontierMath Tier 4 (v1)22.9%18.8%

Knowledge Claude Opus 4.6 leads

Claude Opus 4.6: 61.9 (#26), GPT-5.2: 59.3 (#32)

BenchmarkClaude Opus 4.6GPT-5.2
GPQA Diamond90.5%91.4%
Humanity's Last Exam34.4%27.8%
SimpleQA Verified47%37.1%
Vectara Hallucination Rate12.2%8.4%
LMArena Expert15461445

Multimodal GPT-5.2 leads

Claude Opus 4.6: 37.3 (#74), GPT-5.2: 51.3 (#7)

BenchmarkClaude Opus 4.6GPT-5.2
LMArena Vision13161268
Furniture Assembly28.3%38.3%
LMArena Document15071405
VPCT—84%

Multilingual Claude Opus 4.6 leads

Claude Opus 4.6: 57.9 (#6), GPT-5.2: 53.4 (#67)

BenchmarkClaude Opus 4.6GPT-5.2
LMArena Non-English14891425
LMArena Chinese15511460
LMArena French15131455
LMArena German15021448
LMArena Japanese14841420
LMArena Korean14641392
LMArena Russian14971440
LMArena Spanish15101433

Instruction Following Claude Opus 4.6 leads

Claude Opus 4.6: 79.5 (#4), GPT-5.2: 74.7 (#89)

BenchmarkClaude Opus 4.6GPT-5.2
LMArena Instruction Following15231417

Long Context Claude Opus 4.6 leads

Claude Opus 4.6: 48.1 (#13), GPT-5.2: 44.0 (#78)

BenchmarkClaude Opus 4.6GPT-5.2
CL-bench20.7%18.2%
LMArena Longer Query15201428
CL-bench Life17%—

Writing & Preference Claude Opus 4.6 leads

Claude Opus 4.6: 73.5 (#10), GPT-5.2: 66.8 (#32)

BenchmarkClaude Opus 4.6GPT-5.2
LMArena Text15031439
LMArena Creative Writing15051401
EQ-Bench Creative Writing18091703
LMArena Multi-Turn15131458
EQ-Bench 41223—

Frequently asked questions

Is Claude Opus 4.6 better than GPT-5.2?

Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 54.1 on the Noometry Index. GPT-5.2 costs 2.1× 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 GPT-5.2?

GPT-5.2 is cheaper. It lists at $1.75 per million input tokens and $14 per million output tokens; Claude Opus 4.6 lists at $5 and $25.

Is Claude Opus 4.6 or GPT-5.2 better for coding?

Claude Opus 4.6 scores higher on coding benchmarks: 57.2 versus 51.6 in the Noometry coding category.

Which has the bigger context window?

Claude Opus 4.6 does, with 1M tokens against 400K.

How many benchmarks do Claude Opus 4.6 and GPT-5.2 share?

61 benchmarks have published results for both models. Claude Opus 4.6 has 68 scored results on Noometry and GPT-5.2 has 67.

Related comparisons

Go deeper