Noometry

Model comparison

Claude Opus 4.6 vs GPT-5 Nano

Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 33.5 on the Noometry Index. GPT-5 Nano costs 73× less per token, which makes it the better buy when Claude Opus 4.6's lead doesn't matter for your workload.

Last verified . 40 shared benchmarks.

Claude Opus 4.6 Anthropic

58.2

Rank #20 Confirmed

GPT-5 Nano OpenAI

33.5

Rank #241 Confirmed

Summary

  • They share 40 benchmarks with published results for both. Claude Opus 4.6 scores higher in 10 categories and GPT-5 Nano in 0 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Opus 4.6 leads 57.8 to 16.3.
  • The biggest single-benchmark swing is ARC-AGI-1: 94% for Claude Opus 4.6 and 20.7% for GPT-5 Nano.
  • GPT-5 Nano is cheaper at $0.05 / $0.40 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 Nano
ProviderAnthropicOpenAI
Noometry Index58.233.5
Released2026-02-042025-08-07
WeightsProprietaryProprietary
Context window1M400K
Max output128K128K
Input $ / M tokens$5$0.05
Output $ / M tokens$25$0.40
Results tracked6849

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 Nano: 33.6 (#254)

BenchmarkClaude Opus 4.6GPT-5 Nano
SWE-bench Verified (bash only)75.6%34.8%
WeirdML78%38.1%
LMArena Coding15361351
ALE-Bench996.5718.67
SWE-bench Verified78.7%—
FrontierCode26.6%—
LMArena WebDev1547—
SWE-bench Multilingual72%—
GSO41.2%—
AlgoTune1.47—

Agentic & Tool Use Claude Opus 4.6 leads

Claude Opus 4.6: 51.1 (#4), GPT-5 Nano: 25.8 (#106)

BenchmarkClaude Opus 4.6GPT-5 Nano
Terminal-Bench79.8%21.8%
APEX-Agents46.3%—
Berkeley Function Calling Leaderboard—51.5%
Remote Labor Index4.2%—
τ²-bench Banking27.3%—
Cybench93%—
DeepResearch Bench55.3%—
GBAEval44.1%—
LMArena Search1253—
METR Time Horizons78.9%—
Vending-Bench 28,018—

Reasoning Claude Opus 4.6 leads

Claude Opus 4.6: 57.8 (#23), GPT-5 Nano: 16.3 (#306)

BenchmarkClaude Opus 4.6GPT-5 Nano
ARC-AGI-269.2%2.6%
Kagi LLM Benchmark83.6%62.2%
ARC-AGI-194%20.7%
Chess Puzzles17%27%
LMArena Hard Prompts15271328
Mystery Game Puzzles25%9%
DTBench91.2%62.7%
LMCA55.8%7.9%
Epoch Capabilities Index155.24139.38
ForecastBench6059.1
SimpleBench67.6%—
NYT Connections (extended)92.1%—
EnigmaEval7.6%—
Thematic Generalization80.6%—
EBR-Bench12.7%—

Math Claude Opus 4.6 leads

Claude Opus 4.6: 63.0 (#31), GPT-5 Nano: 29.4 (#241)

BenchmarkClaude Opus 4.6GPT-5 Nano
FrontierMath (Tiers 1-3)66%20%
FrontierMath Tier 426.8%2.4%
OTIS Mock AIME 2024-202594.4%81.1%
ProofBench50%12%
LMArena Math15191317
FrontierMath (Feb 2025 set)40.7%8.3%
FrontierMath Tier 4 (v1)22.9%2.1%
MathArena Final-Answer Competitions78.5%—
Omni-MATH—54.6%
MATH Level 5—95.2%

Knowledge Claude Opus 4.6 leads

Claude Opus 4.6: 61.9 (#26), GPT-5 Nano: 35.9 (#178)

BenchmarkClaude Opus 4.6GPT-5 Nano
GPQA Diamond90.5%69.4%
SimpleQA Verified47%11.7%
Vectara Hallucination Rate12.2%10.5%
LMArena Expert15461321
Humanity's Last Exam34.4%—
MMLU-Pro—77.8%
GPQA (HELM)—67.9%

Multimodal Claude Opus 4.6 leads

Claude Opus 4.6: 37.3 (#74), GPT-5 Nano: 31.3 (#108)

BenchmarkClaude Opus 4.6GPT-5 Nano
LMArena Vision13161159
VPCT—37.2%
Furniture Assembly28.3%—
LMArena Document1507—

Multilingual Claude Opus 4.6 leads

Claude Opus 4.6: 57.9 (#6), GPT-5 Nano: 45.3 (#172)

BenchmarkClaude Opus 4.6GPT-5 Nano
LMArena Non-English14891313
LMArena Chinese15511356
LMArena German15021327
LMArena Japanese14841226
LMArena Korean14641269
LMArena Russian14971296
LMArena Spanish15101360
LMArena French1513—

Instruction Following Claude Opus 4.6 leads

Claude Opus 4.6: 79.5 (#4), GPT-5 Nano: 75.0 (#79)

BenchmarkClaude Opus 4.6GPT-5 Nano
LMArena Instruction Following15231306
IFEval—93.2%

Long Context Claude Opus 4.6 leads

Claude Opus 4.6: 48.1 (#13), GPT-5 Nano: 31.3 (#281)

BenchmarkClaude Opus 4.6GPT-5 Nano
LMArena Longer Query15201312
Fiction.LiveBench—44.4%
CL-bench20.7%—
CL-bench Life17%—

Writing & Preference Claude Opus 4.6 leads

Claude Opus 4.6: 73.5 (#10), GPT-5 Nano: 39.1 (#249)

BenchmarkClaude Opus 4.6GPT-5 Nano
LMArena Text15031320
LMArena Creative Writing15051249
EQ-Bench Creative Writing1809705
LMArena Multi-Turn15131311
WildBench—80.6%
EQ-Bench 41223—

Frequently asked questions

Is Claude Opus 4.6 better than GPT-5 Nano?

Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 33.5 on the Noometry Index. GPT-5 Nano costs 73× 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 Nano?

GPT-5 Nano is cheaper. It lists at $0.05 per million input tokens and $0.40 per million output tokens; Claude Opus 4.6 lists at $5 and $25.

Is Claude Opus 4.6 or GPT-5 Nano better for coding?

Claude Opus 4.6 scores higher on coding benchmarks: 57.2 versus 33.6 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 Nano share?

40 benchmarks have published results for both models. Claude Opus 4.6 has 68 scored results on Noometry and GPT-5 Nano has 49.

Related comparisons

Go deeper