Noometry

Model comparison

Claude Opus 4.6 vs GPT-4o mini

Claude Opus 4.6 is the stronger model overall, scoring 58.3 to 25.4 on the Noometry Index. GPT-4o mini costs 38× less per token, which makes it the better buy when Claude Opus 4.6's lead doesn't matter for your workload.

Last verified . 32 shared benchmarks.

Claude Opus 4.6 Anthropic

58.3

Rank #18 Confirmed

GPT-4o mini OpenAI

25.4

Rank #337 Confirmed

Summary

  • They share 32 benchmarks with published results for both. Claude Opus 4.6 scores higher in 10 categories and GPT-4o mini in 0 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Opus 4.6 leads 62.7 to 9.9.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 94.4% for Claude Opus 4.6 and 6.9% for GPT-4o mini.
  • GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $5 / $25 for Claude Opus 4.6.
  • Claude Opus 4.6 accepts more context: 1M tokens versus 128K.

Side by side

Claude Opus 4.6GPT-4o mini
ProviderAnthropicOpenAI
Noometry Index58.325.4
Released2026-02-042024-07-18
WeightsProprietaryProprietary
Context window1M128K
Max output128K16K
Input $ / M tokens$5$0.15
Output $ / M tokens$25$0.60
Results tracked6860

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: 57.7 (#15), GPT-4o mini: 21.6 (#330)

BenchmarkClaude Opus 4.6GPT-4o mini
WeirdML78%11.8%
LMArena Coding15351290
SWE-bench Verified78.7%—
FrontierCode26.6%—
SWE-bench Verified (bash only)75.6%—
Aider Polyglot—3.6%
LMArena WebDev1546—
SWE-bench Multilingual72%—
GSO41.2%—
BigCodeBench Instruct—46.1%
LiveBench Coding—43.1%
BigCodeBench Complete—57.4%
ALE-Bench996.5—
AlgoTune1.47—
HumanEval+—83.5%
MBPP+—72.2%

Agentic & Tool Use Claude Opus 4.6 leads

Claude Opus 4.6: 51.0 (#4), GPT-4o mini: 27.2 (#95)

BenchmarkClaude Opus 4.6GPT-4o mini
Terminal-Bench79.8%—
APEX-Agents46.3%—
Remote Labor Index4.2%—
τ²-bench Banking27.3%—
Cybench93%—
DeepResearch Bench55.3%—
BALROG—17.4%
GBAEval44.1%—
LMArena Search1253—
METR Time Horizons78.9%—
Vending-Bench 28,018—

Reasoning Claude Opus 4.6 leads

Claude Opus 4.6: 57.7 (#21), GPT-4o mini: 8.7 (#343)

BenchmarkClaude Opus 4.6GPT-4o mini
ARC-AGI-269.2%0%
SimpleBench67.6%10.7%
Kagi LLM Benchmark83.6%28.8%
Chess Puzzles17%0%
LMArena Hard Prompts15271267
Mystery Game Puzzles25%12%
DTBench91.2%54.4%
LMCA55.8%10.4%
Epoch Capabilities Index155.36126.56
NYT Connections (extended)92.1%—
ARC-AGI-194%—
EnigmaEval7.6%—
Thematic Generalization80.6%—
EBR-Bench12.7%—
LiveBench Reasoning—32.8%
LiveBench Data Analysis—50%
ForecastBench60—
LiveBench—41.3%
PIQA—88.7%

Math Claude Opus 4.6 leads

Claude Opus 4.6: 62.7 (#25), GPT-4o mini: 9.9 (#307)

BenchmarkClaude Opus 4.6GPT-4o mini
FrontierMath (Tiers 1-3)66%0.7%
OTIS Mock AIME 2024-202594.4%6.9%
LMArena Math15171267
FrontierMath Tier 426.8%—
MathArena Final-Answer Competitions78.5%—
ProofBench50%—
Omni-MATH—28%
LiveBench Math—36.3%
MATH Level 5—52.6%
FrontierMath (Feb 2025 set)40.7%—
FrontierMath Tier 4 (v1)22.9%—
GSM8K—91.3%

Knowledge Claude Opus 4.6 leads

Claude Opus 4.6: 61.8 (#23), GPT-4o mini: 17.7 (#279)

BenchmarkClaude Opus 4.6GPT-4o mini
GPQA Diamond90.5%37.7%
SimpleQA Verified47%8.3%
LMArena Expert15461235
Humanity's Last Exam34.4%—
MMLU-Pro—60.3%
Confabulations—37.2%
Vectara Hallucination Rate12.2%—
GPQA (HELM)—36.8%
BoolQ—88.7%
MMLU—81.8%

Multimodal Claude Opus 4.6 leads

Claude Opus 4.6: 37.0 (#67), GPT-4o mini: 25.3 (#117)

BenchmarkClaude Opus 4.6GPT-4o mini
LMArena Vision13161066
Video-MME—64.8%
GeoBench—64%
VPCT—34%
Furniture Assembly28.3%—
LMArena Document1507—

Multilingual Claude Opus 4.6 leads

Claude Opus 4.6: 58.2 (#4), GPT-4o mini: 42.2 (#194)

BenchmarkClaude Opus 4.6GPT-4o mini
LMArena Non-English14901266
LMArena Chinese15511264
LMArena French15131296
LMArena German15041272
LMArena Japanese14841216
LMArena Korean14651195
LMArena Russian14971275
LMArena Spanish15121276

Instruction Following Claude Opus 4.6 leads

Claude Opus 4.6: 79.7 (#3), GPT-4o mini: 62.1 (#234)

BenchmarkClaude Opus 4.6GPT-4o mini
LMArena Instruction Following15231259
LiveBench Instruction Following—56.8%
IFEval—78.2%

Long Context Claude Opus 4.6 leads

Claude Opus 4.6: 48.1 (#13), GPT-4o mini: 39.1 (#181)

BenchmarkClaude Opus 4.6GPT-4o mini
LMArena Longer Query15201289
CL-bench20.7%—
CL-bench Life17%—

Writing & Preference Claude Opus 4.6 leads

Claude Opus 4.6: 73.7 (#9), GPT-4o mini: 39.7 (#243)

BenchmarkClaude Opus 4.6GPT-4o mini
LMArena Text15041286
LMArena Creative Writing15061268
EQ-Bench Creative Writing1809873
LMArena Multi-Turn15141285
Short-Story Creative Writing—67.2%
WildBench—79.1%
EQ-Bench 41223—
LiveBench Language—28.6%

Frequently asked questions

Is Claude Opus 4.6 better than GPT-4o mini?

Claude Opus 4.6 is the stronger model overall, scoring 58.3 to 25.4 on the Noometry Index. GPT-4o mini costs 38× 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-4o mini?

GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Claude Opus 4.6 lists at $5 and $25.

Is Claude Opus 4.6 or GPT-4o mini better for coding?

Claude Opus 4.6 scores higher on coding benchmarks: 57.7 versus 21.6 in the Noometry coding category.

Which has the bigger context window?

Claude Opus 4.6 does, with 1M tokens against 128K.

How many benchmarks do Claude Opus 4.6 and GPT-4o mini share?

32 benchmarks have published results for both models. Claude Opus 4.6 has 68 scored results on Noometry and GPT-4o mini has 60.

Related comparisons

Go deeper