Noometry

Model comparison

Claude Opus 5.5 vs GPT-4o mini

Claude Opus 5.5 is the stronger model overall, scoring 68.6 to 25.5 on the Noometry Index. GPT-4o mini costs 30× less per token, which makes it the better buy when Claude Opus 5.5's lead doesn't matter for your workload.

Last verified . 25 shared benchmarks.

Claude Opus 5.5 Anthropic

68.6

Rank #3 Confirmed

GPT-4o mini OpenAI

25.5

Rank #343 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Claude Opus 5.5 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 5.5 leads 91.8 to 10.4.
  • The biggest single-benchmark swing is ARC-AGI-2: 93.3% for Claude Opus 5.5 and 0% for GPT-4o mini.
  • GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $4 / $20 for Claude Opus 5.5.
  • Claude Opus 5.5 accepts more context: 1M tokens versus 128K.

Side by side

Claude Opus 5.5GPT-4o mini
ProviderAnthropicOpenAI
Noometry Index68.625.5
Released2026-09-222024-07-18
WeightsProprietaryProprietary
Context window1M128K
Max output128K16K
Input $ / M tokens$4$0.15
Output $ / M tokens$20$0.60
Results tracked4460

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

Category by category

Coding Claude Opus 5.5 leads

Claude Opus 5.5: 71.9 (#3), GPT-4o mini: 22.0 (#335)

BenchmarkClaude Opus 5.5GPT-4o mini
LMArena Coding15471290
FrontierCode54.6%—
Aider Polyglot—3.6%
CursorBench57.8%—
LMArena WebDev1813—
FrontierSWE62.3%—
SciCode66.9%—
WeirdML—11.8%
BigCodeBench Instruct—46.1%
LiveBench Coding—43.1%
MirrorCode77.4%—
BigCodeBench Complete—57.4%
ALE-Bench2,147—
HumanEval+—83.5%
MBPP+—72.2%

Agentic & Tool Use Claude Opus 5.5 leads

Claude Opus 5.5: 45.3 (#15), GPT-4o mini: 27.5 (#101)

BenchmarkClaude Opus 5.5GPT-4o mini
APEX-Agents73.5%—
BALROG—17.4%
GDP.pdf30.6%—
Vending-Bench 29,235—

Reasoning Claude Opus 5.5 leads

Claude Opus 5.5: 80.2 (#3), GPT-4o mini: 8.7 (#347)

BenchmarkClaude Opus 5.5GPT-4o mini
ARC-AGI-293.3%0%
LMArena Hard Prompts15351267
Mystery Game Puzzles71%12%
DTBench98.9%54.4%
LMCA68.2%10.4%
Epoch Capabilities Index167.33126.56
SimpleBench—10.7%
Kagi LLM Benchmark—28.8%
NYT Connections (extended)88.5%—
ARC-AGI-198.5%—
CritPt31.7%—
Chess Puzzles—0%
EBR-Bench71.4%—
LiveBench Reasoning—32.8%
LiveBench Data Analysis—50%
LiveBench—41.3%
PIQA—88.7%

Math Claude Opus 5.5 leads

Claude Opus 5.5: 91.8 (#3), GPT-4o mini: 10.4 (#314)

BenchmarkClaude Opus 5.5GPT-4o mini
FrontierMath (Tiers 1-3)91.2%0.7%
OTIS Mock AIME 2024-2025100%6.9%
LMArena Math15061267
FrontierMath Tier 495%—
ProofBench100%—
Omni-MATH—28%
LiveBench Math—36.3%
MATH Level 5—52.6%
FrontierMath Erdős2.9%—
GSM8K—91.3%

Knowledge Claude Opus 5.5 leads

Claude Opus 5.5: 66.4 (#10), GPT-4o mini: 17.7 (#284)

BenchmarkClaude Opus 5.5GPT-4o mini
GPQA Diamond90.6%37.7%
SimpleQA Verified72.2%8.3%
LMArena Expert15471235
MMLU-Pro—60.3%
Confabulations—37.2%
GPQA (HELM)—36.8%
BoolQ—88.7%
MMLU—81.8%

Multimodal Claude Opus 5.5 leads

Claude Opus 5.5: 57.8 (#1), GPT-4o mini: 25.9 (#122)

BenchmarkClaude Opus 5.5GPT-4o mini
LMArena Vision13211066
Video-MME—64.8%
GeoBench—64%
VPCT—34%
Blueprint-Bench 251.2%—
Furniture Assembly83.3%—

Multilingual Claude Opus 5.5 leads

Claude Opus 5.5: 59.1 (#2), GPT-4o mini: 42.0 (#199)

BenchmarkClaude Opus 5.5GPT-4o mini
LMArena Non-English15071266
LMArena Chinese15881265
LMArena French15141297
LMArena Russian15201275
LMArena Spanish15071276
LMArena German—1272
LMArena Japanese—1216
LMArena Korean—1195

Instruction Following Claude Opus 5.5 leads

Claude Opus 5.5: 80.0 (#3), GPT-4o mini: 61.9 (#239)

BenchmarkClaude Opus 5.5GPT-4o mini
LMArena Instruction Following15371258
LiveBench Instruction Following—56.8%
IFEval—78.2%

Long Context Claude Opus 5.5 leads

Claude Opus 5.5: 47.1 (#19), GPT-4o mini: 39.1 (#186)

BenchmarkClaude Opus 5.5GPT-4o mini
LMArena Longer Query15321289

Writing & Preference Claude Opus 5.5 leads

Claude Opus 5.5: 78.2 (#3), GPT-4o mini: 39.5 (#248)

BenchmarkClaude Opus 5.5GPT-4o mini
LMArena Text15151286
LMArena Creative Writing15331268
EQ-Bench Creative Writing2050873
LMArena Multi-Turn14991285
Short-Story Creative Writing—67.2%
WildBench—79.1%
LiveBench Language—28.6%

Frequently asked questions

Is Claude Opus 5.5 better than GPT-4o mini?

Claude Opus 5.5 is the stronger model overall, scoring 68.6 to 25.5 on the Noometry Index. GPT-4o mini costs 30× less per token, which makes it the better buy when Claude Opus 5.5's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 5.5 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 5.5 lists at $4 and $20.

Is Claude Opus 5.5 or GPT-4o mini better for coding?

Claude Opus 5.5 scores higher on coding benchmarks: 71.9 versus 22.0 in the Noometry coding category.

Which has the bigger context window?

Claude Opus 5.5 does, with 1M tokens against 128K.

How many benchmarks do Claude Opus 5.5 and GPT-4o mini share?

25 benchmarks have published results for both models. Claude Opus 5.5 has 44 scored results on Noometry and GPT-4o mini has 60.

Related comparisons

Go deeper