Noometry

Model comparison

Claude Haiku 4.5 vs GPT-4o mini

Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 25.5 on the Noometry Index. GPT-4o mini costs 7.6× less per token, which makes it the better buy when Claude Haiku 4.5's lead doesn't matter for your workload.

Last verified . 33 shared benchmarks.

Claude Haiku 4.5 Anthropic

39.5

Rank #165 Confirmed

GPT-4o mini OpenAI

25.5

Rank #343 Confirmed

Summary

  • They share 33 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 10 categories and GPT-4o mini in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Haiku 4.5 leads 44.9 to 10.4.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 66.7% for Claude Haiku 4.5 and 6.9% for GPT-4o mini.
  • GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $1 / $5 for Claude Haiku 4.5.
  • Claude Haiku 4.5 accepts more context: 200K tokens versus 128K.

Side by side

Claude Haiku 4.5GPT-4o mini
ProviderAnthropicOpenAI
Noometry Index39.525.5
Released2025-10-152024-07-18
WeightsProprietaryProprietary
Context window200K128K
Max output64K16K
Input $ / M tokens$1$0.15
Output $ / M tokens$5$0.60
Results tracked5360

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

Category by category

Coding Claude Haiku 4.5 leads

Claude Haiku 4.5: 44.0 (#78), GPT-4o mini: 22.0 (#335)

BenchmarkClaude Haiku 4.5GPT-4o mini
WeirdML45.4%11.8%
LMArena Coding14531290
SWE-bench Verified (bash only)66.6%—
Aider Polyglot—3.6%
LMArena WebDev1330—
SWE-bench Multilingual64.7%—
SciCode43.3%—
BigCodeBench Instruct—46.1%
LiveBench Coding—43.1%
BigCodeBench Complete—57.4%
ALE-Bench653.48—
HumanEval+—83.5%
MBPP+—72.2%

Agentic & Tool Use Claude Haiku 4.5 leads

Claude Haiku 4.5: 33.6 (#52), GPT-4o mini: 27.5 (#101)

BenchmarkClaude Haiku 4.5GPT-4o mini
BALROG31.2%17.4%
Terminal-Bench35.5%—
Berkeley Function Calling Leaderboard68.7%—
DeepResearch Bench45.5%—
ExploitBench13.7%—
Vending-Bench 2458.89—

Reasoning Claude Haiku 4.5 leads

Claude Haiku 4.5: 15.1 (#320), GPT-4o mini: 8.7 (#347)

BenchmarkClaude Haiku 4.5GPT-4o mini
ARC-AGI-24%0%
Chess Puzzles8%0%
LMArena Hard Prompts14201267
DTBench73.6%54.4%
LMCA30.9%10.4%
Epoch Capabilities Index142.41126.56
SimpleBench—10.7%
Kagi LLM Benchmark—28.8%
NYT Connections (extended)14.3%—
ARC-AGI-147.7%—
CritPt0%—
LiveBench Reasoning—32.8%
Mystery Game Puzzles—12%
LiveBench Data Analysis—50%
ForecastBench61.4—
LiveBench—41.3%
PIQA—88.7%

Math Claude Haiku 4.5 leads

Claude Haiku 4.5: 44.9 (#78), GPT-4o mini: 10.4 (#314)

BenchmarkClaude Haiku 4.5GPT-4o mini
OTIS Mock AIME 2024-202566.7%6.9%
Omni-MATH56.1%28%
LMArena Math13961267
MATH Level 596.4%52.6%
FrontierMath (Tiers 1-3)—0.7%
LiveBench Math—36.3%
FrontierMath (Feb 2025 set)5.9%—
FrontierMath Tier 4 (v1)2.1%—
GSM8K—91.3%

Knowledge Claude Haiku 4.5 leads

Claude Haiku 4.5: 37.7 (#153), GPT-4o mini: 17.7 (#284)

BenchmarkClaude Haiku 4.5GPT-4o mini
GPQA Diamond71.2%37.7%
SimpleQA Verified13.2%8.3%
MMLU-Pro77.7%60.3%
GPQA (HELM)60.5%36.8%
LMArena Expert14421235
Confabulations—37.2%
Vectara Hallucination Rate9.8%—
BoolQ—88.7%
MMLU—81.8%

Multimodal Too close to call

Claude Haiku 4.5: 26.8 (#118), GPT-4o mini: 25.9 (#122)

BenchmarkClaude Haiku 4.5GPT-4o mini
LMArena Vision—1066
Video-MME—64.8%
GeoBench—64%
VPCT—34%
Blueprint-Bench 20%—
LMArena Document1420—

Multilingual Claude Haiku 4.5 leads

Claude Haiku 4.5: 49.9 (#129), GPT-4o mini: 42.0 (#199)

BenchmarkClaude Haiku 4.5GPT-4o mini
LMArena Non-English13771266
LMArena Chinese14171265
LMArena French14081297
LMArena German13751272
LMArena Japanese13391216
LMArena Korean13471195
LMArena Russian13811275
LMArena Spanish14201276

Instruction Following Claude Haiku 4.5 leads

Claude Haiku 4.5: 71.4 (#149), GPT-4o mini: 61.9 (#239)

BenchmarkClaude Haiku 4.5GPT-4o mini
IFEval80.1%78.2%
LMArena Instruction Following14141258
LiveBench Instruction Following—56.8%

Long Context Claude Haiku 4.5 leads

Claude Haiku 4.5: 43.6 (#92), GPT-4o mini: 39.1 (#186)

BenchmarkClaude Haiku 4.5GPT-4o mini
LMArena Longer Query14271289

Writing & Preference Claude Haiku 4.5 leads

Claude Haiku 4.5: 57.9 (#123), GPT-4o mini: 39.5 (#248)

BenchmarkClaude Haiku 4.5GPT-4o mini
LMArena Text13961286
LMArena Creative Writing13721268
WildBench83.9%79.1%
LMArena Multi-Turn14091285
Short-Story Creative Writing—67.2%
EQ-Bench Creative Writing—873
EQ-Bench 41064—
LiveBench Language—28.6%

Frequently asked questions

Is Claude Haiku 4.5 better than GPT-4o mini?

Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 25.5 on the Noometry Index. GPT-4o mini costs 7.6× less per token, which makes it the better buy when Claude Haiku 4.5's lead doesn't matter for your workload.

Which is cheaper, Claude Haiku 4.5 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 Haiku 4.5 lists at $1 and $5.

Is Claude Haiku 4.5 or GPT-4o mini better for coding?

Claude Haiku 4.5 scores higher on coding benchmarks: 44.0 versus 22.0 in the Noometry coding category.

Which has the bigger context window?

Claude Haiku 4.5 does, with 200K tokens against 128K.

How many benchmarks do Claude Haiku 4.5 and GPT-4o mini share?

33 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and GPT-4o mini has 60.

Related comparisons

Go deeper