Noometry

Model comparison

Claude Haiku 4.5 vs Claude Instant

Claude Haiku 4.5 has enough public results to be ranked (#155); Claude Instant does not yet, so treat this comparison as directional.

Last verified . 2 shared benchmarks.

Claude Haiku 4.5 Anthropic

39.3

Rank #155 Confirmed

Claude Instant Anthropic

28.8

Unranked Sparse

Summary

  • They share 2 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 0 categories and Claude Instant in 1 category; one gap is clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Instant leads 18.8 to 15.1.
  • The biggest single-benchmark swing is DTBench: 73.6% for Claude Haiku 4.5 and 45.8% for Claude Instant.

Side by side

Claude Haiku 4.5Claude Instant
ProviderAnthropicAnthropic
Noometry Index39.328.8
Released2025-10-152023-08-09
WeightsProprietaryProprietary
Context window200K—
Max output64K—
Input $ / M tokens$1—
Output $ / M tokens$5—
Results tracked537

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

Category by category

Coding Not comparable

Claude Haiku 4.5: 43.9 (#71), Claude Instant: —

BenchmarkClaude Haiku 4.5Claude Instant
SWE-bench Verified (bash only)66.6%—
LMArena WebDev1330—
SWE-bench Multilingual64.7%—
SciCode43.3%—
WeirdML45.4%—
LMArena Coding1454—
ALE-Bench653.48—
HumanEval+—50.6%

Agentic & Tool Use Not comparable

Claude Haiku 4.5: 33.5 (#50), Claude Instant: —

BenchmarkClaude Haiku 4.5Claude Instant
Terminal-Bench35.5%—
Berkeley Function Calling Leaderboard68.7%—
DeepResearch Bench45.5%—
BALROG31.2%—
ExploitBench13.7%—
Vending-Bench 2458.89—

Reasoning Claude Instant leads

Claude Haiku 4.5: 15.1 (#310), Claude Instant: 18.8

BenchmarkClaude Haiku 4.5Claude Instant
DTBench73.6%45.8%
Epoch Capabilities Index142.42120.2
ARC-AGI-24%—
NYT Connections (extended)14.3%—
ARC-AGI-147.7%—
CritPt0%—
Chess Puzzles8%—
LMArena Hard Prompts1420—
LMCA30.9%—
ForecastBench61.4—

Math Not comparable

Claude Haiku 4.5: 43.0 (#69), Claude Instant: —

BenchmarkClaude Haiku 4.5Claude Instant
OTIS Mock AIME 2024-202566.7%—
Omni-MATH56.1%—
LMArena Math1395—
MATH Level 596.4%—
FrontierMath (Feb 2025 set)5.9%—
FrontierMath Tier 4 (v1)2.1%—
GSM8K—86.7%

Knowledge Not comparable

Claude Haiku 4.5: 37.6 (#146), Claude Instant: —

BenchmarkClaude Haiku 4.5Claude Instant
GPQA Diamond71.2%—
SimpleQA Verified13.2%—
MMLU-Pro77.7%—
Vectara Hallucination Rate9.8%—
GPQA (HELM)60.5%—
LMArena Expert1443—
ARC (AI2) Challenge—86.3%
MMLU—73.4%
TriviaQA—78.9%

Multimodal Not comparable

Claude Haiku 4.5: 27.0 (#111), Claude Instant: —

BenchmarkClaude Haiku 4.5Claude Instant
Blueprint-Bench 20%—
LMArena Document1420—

Multilingual Not comparable

Claude Haiku 4.5: 50.1 (#124), Claude Instant: —

BenchmarkClaude Haiku 4.5Claude Instant
LMArena Non-English1376—
LMArena Chinese1415—
LMArena French1408—
LMArena German1377—
LMArena Japanese1339—
LMArena Korean1346—
LMArena Russian1380—
LMArena Spanish1420—

Instruction Following Not comparable

Claude Haiku 4.5: 71.6 (#144), Claude Instant: —

BenchmarkClaude Haiku 4.5Claude Instant
IFEval80.1%—
LMArena Instruction Following1414—

Long Context Not comparable

Claude Haiku 4.5: 43.6 (#86), Claude Instant: —

BenchmarkClaude Haiku 4.5Claude Instant
LMArena Longer Query1427—

Writing & Preference Not comparable

Claude Haiku 4.5: 58.1 (#119), Claude Instant: —

BenchmarkClaude Haiku 4.5Claude Instant
LMArena Text1396—
LMArena Creative Writing1371—
WildBench83.9%—
EQ-Bench 41064—
LMArena Multi-Turn1409—

Frequently asked questions

Is Claude Haiku 4.5 better than Claude Instant?

Claude Haiku 4.5 has enough public results to be ranked (#155); Claude Instant does not yet, so treat this comparison as directional.

How many benchmarks do Claude Haiku 4.5 and Claude Instant share?

2 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Claude Instant has 7.

Related comparisons

Go deeper