Noometry

Model comparison

Claude Haiku 4.5 vs Gemini 3 Flash Preview

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 39.3 on the Noometry Index.

Last verified . 42 shared benchmarks.

Claude Haiku 4.5 Anthropic

39.3

Rank #155 Confirmed

Gemini 3 Flash Preview Google

52.3

Rank #33 Confirmed

Summary

  • They share 42 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 0 categories and Gemini 3 Flash Preview in 10 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3 Flash Preview leads 49.2 to 15.1.
  • The biggest single-benchmark swing is NYT Connections (extended): 14.3% for Claude Haiku 4.5 and 83.1% for Gemini 3 Flash Preview.
  • Gemini 3 Flash Preview is cheaper at $0.50 / $3 per million input/output tokens, against $1 / $5 for Claude Haiku 4.5.
  • Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 200K.

Side by side

Claude Haiku 4.5Gemini 3 Flash Preview
ProviderAnthropicGoogle
Noometry Index39.352.3
Released2025-10-152025-12-17
WeightsProprietaryProprietary
Context window200K1.05M
Max output64K66K
Input $ / M tokens$1$0.50
Output $ / M tokens$5$3
Results tracked5359

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

Category by category

Coding Gemini 3 Flash Preview leads

Claude Haiku 4.5: 43.9 (#71), Gemini 3 Flash Preview: 51.5 (#35)

BenchmarkClaude Haiku 4.5Gemini 3 Flash Preview
SWE-bench Verified (bash only)66.6%75.8%
LMArena WebDev13301439
SWE-bench Multilingual64.7%72.7%
WeirdML45.4%61.6%
LMArena Coding14541460
ALE-Bench653.481,367
SWE-bench Verified—75.4%
SciCode43.3%—
GSO—9.8%

Agentic & Tool Use Gemini 3 Flash Preview leads

Claude Haiku 4.5: 33.5 (#50), Gemini 3 Flash Preview: 38.6 (#27)

BenchmarkClaude Haiku 4.5Gemini 3 Flash Preview
Terminal-Bench35.5%64.3%
DeepResearch Bench45.5%49.8%
BALROG31.2%48.1%
Vending-Bench 2458.893,635
Berkeley Function Calling Leaderboard68.7%—
τ²-bench Airline—82.5%
τ²-bench Banking—27.3%
τ²-bench Retail—76.8%
τ²-bench Telecom—91.2%
ExploitBench13.7%—
GDP.pdf—10%
LMArena Search—1198

Reasoning Gemini 3 Flash Preview leads

Claude Haiku 4.5: 15.1 (#310), Gemini 3 Flash Preview: 49.2 (#35)

BenchmarkClaude Haiku 4.5Gemini 3 Flash Preview
ARC-AGI-24%33.6%
NYT Connections (extended)14.3%83.1%
ARC-AGI-147.7%84.7%
Chess Puzzles8%40%
LMArena Hard Prompts14201465
DTBench73.6%89.1%
LMCA30.9%43.1%
Epoch Capabilities Index142.42151.83
ForecastBench61.458.5
SimpleBench—61.1%
CritPt0%—
Mystery Game Puzzles—26%

Math Gemini 3 Flash Preview leads

Claude Haiku 4.5: 43.0 (#69), Gemini 3 Flash Preview: 51.4 (#42)

BenchmarkClaude Haiku 4.5Gemini 3 Flash Preview
OTIS Mock AIME 2024-202566.7%95.6%
LMArena Math13951472
FrontierMath (Feb 2025 set)5.9%35.6%
FrontierMath Tier 4 (v1)2.1%4.2%
FrontierMath (Tiers 1-3)—51.2%
FrontierMath Tier 4—17.1%
MathArena Final-Answer Competitions—67.6%
ProofBench—15%
Omni-MATH56.1%—
MATH Level 596.4%—

Knowledge Gemini 3 Flash Preview leads

Claude Haiku 4.5: 37.6 (#146), Gemini 3 Flash Preview: 58.8 (#30)

BenchmarkClaude Haiku 4.5Gemini 3 Flash Preview
GPQA Diamond71.2%89.4%
SimpleQA Verified13.2%66.8%
Vectara Hallucination Rate9.8%13.5%
LMArena Expert14431461
MMLU-Pro77.7%—
GPQA (HELM)60.5%—

Multimodal Gemini 3 Flash Preview leads

Claude Haiku 4.5: 27.0 (#111), Gemini 3 Flash Preview: 45.3 (#15)

BenchmarkClaude Haiku 4.5Gemini 3 Flash Preview
Blueprint-Bench 20%0%
LMArena Document14201413
LMArena Vision—1285
GeoBench—88%
VPCT—72.6%

Multilingual Gemini 3 Flash Preview leads

Claude Haiku 4.5: 50.1 (#124), Gemini 3 Flash Preview: 55.9 (#26)

BenchmarkClaude Haiku 4.5Gemini 3 Flash Preview
LMArena Non-English13761458
LMArena Chinese14151510
LMArena French14081478
LMArena German13771497
LMArena Japanese13391488
LMArena Korean13461443
LMArena Russian13801480
LMArena Spanish14201470

Instruction Following Gemini 3 Flash Preview leads

Claude Haiku 4.5: 71.6 (#144), Gemini 3 Flash Preview: 75.8 (#52)

BenchmarkClaude Haiku 4.5Gemini 3 Flash Preview
LMArena Instruction Following14141437
IFEval80.1%—

Long Context Too close to call

Claude Haiku 4.5: 43.6 (#86), Gemini 3 Flash Preview: 44.4 (#63)

BenchmarkClaude Haiku 4.5Gemini 3 Flash Preview
LMArena Longer Query14271452

Writing & Preference Gemini 3 Flash Preview leads

Claude Haiku 4.5: 58.1 (#119), Gemini 3 Flash Preview: 65.6 (#44)

BenchmarkClaude Haiku 4.5Gemini 3 Flash Preview
LMArena Text13961466
LMArena Creative Writing13711457
LMArena Multi-Turn14091471
WildBench83.9%—
EQ-Bench 41064—

Frequently asked questions

Is Claude Haiku 4.5 better than Gemini 3 Flash Preview?

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 39.3 on the Noometry Index.

Which is cheaper, Claude Haiku 4.5 or Gemini 3 Flash Preview?

Gemini 3 Flash Preview is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; Claude Haiku 4.5 lists at $1 and $5.

Is Claude Haiku 4.5 or Gemini 3 Flash Preview better for coding?

Gemini 3 Flash Preview scores higher on coding benchmarks: 51.5 versus 43.9 in the Noometry coding category.

Which has the bigger context window?

Gemini 3 Flash Preview does, with 1.05M tokens against 200K.

How many benchmarks do Claude Haiku 4.5 and Gemini 3 Flash Preview share?

42 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Gemini 3 Flash Preview has 59.

Related comparisons

Go deeper