LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Claude Haiku 4.5 vs Gemini 4 Argon

Updated October 21, 2026. 63 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Haiku 4.5 Replace Gemini 4 Argon
Claude Haiku 4.5Anthropic
Coding
49.8
Overall
16.9
Output $/M
$5.00
0
Gemini 4 ArgonGoogle
Coding
80.5
Overall
52.6
Output $/M
$10.00
63
vs boards won of 63 shared

Decision reading

Pick Gemini 4 Argon for coding: it scores 80.5 on the Vibe Coding Index against 49.8 for Claude Haiku 4.5, though on 2 benchmarks against 3.

Pick Claude Haiku 4.5 when output tokens cost 2.0x less.

Model AClaude Haiku 4.5Anthropic49.8/1003 independent benchmarks$0.56 per solved taskModel BGemini 4 ArgonGoogle80.5/1002 independent benchmarksNo cost per solved task
Shared results
63
Claude Haiku 4.5 only
31
Gemini 4 Argon only
29
Like-for-like categories
8 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
Claude Haiku 4.5 49.8 from 3 benchmarks, Gemini 4 Argon 80.5 from 2 benchmarks.
Widest category
Agentic work, 50.6 points apart on average over 8 shared benchmarks.
Widest single gap
ARC-AGI-2: Claude Haiku 4.5 4.0% against Gemini 4 Argon 91.3%, 87.2 points apart on a 0 to 100 scale.
Output price
Claude Haiku 4.5 $5.00 against Gemini 4 Argon $10.00 per million output tokens, 2.0x apart.
Context window
Claude Haiku 4.5 takes 200K tokens, Gemini 4 Argon 1.05M.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryClaude Haiku 4.5BarsGemini 4 ArgonTies
Coding010
Intelligence02
Agentic work08
Reasoning08
Math03
Knowledge07
Web design07
General018
All shared boards063
CodingLike-for-likeFour of these boards feed the Vibe Coding Index010
Coding benchmarks for Claude Haiku 4.5 and Gemini 4 Argon
BenchmarkClaude Haiku 4.5Gemini 4 ArgonLeader
SWE-bench Verified66.6%Not measuredOnly Claude Haiku 4.5 measured
SWE-bench Multilingual64.7%Not measuredOnly Claude Haiku 4.5 measured
LiveBench coding48.1%89.7%Gemini 4 Argon
LMArena WebDev13301678Gemini 4 Argon
AA Coding Index43.9Not measuredOnly Claude Haiku 4.5 measured
LiveCodeBench (Vals AI)41.2%Not measuredOnly Claude Haiku 4.5 measured
SWE-bench Verified (Vals AI)66.6%Not measuredOnly Claude Haiku 4.5 measured
Terminal-Bench 4 (Vals AI)Not measured57.6%Only Gemini 4 Argon measured
Vibe Code Bench (Vals AI)11.4%91.9%Gemini 4 Argon
Code migration (Vals AI)7.5%68.2%Gemini 4 Argon
ProgramBench (Vals AI)0.0%2.5%Gemini 4 Argon
IOI (Vals AI)Not measured100.0%Only Gemini 4 Argon measured
Terminal-Bench 2.1 (Vals AI)43.8%57.7%Gemini 4 Argon
SWE-bench Multimodal (Vals AI)Not measured56.0%Only Gemini 4 Argon measured
Vibe Code Bench 1-100 (Vals AI)Not measured21.2%Only Gemini 4 Argon measured
CyberBench (Vals AI)Not measured77.9%Only Gemini 4 Argon measured
SciCodeNot measured61.8%Only Gemini 4 Argon measured
Terminal-Bench35.5%Not measuredOnly Claude Haiku 4.5 measured
FrontierCodeNot measured47.5%Only Gemini 4 Argon measured
FrontierSWENot measured55.0%Only Gemini 4 Argon measured
WeirdML45.4%Not measuredOnly Claude Haiku 4.5 measured
ALE-BenchNot measured2100.1Only Gemini 4 Argon measured
LMArena Text: coding14541546Gemini 4 Argon
LMArena Text: software and IT14391556Gemini 4 Argon
LMArena WebDev: React13261692Gemini 4 Argon
LMArena WebDev: HTML13181643Gemini 4 Argon
Neither model has a result on the other 12 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Haiku 4.5 and Gemini 4 Argon
BenchmarkClaude Haiku 4.5Gemini 4 ArgonLeader
AA Intelligence Index16.952.6Gemini 4 Argon
Epoch Capabilities Index142.2166.4Gemini 4 Argon
Agentic workLike-for-likePublic boards, shown as published, kept out of the index08
Agentic work benchmarks for Claude Haiku 4.5 and Gemini 4 Argon
BenchmarkClaude Haiku 4.5Gemini 4 ArgonLeader
AA Agentic Index8.0Not measuredOnly Claude Haiku 4.5 measured
Design Arena: spreadsheetsNot measured1151Only Gemini 4 Argon measured
LiveBench research42.2%83.1%Gemini 4 Argon
LiveBench browser40.0%92.0%Gemini 4 Argon
LiveBench long agentic11.1%69.9%Gemini 4 Argon
SREBench (Vals AI)Not measured44.3%Only Gemini 4 Argon measured
Finance Agent (Vals AI)31.0%65.4%Gemini 4 Argon
Tax Agent Bench (Vals AI)5.9%44.6%Gemini 4 Argon
Legal Research Bench (Vals AI)10.6%54.8%Gemini 4 Argon
Harvey's Legal Agent Benchmark (Vals AI)Not measured27.1%Only Gemini 4 Argon measured
Excel Modeling Benchmark (Vals AI)22.7%75.2%Gemini 4 Argon
BioMysteryBench (Vals AI)Not measured76.3%Only Gemini 4 Argon measured
Terminal-Bench-Science (Vals AI)Not measured44.3%Only Gemini 4 Argon measured
Vals Science IndexNot measured55.4%Only Gemini 4 Argon measured
Time Horizon Index (Vals AI)Not measured52.5%Only Gemini 4 Argon measured
CUA-bench (Vals AI)Not measured4.8%Only Gemini 4 Argon measured
Robo-bench (Vals AI)Not measured0.8%Only Gemini 4 Argon measured
APEX-AgentsNot measured82.4%Only Gemini 4 Argon measured
BALROG31.2%Not measuredOnly Claude Haiku 4.5 measured
DeepResearch Bench45.5%Not measuredOnly Claude Haiku 4.5 measured
Vending-Bench 2$459$13,718Gemini 4 Argon
Neither model has a result on the other 18 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index08
Reasoning benchmarks for Claude Haiku 4.5 and Gemini 4 Argon
BenchmarkClaude Haiku 4.5Gemini 4 ArgonLeader
GPQA Diamond72.2%Not measuredOnly Claude Haiku 4.5 measured
LiveBench reasoning61.7%95.1%Gemini 4 Argon
MysteryMechanism (Vals AI)Not measured45.5%Only Gemini 4 Argon measured
MMMU Pro (Vals AI)46.1%Not measuredOnly Claude Haiku 4.5 measured
Humanity's Last Exam (Artificial Analysis run)Not measured57.1%Only Gemini 4 Argon measured
GPQA Diamond (Epoch AI run)71.2%96.4%Gemini 4 Argon
ARC-AGI47.7%98.5%Gemini 4 Argon
ARC-AGI-24.0%91.3%Gemini 4 Argon
Chess puzzles8.0%59.0%Gemini 4 Argon
Mystery game puzzlesNot measured64.0%Only Gemini 4 Argon measured
EBR-benchNot measured64.8%Only Gemini 4 Argon measured
LMArena Text: hard prompts14211546Gemini 4 Argon
LMArena Text: expert14431550Gemini 4 Argon
LMArena Text: hard prompts in English14351548Gemini 4 Argon
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for Claude Haiku 4.5 and Gemini 4 Argon
BenchmarkClaude Haiku 4.5Gemini 4 ArgonLeader
AIME82.7%Not measuredOnly Claude Haiku 4.5 measured
MGSM (Vals AI)92.2%Not measuredOnly Claude Haiku 4.5 measured
OTIS Mock AIME66.7%100.0%Gemini 4 Argon
FrontierMath, tiers 1 to 3Not measured86.0%Only Gemini 4 Argon measured
FrontierMath, tier 4Not measured78.0%Only Gemini 4 Argon measured
ProofBenchNot measured99.0%Only Gemini 4 Argon measured
MATH level 596.4%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: math13981536Gemini 4 Argon
LMArena Text: mathematical work14301557Gemini 4 Argon
Neither model has a result on the other 4 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index07
Knowledge benchmarks for Claude Haiku 4.5 and Gemini 4 Argon
BenchmarkClaude Haiku 4.5Gemini 4 ArgonLeader
MMLU Pro78.7%Not measuredOnly Claude Haiku 4.5 measured
LegalBench (Vals AI)81.2%88.3%Gemini 4 Argon
CaseLaw (Vals AI)56.5%Not measuredOnly Claude Haiku 4.5 measured
CorpFin (Vals AI)60.6%Not measuredOnly Claude Haiku 4.5 measured
TaxEval (Vals AI)67.5%Not measuredOnly Claude Haiku 4.5 measured
MortgageTax (Vals AI)62.2%Not measuredOnly Claude Haiku 4.5 measured
MedQA (Vals AI)79.6%Not measuredOnly Claude Haiku 4.5 measured
MedCode (Vals AI)32.7%58.8%Gemini 4 Argon
SimpleQA Verified13.2%76.0%Gemini 4 Argon
LMArena Text: science14061548Gemini 4 Argon
LMArena Text: medicine and healthcare13941555Gemini 4 Argon
LMArena Text: legal and government14001548Gemini 4 Argon
LMArena Text: business and finance14001525Gemini 4 Argon
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index07
Web design benchmarks for Claude Haiku 4.5 and Gemini 4 Argon
BenchmarkClaude Haiku 4.5Gemini 4 ArgonLeader
Design Arena: websites11221315Gemini 4 Argon
Design Arena: UI components11001333Gemini 4 Argon
Design Arena: game dev10971377Gemini 4 Argon
Design Arena: data viz11241334Gemini 4 Argon
Design Arena: 3D10721389Gemini 4 Argon
Design Arena: all code categories11151328Gemini 4 Argon
Design Arena: SVG1025Not measuredOnly Claude Haiku 4.5 measured
Design Arena: ASCII art1139Not measuredOnly Claude Haiku 4.5 measured
LiveBench design59.9%73.7%Gemini 4 Argon
GeneralLike-for-likePublic boards, shown as published, kept out of the index018
General benchmarks for Claude Haiku 4.5 and Gemini 4 Argon
BenchmarkClaude Haiku 4.5Gemini 4 ArgonLeader
Vals IndexNot measured69.2%Only Gemini 4 Argon measured
LiveBench data analysis59.3%85.2%Gemini 4 Argon
Public Benefits Bench (Vals AI)54.3%69.8%Gemini 4 Argon
SAGE (Vals AI)31.8%53.6%Gemini 4 Argon
MedScribe (Vals AI)85.2%87.4%Gemini 4 Argon
Vals Multimodal Index42.9%Not measuredOnly Claude Haiku 4.5 measured
Long context reasoning (AA-LCR)Not measured79.7%Only Gemini 4 Argon measured
DTBench73.6%97.6%Gemini 4 Argon
LMCA30.9%63.7%Gemini 4 Argon
Furniture assemblyNot measured72.5%Only Gemini 4 Argon measured
ExploitBench13.7%Not measuredOnly Claude Haiku 4.5 measured
LMArena Text13971532Gemini 4 Argon
LMArena Text: instruction following14141534Gemini 4 Argon
LMArena Text: creative writing13711527Gemini 4 Argon
LMArena Text: English14141538Gemini 4 Argon
LMArena Text: non-English13771522Gemini 4 Argon
LMArena Text: Chinese14181611Gemini 4 Argon
LMArena Text: German1374Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: Japanese1338Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: Korean1346Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: French1411Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: Spanish14211503Gemini 4 Argon
LMArena Text: Russian13811534Gemini 4 Argon
LMArena Text: Polish1343Not measuredOnly Claude Haiku 4.5 measured
LMArena Text: multi-turn14091556Gemini 4 Argon
LMArena Text: longer queries14271547Gemini 4 Argon
LMArena Text: writing and language13861529Gemini 4 Argon
LMArena Text: entertainment and media13691527Gemini 4 Argon
LMArena Document1420Not measuredOnly Claude Haiku 4.5 measured
Neither model has a result on the other 17 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Haiku 4.5 and Gemini 4 Argon
BenchmarkClaude Haiku 4.5Gemini 4 ArgonLeader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

Claude Haiku 4.5$0.0035Fits in one request
Gemini 4 Argon$0.0070Fits in one request

Claude Haiku 4.5 costs less

Repository review

50K input + 3K output tokens

Claude Haiku 4.5$0.065Fits in one request
Gemini 4 Argon$0.130Fits in one request

Claude Haiku 4.5 costs less

Agent loop

200K input + 10K output tokens

Claude Haiku 4.5$0.250Exceeds the context window
Gemini 4 Argon$0.500Fits in one request

Claude Haiku 4.5 costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of Claude Haiku 4.5 and Gemini 4 Argon
SpecificationAnthropic Claude Haiku 4.5Google Gemini 4 Argon
MakerAnthropicGoogle
WeightsNo public weights listedNo public weights listed
ReleasedOctober 15, 2025October 13, 2026
Context window200K1.05M
Input $/Mtok$1.00$2.00
Output $/Mtok$5.00$10.00
Coding index49.880.5
Independent measurements behind it32
Cost per solved task$0.56Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Haiku 4.5 better than Gemini 4 Argon for coding?

Pick Gemini 4 Argon for coding: it scores 80.5 on the Vibe Coding Index against 49.8 for Claude Haiku 4.5, though on 2 benchmarks against 3. Pick Claude Haiku 4.5 when output tokens cost 2.0x less.

Which is cheaper, Claude Haiku 4.5 or Gemini 4 Argon?

Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; Gemini 4 Argon costs $2.00 and $10.00. Cost per solved task is known for Claude Haiku 4.5 only.

Which has the bigger context window, Claude Haiku 4.5 or Gemini 4 Argon?

Gemini 4 Argon, with 1.05M tokens against 200K.

How many benchmarks is the Claude Haiku 4.5 vs Gemini 4 Argon comparison based on?

63 benchmarks have a result for both models as of October 21, 2026. Claude Haiku 4.5's coding index rests on 3 independent benchmarks and Gemini 4 Argon's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/claude-haiku-4-5-vs-gemini-4-argon" title="Claude Haiku 4.5 vs Gemini 4 Argon, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/claude-haiku-4-5-vs-gemini-4-argon">LLMBenchmark.ai, Claude Haiku 4.5 vs Gemini 4 Argon</a></p>