Skip to main content
BenchLM
Data

Claude Haiku 4.5 vs Gemini 4 Argon

Updated November 13, 2026. Rank says Gemini 4 Argon is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Share or export
Share on XLinkedInAPI/MCP

Decision reading

Gemini 4 Argon has the higher public point estimate, 79.03 versus 40.13. Their conditional score ranges do not overlap. These ranges do not establish rank confidence. 3 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A
Anthropic logo
Claude Haiku 4.5

Anthropic

40.13/100

Estimated · Public rank #138

Conditional range 30.4–49.9

Model B
Google logo
Gemini 4 Argon

Google

79.03/100

Supported · Public rank #8

90% interval 75.4–82.7

API price per 1M tokens

Claude Haiku 4.5: $1 input / $5 output

Gemini 4 Argon: $2 input / $10 output

Context window

Claude Haiku 4.5: 200K

Gemini 4 Argon: 1M

Released

Claude Haiku 4.5: October 15, 2025

Gemini 4 Argon: September 30, 2026

Shared results
3
Claude Haiku 4.5 only
8
Gemini 4 Argon only
36
Like-for-like categories
1 / 8
Estimated: Claude Haiku 4.5 · Supported: Gemini 4 Argon. Conditional ranges do not establish rank confidence.How the comparison works

Which one for your work

Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.

  • Agentic work

    Tool use, computer use, and multi-step task completion

    Gemini 4 Argon

    Gemini 4 Argon has the higher public agentic point estimate, 74.9 to 22.3, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

    Confidence: limited

  • Long documents

    Prompts that approach the documented context limit

    Gemini 4 Argon

    Gemini 4 Argon has the larger documented context window.

    Confidence: documented

  • Chat turn cost

    1K fresh input + 500 output tokens

    Claude Haiku 4.5

    Claude Haiku 4.5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates
Show secondary and unsupported calls

  • Repository review cost

    50K fresh input + 3K output tokens

    Claude Haiku 4.5

    Claude Haiku 4.5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

  • Coding work

    Code generation, repair, and software-engineering tasks

    Not enough matched evidence

    Claude Haiku 4.5 is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.

    Confidence: limited

  • Cache-heavy agent loop cost

    200K cached + 20K fresh input + 10K output tokens

    Not enough matched evidence

    The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. Claude Haiku 4.5 does not fit this workload in one request.

    Confidence: listed-rates

Which one for a specific job

Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.

The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.

23.3Claude Haiku 4.571.8Gemini 4 Argon

Directional only · BenchAlign v5.8

Gemini 4 Argon has the higher coding point estimate. Conditional score ranges do not establish rank confidence.

Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.

Open the coding leaderboardShortlist models for this job
Same basis rules as the category table below

Or describe your own job

The LLM Selector reads what you need a model for and returns a shortlist, ranked in the same order the job pages publish.

Describe the task and constraints. This selector recommends models; it cannot carry out the task or access your files and accounts.

We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy

What is actually comparable

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

2 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.

Shape of the matched evidence

Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.

A shared-evidence shape is not available.

BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign v5.8 lane for agentic, coding, reasoning, multimodal, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.

Agentic

Like-for-like
Claude Haiku 4.5
22.3
Supported · #115/135
Gemini 4 Argon
74.9
Supported · #6/135
Basis
BenchAlign v5.8 lane · 4 vs 13 public rows
Reading
Gemini 4 Argon leads

Coding

Directional only
Claude Haiku 4.5
23.3
Estimated · #132/162
Gemini 4 Argon
71.8
Supported · #9/162
Basis
BenchAlign v5.8 lane · 4 vs 9 public rows
Reading
Directional only

Knowledge

Directional only
Claude Haiku 4.5
35.8
Estimated · #133/180
Gemini 4 Argon
79.2
Supported · #8/180
Basis
BenchAlign v5.8 lane · 2 vs 2 public rows
Reading
Directional only

Reasoning

Not comparable
Claude Haiku 4.5
Not ranked
Gemini 4 Argon
76.5
Supported · #7/160
Basis
BenchAlign v5.8 lane · 0 vs 7 public rows
Reading
Not comparable

Multimodal

Not comparable
Claude Haiku 4.5
Not ranked
Gemini 4 Argon
Not ranked
Basis
BenchAlign v5.8 lane · 1 vs 5 public rows
Reading
Not comparable

Multilingual

Not comparable
Claude Haiku 4.5
Not ranked
Gemini 4 Argon
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Instruction following

Not comparable
Claude Haiku 4.5
Not ranked
Gemini 4 Argon
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
Claude Haiku 4.5
Not ranked
Gemini 4 Argon
87.4
Unranked · 2 rankable rows
Basis
Provisional lane · 0 vs 2 weighted rows
Reading
Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, reasoning, multimodal, and knowledge denominators (BenchAlign v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.

Supported evidence per lane · bars run 0–100Methodology

What each workload costs

Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.

Chat turn

1K fresh input + 500 output tokens

Claude Haiku 4.5
$0.0035
Fits in one request
Gemini 4 Argon
$0.007
Fits in one request

Claude Haiku 4.5 has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Claude Haiku 4.5
$0.065
Fits in one request
Gemini 4 Argon
$0.13
Fits in one request

Claude Haiku 4.5 has the lower modeled cost

Costs use the listed standard API rates.

Cache-heavy agent loop

200K cached + 20K fresh input + 10K output tokens

Claude Haiku 4.5
$0.09
Does not fit in one request
Gemini 4 Argon
$0.16
Fits in one request

Claude Haiku 4.5 does not fit this workload in one request.

Your workload

Enter a month of tokens to price it at both models’ listed API rates.

Claude Haiku 4.5
$20.00
per month
Gemini 4 Argon
$40.00
per month

Standard listed rates, no batch or volume discounts.

Cached input falls back to the list input rate only where a cached rate is unpublished

Price against score, among all priced models

Overall score against output price per 1M tokens, one model per family. Pricing as of November 12, 2026.

Claude Haiku 4.5Gemini 4 Argon

20406080100$0.10$0.50$1$5$10$50$100Output price, $ per 1M tokens (log)Overall score
  • 37 cheaper models score at least as high as Claude Haiku 4.5. The nearest is Inkling (score 48.2, $4.68 per 1M output tokens).
  • 2 models at the same price score higher than Gemini 4 Argon. The nearest is Gemini 4 Carbon (score 89.2, also $10.00 per 1M output tokens).

Gray dots are the other priced models. The dark step line is the efficiency frontier: for a model under it, another model costs no more and scores at least as high.

See Claude Haiku 4.5 on the full price vs performance chart

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

Cached-input rate

A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.

Claude Haiku 4.5

$0.1 per 1M cached input tokens

Claude API pricing

Gemini 4 Argon

$0.1 per 1M cached input tokens

Google Gemini API pricing

Reasoning profile

Claude Haiku 4.5

Non-Reasoning

Gemini 4 Argon

Reasoning

Weight access

Claude Haiku 4.5

Proprietary

Gemini 4 Argon

Proprietary

License

Claude Haiku 4.5

Proprietary

Gemini 4 Argon

Proprietary

Release date

Claude Haiku 4.5

2025-10-15

Gemini 4 Argon

2026-09-30

If you already use one of these models

Deployment change
The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
Quality signal
Gemini 4 Argon has the higher public point estimate, 79.03 versus 40.13. Their conditional score ranges do not overlap. These ranges do not establish rank confidence.
Workload cost
Repository review: $0.065 vs $0.13. Cache-heavy agent loop: $0.09 vs $0.16.
Context tradeoff
Gemini 4 Argon has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.

Questions

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

Gemini 4 Argon has the higher public point estimate, 79.03 versus 40.13. Their conditional score ranges do not overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, Claude Haiku 4.5 or Gemini 4 Argon?

Gemini 4 Argon scores higher for coding on the public lane, 71.8 to 23.3. Claude Haiku 4.5 is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

Which is better for agentic tasks, Claude Haiku 4.5 or Gemini 4 Argon?

Gemini 4 Argon has the higher public agentic tasks point estimate, 74.9 to 22.3, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

Which costs less, Claude Haiku 4.5 or Gemini 4 Argon?

For the stated presets, chat costs $0.0035 on Claude Haiku 4.5 and $0.007 on Gemini 4 Argon; repository review costs $0.065 and $0.13; the cache-heavy agent loop costs $0.09 and $0.16. Claude Haiku 4.5 does not fit this workload in one request.

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

Gemini 4 Argon has the larger documented context window: 1M, compared with 200K.

Benchmark evidence

The full public result ledger is available for audit without forcing a wide desktop table onto a phone.

Browse raw public benchmark evidence47 rows

Agentic

  • JobBench

    Claude Haiku 4.516.0%
    Source
    Gemini 4 Argon—

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    Claude Haiku 4.543.8%
    Source
    Gemini 4 Argon57.7%
    Source

    Gemini 4 Argon leads this result

  • MazeBench

    Claude Haiku 4.50%
    Source
    Gemini 4 Argon12%
    Source

    Gemini 4 Argon leads this result

  • OSWorld 2.1 Offline

    Claude Haiku 4.515.7%
    Source
    Gemini 4 Argon74.7%
    Source

    Gemini 4 Argon leads this result

  • AutomationBench

    Claude Haiku 4.5—
    Gemini 4 Argon51.3%
    Source

    Not directly comparable

  • Finance Agent v2

    Claude Haiku 4.5—
    Gemini 4 Argon65.4%
    Source

    Not directly comparable

  • Terminal-Bench 4.0

    Claude Haiku 4.5—
    Gemini 4 Argon57.40%
    Source

    Not directly comparable

  • Agents' Last Exam

    Claude Haiku 4.5—
    Gemini 4 Argon39.5%
    Source

    Not directly comparable

  • OSWorld 2.0

    Claude Haiku 4.5—
    Gemini 4 Argon69.2%
    Source

    Not directly comparable

  • CWE-bench v1

    Claude Haiku 4.5—
    Gemini 4 Argon68.0%
    Source

    Not directly comparable

  • Terminal-Bench-Science 0.1 (6x verifier timeout)

    Claude Haiku 4.5—
    Gemini 4 Argon57.6%
    Source

    Not directly comparable

  • ExploitGym

    Claude Haiku 4.5—
    Gemini 4 Argon39.5%
    Source

    Not directly comparable

  • RoboDojo Sim

    Claude Haiku 4.5—
    Gemini 4 Argon34.2%
    Source

    Not directly comparable

  • CWE-bench

    Claude Haiku 4.5—
    Gemini 4 Argon65.0%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    Claude Haiku 4.573.3%
    Source
    Gemini 4 Argon—

    Not directly comparable

  • VulcanBench v3

    Claude Haiku 4.576.2%
    Source
    Gemini 4 Argon—

    Not directly comparable

  • LiveCodeBench (Vals)

    Claude Haiku 4.541.2%
    Source
    Gemini 4 Argon—

    Not directly comparable

  • SWE-bench (Vals)

    Claude Haiku 4.566.6%
    Source
    Gemini 4 Argon—

    Not directly comparable

  • ScarfBench

    Claude Haiku 4.5—
    Gemini 4 Argon75.2%
    Source

    Not directly comparable

  • DeepSWE

    Claude Haiku 4.5—
    Gemini 4 Argon77.9%
    Source

    Not directly comparable

  • FrontierSWE v2

    Claude Haiku 4.5—
    Gemini 4 Argon55.0%
    Source

    Not directly comparable

  • Vibe Code Bench

    Claude Haiku 4.5—
    Gemini 4 Argon91.90%
    Source

    Not directly comparable

  • PostTrainBench v1.1

    Claude Haiku 4.5—
    Gemini 4 Argon45.3%
    Source

    Not directly comparable

  • Bug Hunt Bench

    Claude Haiku 4.5—
    Gemini 4 Argon40.7 fixes
    Source

    Not directly comparable

  • FrontierCode 2.0

    Claude Haiku 4.5—
    Gemini 4 Argon26.3%
    Source

    Not directly comparable

  • CursorBench 4.0

    Claude Haiku 4.5—
    Gemini 4 Argon52.9%
    Source

    Not directly comparable

  • PostTrainBench

    Claude Haiku 4.5—
    Gemini 4 Argon40.4%
    Source

    Not directly comparable

Reasoning

  • STEMBench

    Claude Haiku 4.5—
    Gemini 4 Argon2.44
    Source

    Not directly comparable

  • Graphwalks BFS 128K

    Claude Haiku 4.5—
    Gemini 4 Argon99.7%
    Source

    Not directly comparable

  • GraphWalks BFS 256K–1M

    Claude Haiku 4.5—
    Gemini 4 Argon84.2%
    Source

    Not directly comparable

  • ARC-AGI-1

    Claude Haiku 4.5—
    Gemini 4 Argon98.50%
    Source

    Not directly comparable

  • ARC-AGI-2

    Claude Haiku 4.5—
    Gemini 4 Argon91.3%
    Source

    Not directly comparable

  • ARC-AGI-3

    Claude Haiku 4.5—
    Gemini 4 Argon46.3%
    Source

    Not directly comparable

  • ARC-AGI-3 Provider Adapter

    Claude Haiku 4.5—
    Gemini 4 Argon97.30%
    Source

    Not directly comparable

Multimodal

  • ParseBench-1

    Claude Haiku 4.549.34%
    Source
    Gemini 4 Argon—

    Not directly comparable

  • ParseBench-2

    Claude Haiku 4.5—
    Gemini 4 Argon84.20%
    Source

    Not directly comparable

  • ExtractBench Pro

    Claude Haiku 4.5—
    Gemini 4 Argon30%
    Source

    Not directly comparable

  • Chartography (no tools)

    Claude Haiku 4.5—
    Gemini 4 Argon71.6%
    Source

    Not directly comparable

  • LVBench

    Claude Haiku 4.5—
    Gemini 4 Argon91.7%
    Source

    Not directly comparable

  • Blueprint-Bench 2

    Claude Haiku 4.5—
    Gemini 4 Argon54.4%
    Source

    Not directly comparable

Knowledge

  • GPQA Diamond (Vals)

    Claude Haiku 4.572.2%
    Source
    Gemini 4 Argon—

    Not directly comparable

  • MMLU-Pro (Vals)

    Claude Haiku 4.578.7%
    Source
    Gemini 4 Argon—

    Not directly comparable

  • LABBench2

    Claude Haiku 4.5—
    Gemini 4 Argon88.8%
    Source

    Not directly comparable

  • Morphology-to-molecule matching

    Claude Haiku 4.5—
    Gemini 4 Argon25.2%
    Source

    Not directly comparable

Instruction following

  • Gray Swan IPI (15 attempts)

    Claude Haiku 4.5—
    Gemini 4 Argon0.7%
    Source

    Not directly comparable

Math

  • FrontierMath v2 (Tiers 1-3)

    Claude Haiku 4.5—
    Gemini 4 Argon85.965%
    Source

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    Claude Haiku 4.5—
    Gemini 4 Argon78.049%
    Source

    Not directly comparable

47 public results · 3 shared

Related comparisons

Compare API pricingRead the methodologyOpen the model selector

Watch Claude Haiku 4.5 vs Gemini 4 Argon

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 7,000+ subscribers.

Last updated November 13, 2026