Model A

Anthropic

64.8/100

Estimated · Public rank #37

90% interval 50.5–79.1

Claude Sonnet 5 vs Gemini 3 Pro

Updated August 15, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Model B

Gemini 3 Pro

Google

67.4/100

Supported · Public rank #23

90% interval 56.1–78.7

Decision reading

Gemini 3 Pro has the higher public score estimate, 67.37 versus 64.78, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

1 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.

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.

Long documents
Prompts that approach the documented context limit
Gemini 3 Pro
Gemini 3 Pro has the larger documented context window.
Confidence: documented
Chat turn cost
1K fresh input + 500 output tokens
Claude Sonnet 5
Claude Sonnet 5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Claude Sonnet 5
Claude Sonnet 5 has the lower estimated token cost for this stated workload. Gemini 3 Pro has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback

Show secondary and unsupported calls

Repository review cost
50K fresh input + 3K output tokens
Claude Sonnet 5
Claude Sonnet 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
No shared weighted benchmark basis supports a winner.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
No shared weighted benchmark basis supports a winner.
Confidence: limited

What is actually comparable

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

18 Claude Sonnet 5 only

1 Shared

11 Gemini 3 Pro only

Shared results: 1
Claude Sonnet 5 only: 18
Gemini 3 Pro only: 11
Like-for-like categories: 0 / 8

1 category uses different evidence sets. Those rows remain visible for coverage context but do not name a winner.

Category results, on a stated basis

Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.

Multimodal

Directional only

Claude Sonnet 5: 88.3
Gemini 3 Pro: 81.1
Weighted basis: 1 vs 2 rows
Reading: Directional only

Agentic

Not comparable

Claude Sonnet 5: 81.9
Gemini 3 Pro: Not measured
Weighted basis: 3 vs 0 rows
Reading: Not comparable

Coding

Not comparable

Claude Sonnet 5: 76.7
Gemini 3 Pro: Not measured
Weighted basis: 2 vs 0 rows
Reading: Not comparable

Reasoning

Not comparable

Claude Sonnet 5: Not measured
Gemini 3 Pro: 31.1
Weighted basis: 0 vs 1 rows
Reading: Not comparable

Knowledge

Not comparable

Claude Sonnet 5: 57.4
Gemini 3 Pro: Not measured
Weighted basis: 1 vs 0 rows
Reading: Not comparable

Math

Not comparable

Claude Sonnet 5: Not measured
Gemini 3 Pro: 32.9
Weighted basis: 0 vs 2 rows
Reading: Not comparable

Multilingual

Not comparable

Claude Sonnet 5: Not measured
Gemini 3 Pro: Not measured
Weighted basis: 0 vs 0 rows
Reading: Not comparable

Instruction following

Not comparable

Claude Sonnet 5: Not measured
Gemini 3 Pro: Not measured
Weighted basis: 0 vs 0 rows
Reading: Not comparable

Category averages with the server-provided evidence basis for Claude Sonnet 5 and Gemini 3 Pro
Category	Claude Sonnet 5	Gemini 3 Pro	Weighted basis	Reading
Multimodal	88.3	81.1	Directional only1 vs 2 rows	Directional only
Agentic	81.9	Not measured	Not comparable3 vs 0 rows	Not comparable
Coding	76.7	Not measured	Not comparable2 vs 0 rows	Not comparable
Reasoning	Not measured	31.1	Not comparable0 vs 1 rows	Not comparable
Knowledge	57.4	Not measured	Not comparable1 vs 0 rows	Not comparable
Math	Not measured	32.9	Not comparable0 vs 2 rows	Not comparable
Multilingual	Not measured	Not measured	Not comparable0 vs 0 rows	Not comparable
Instruction following	Not measured	Not measured	Not comparable0 vs 0 rows	Not comparable

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.

Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.

CharXiv
Multimodal
Claude Sonnet 5: 88.3%Gemini 3 Pro: 81.4%Normalized gap 6.9Claude Sonnet 5 source Gemini 3 Pro source

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 Sonnet 5: $0.007; Fits in one request
Gemini 3 Pro: $0.008; Fits in one request

Claude Sonnet 5 has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Claude Sonnet 5: $0.13; Fits in one request
Gemini 3 Pro: $0.136; Fits in one request

Claude Sonnet 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 Sonnet 5: $0.18; Fits in one request
Gemini 3 Pro: $0.56; Fits in one request; Cached input priced at the published list-input rate

Claude Sonnet 5 has the lower modeled cost

Gemini 3 Pro has no published cached-input rate, so cached tokens use its listed input rate.

Specification differences

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

SpecificationClaude Sonnet 5Gemini 3 Pro

Context window

Maximum documented context; output-token limits may be lower.

Claude Sonnet 5

Anthropic model overview

Gemini 3 Pro

API model ID

Claude Sonnet 5

claude-sonnet-5

Anthropic model overview

Gemini 3 Pro

Not sourced

Cached-input rate

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

Claude Sonnet 5

$0.2 per 1M cached input tokens

Claude API pricing

Gemini 3 Pro

Not published

Documented inputs

Claude Sonnet 5

text, image

Anthropic model overview

Gemini 3 Pro

Not sourced

Documented outputs

Claude Sonnet 5

text

Anthropic model overview

Gemini 3 Pro

Not sourced

Provider availability

Claude Sonnet 5

Generally Available · Claude API

Anthropic model overview

Gemini 3 Pro

Not sourced

Reasoning profile

Claude Sonnet 5

Reasoning

Gemini 3 Pro

Non-Reasoning

Weight access

Claude Sonnet 5

Proprietary

Gemini 3 Pro

Proprietary

License

Claude Sonnet 5

Proprietary

Gemini 3 Pro

Proprietary

Release date

Claude Sonnet 5

2026-06-30

Gemini 3 Pro

2025-11-18

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 3 Pro has the higher public score estimate, 67.37 versus 64.78, but the 90% score intervals overlap.
Workload cost: Repository review: $0.13 vs $0.136. Cache-heavy agent loop: $0.18 vs $0.56.
Context tradeoff: Gemini 3 Pro has the larger documented window (2M).

Run the same representative tasks against both endpoints before changing production traffic.

Benchmark evidence

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

Browse raw public benchmark evidence30 rows

Agentic

Terminal-Bench 3.0
Claude Sonnet 514.6%
Source
Gemini 3 Pro—
Not directly comparable
Terminal-Bench 2.0
Claude Sonnet 580.4%
Source
Gemini 3 Pro—
Not directly comparable
BrowseComp
Claude Sonnet 584.7%
Source
Gemini 3 Pro—
Not directly comparable
HLE w/ tools
Claude Sonnet 557.4%
Source
Gemini 3 Pro—
Not directly comparable
OSWorld-Verified
Claude Sonnet 581.2%
Source
Gemini 3 Pro—
Not directly comparable
Gert Labs
Claude Sonnet 5—
Gemini 3 Pro63.23%
Source
Not directly comparable
JobBench
Claude Sonnet 5—
Gemini 3 Pro11.4%
Source
Not directly comparable

Coding

SWE-bench Verified
Claude Sonnet 585.2%
Source
Gemini 3 Pro—
Not directly comparable
SWE-bench Pro
Claude Sonnet 563.2%
Source
Gemini 3 Pro—
Not directly comparable
SWE Multilingual
Claude Sonnet 578.3%
Source
Gemini 3 Pro—
Not directly comparable
SWE Multimodal
Claude Sonnet 528.1%
Source
Gemini 3 Pro—
Not directly comparable
Terminal-Bench 2.0
Claude Sonnet 580.4%
Source
Gemini 3 Pro—
Not directly comparable
FrontierCode 1.1 Main
Claude Sonnet 542.7%
Source
Gemini 3 Pro—
Not directly comparable
cursorBench32
Claude Sonnet 561.5%
Source
Gemini 3 Pro—
Not directly comparable
APEX-SWE
Claude Sonnet 546.4%
Source
Gemini 3 Pro—
Not directly comparable
EEBench
Claude Sonnet 540.3%
Source
Gemini 3 Pro—
Not directly comparable
3DCodeBench
Claude Sonnet 539.2%
Source
Gemini 3 Pro—
Not directly comparable
Vibe Code Bench
Claude Sonnet 5—
Gemini 3 Pro14.30%
Source
Not directly comparable

Reasoning

ARC-AGI-2
Claude Sonnet 5—
Gemini 3 Pro31.1%
Source
Not directly comparable

Knowledge

HLE
Claude Sonnet 557.4%
Source
Gemini 3 Pro—
Not directly comparable
HLE w/o tools
Claude Sonnet 543.2%
Source
Gemini 3 Pro—
Not directly comparable

Math

FrontierMath v2 (Tiers 1-3)
Claude Sonnet 5—
Gemini 3 Pro37.600%
Source
Not directly comparable
FrontierMath v2 (Tier 4)
Claude Sonnet 5—
Gemini 3 Pro18.750%
Source
Not directly comparable

Multimodal

CharXiv
Claude Sonnet 588.3%
Source
Gemini 3 Pro81.4%
Source
Claude Sonnet 5 leads this result
CharXiv w/o tools
Claude Sonnet 577%
Source
Gemini 3 Pro—
Not directly comparable
MMMU-Pro
Claude Sonnet 5—
Gemini 3 Pro81%
Source
Not directly comparable
MathVision
Claude Sonnet 5—
Gemini 3 Pro86.6%
Source
Not directly comparable
VideoMMMU
Claude Sonnet 5—
Gemini 3 Pro87.6%
Source
Not directly comparable
ScreenSpot Pro
Claude Sonnet 5—
Gemini 3 Pro72.7%
Source
Not directly comparable
V*
Claude Sonnet 5—
Gemini 3 Pro88.0%
Source
Not directly comparable

Frequently asked questions

Which is better, Claude Sonnet 5 or Gemini 3 Pro?

Gemini 3 Pro has the higher public score estimate, 67.37 versus 64.78, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.

Which is better for coding, Claude Sonnet 5 or Gemini 3 Pro?

The published evidence does not provide a shared weighted coding basis for both models, so BenchLM does not name a coding winner.

Which is better for agentic tasks, Claude Sonnet 5 or Gemini 3 Pro?

The published evidence does not provide a shared weighted agentic tasks basis for both models, so BenchLM does not name a agentic tasks winner.

Which costs less, Claude Sonnet 5 or Gemini 3 Pro?

For the stated presets, chat costs $0.007 on Claude Sonnet 5 and $0.008 on Gemini 3 Pro; repository review costs $0.13 and $0.136; the cache-heavy agent loop costs $0.18 and $0.56. Gemini 3 Pro has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, Claude Sonnet 5 or Gemini 3 Pro?

Gemini 3 Pro has the larger documented context window: 2M, compared with 1M.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated August 15, 2026

Watch Claude Sonnet 5 vs Gemini 3 Pro

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

Read a sample issue

Join 2,000+ readers.

Claude Sonnet 5 vs Gemini 3 Pro

Which one for your work

Long documents

Chat turn cost

Cache-heavy agent loop cost

Repository review cost

Coding work

Agentic work

What is actually comparable

Category results, on a stated basis

Multimodal

Agentic

Coding

Reasoning

Knowledge

Math

Multilingual

Instruction following

Shape of the matched evidence

What each workload costs

Chat turn

Repository review

Cache-heavy agent loop

Specification differences

Context window

API model ID

Cached-input rate

Documented inputs

Documented outputs

Provider availability

Reasoning profile

Weight access

License

Release date

Benchmark evidence

Agentic

Coding

Reasoning

Knowledge

Math

Multimodal

Frequently asked questions

Which is better, Claude Sonnet 5 or Gemini 3 Pro?

Which is better for coding, Claude Sonnet 5 or Gemini 3 Pro?

Which is better for agentic tasks, Claude Sonnet 5 or Gemini 3 Pro?

Which costs less, Claude Sonnet 5 or Gemini 3 Pro?

Which has the larger context window, Claude Sonnet 5 or Gemini 3 Pro?

Related comparisons

Watch Claude Sonnet 5 vs Gemini 3 Pro