Agentic
Like-for-like- Claude Sonnet 4.6
- 45.0
- Supported · #96/151
- Gemini 3.6 Flash
- 50.7
- Supported · #60/151
- Basis
- BenchAlign lane · 8 vs 2 public rows
- Reading
- Gemini 3.6 Flash leads · intervals overlap
Claude Sonnet 4.6 vs Gemini 3.6 Flash
Updated September 4, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
Gemini 3.6 Flash has the higher public score estimate, 70.11 versus 64.21, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
6 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Share or export
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.
Coding work
Code generation, repair, and software-engineering tasks
Gemini 3.6 Flash
Gemini 3.6 Flash leads on the public coding lane, 58.9 to 52.4, with Supported evidence for both models, although the 90% intervals overlap.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Gemini 3.6 Flash
Gemini 3.6 Flash leads on the public agentic lane, 50.7 to 45, with Supported evidence for both models, although the 90% intervals overlap.
Confidence: limited
Long documents
Prompts that approach the documented context limit
Gemini 3.6 Flash
Gemini 3.6 Flash has the larger documented context window.
Confidence: documented
Show secondary and unsupported calls
Chat turn cost
1K fresh input + 500 output tokens
Gemini 3.6 Flash
Gemini 3.6 Flash has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Repository review cost
50K fresh input + 3K output tokens
Gemini 3.6 Flash
Gemini 3.6 Flash 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
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 Sonnet 4.6 does not fit this workload in one request. Claude Sonnet 4.6 has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
19 Claude Sonnet 4.6 only
6 Shared
2 Gemini 3.6 Flash only
- Shared results
- 6
- Claude Sonnet 4.6 only
- 19
- Gemini 3.6 Flash only
- 2
- Like-for-like categories
- 3 / 8
Category results, on a stated basis
Each row shows the public-lane category score for both models: the BenchAlign lane for agentic, coding, 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.
Coding
Like-for-like- Claude Sonnet 4.6
- 52.4
- Supported · #55/183
- Gemini 3.6 Flash
- 58.9
- Supported · #30/183
- Basis
- BenchAlign lane · 8 vs 4 public rows
- Reading
- Gemini 3.6 Flash leads · intervals overlap
Knowledge
Like-for-like- Claude Sonnet 4.6
- 56.7
- Supported · #51/181
- Gemini 3.6 Flash
- 68.6
- Supported · #18/181
- Basis
- BenchAlign lane · 6 vs 2 public rows
- Reading
- Gemini 3.6 Flash leads · intervals overlap
Reasoning
Not comparable- Claude Sonnet 4.6
- 65.8
- Unranked · 2 rankable rows
- Gemini 3.6 Flash
- 77.8
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- Claude Sonnet 4.6
- 49.0
- Unranked · 2 rankable rows
- Gemini 3.6 Flash
- Not ranked
- Basis
- Provisional lane · 2 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude Sonnet 4.6
- Not ranked
- Gemini 3.6 Flash
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Claude Sonnet 4.6
- 53.9
- #33/48
- Gemini 3.6 Flash
- 82.3
- Unranked · 1 rankable row
- Basis
- Provisional lane · 1 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Claude Sonnet 4.6
- 47.9
- #84/120
- Gemini 3.6 Flash
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | Claude Sonnet 4.6 | Gemini 3.6 Flash | Basis | Reading |
|---|---|---|---|---|
| Agentic | 45.0Supported · #96/151 | 50.7Supported · #60/151 | Like-for-likeBenchAlign lane · 8 vs 2 public rows | Gemini 3.6 Flash leads · intervals overlap |
| Coding | 52.4Supported · #55/183 | 58.9Supported · #30/183 | Like-for-likeBenchAlign lane · 8 vs 4 public rows | Gemini 3.6 Flash leads · intervals overlap |
| Knowledge | 56.7Supported · #51/181 | 68.6Supported · #18/181 | Like-for-likeBenchAlign lane · 6 vs 2 public rows | Gemini 3.6 Flash leads · intervals overlap |
| Reasoning | 65.8Unranked · 2 rankable rows | 77.8Unranked · 2 rankable rows | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 49.0Unranked · 2 rankable rows | Not ranked | Not comparableProvisional lane · 2 vs 0 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | 53.9#33/48 | 82.3Unranked · 1 rankable row | Not comparableProvisional lane · 1 vs 0 weighted rows | Not comparable |
| Instruction following | 47.9#84/120 | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign) differ from the provisional-lane categories. Unranked scores sit on the lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
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.
OSWorld-Verified
Agentic
Claude Sonnet 4.6: 72.1%Gemini 3.6 Flash: 83%Normalized gap 10.9Claude Sonnet 4.6 source Gemini 3.6 Flash sourceLiveCodeBench (Vals)
Coding
Claude Sonnet 4.6: 82.1%Gemini 3.6 Flash: 88.1%Normalized gap 6.0Claude Sonnet 4.6 source Gemini 3.6 Flash sourceMMLU-Pro (Vals)
Knowledge
Claude Sonnet 4.6: 87.3%Gemini 3.6 Flash: 89.3%Normalized gap 2.0Claude Sonnet 4.6 source Gemini 3.6 Flash 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 4.6
- $0.0105
- Fits in one request
- Gemini 3.6 Flash
- $0.00525
- Fits in one request
Gemini 3.6 Flash has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Claude Sonnet 4.6
- $0.195
- Fits in one request
- Gemini 3.6 Flash
- $0.0975
- Fits in one request
Gemini 3.6 Flash 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 4.6
- $0.81
- Does not fit in one request
- Cached input priced at the published list-input rate
- Gemini 3.6 Flash
- $0.135
- Fits in one request
Claude Sonnet 4.6 does not fit this workload in one request. Claude Sonnet 4.6 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 4.6Gemini 3.6 Flash
Context window
Maximum documented context; output-token limits may be lower.
Claude Sonnet 4.6
200K
Gemini 3.6 Flash
API model ID
Claude Sonnet 4.6
Not sourced
Gemini 3.6 Flash
gemini-3.6-flash
Google Gemini 3.6 Flash model documentationCached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Claude Sonnet 4.6
Not published
Gemini 3.6 Flash
$0.15 per 1M cached input tokens
Google Gemini API pricingDocumented inputs
Claude Sonnet 4.6
Not sourced
Gemini 3.6 Flash
text, image, video, audio, pdf
Google Gemini 3.6 Flash model documentationDocumented outputs
Claude Sonnet 4.6
Not sourced
Gemini 3.6 Flash
Provider availability
Claude Sonnet 4.6
Not sourced
Gemini 3.6 Flash
Generally Available · Gemini API, Google AI Studio
Google latest Gemini model guideReasoning profile
Claude Sonnet 4.6
Non-Reasoning
Gemini 3.6 Flash
Reasoning
Weight access
Claude Sonnet 4.6
Proprietary
Gemini 3.6 Flash
Proprietary
License
Claude Sonnet 4.6
Proprietary
Gemini 3.6 Flash
Proprietary
Release date
Claude Sonnet 4.6
2026-02-01
Gemini 3.6 Flash
2026-07-21
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 3.6 Flash has the higher public score estimate, 70.11 versus 64.21, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.195 vs $0.0975. Cache-heavy agent loop: $0.81 vs $0.135.
- Context tradeoff
- Gemini 3.6 Flash has the larger documented window (1M).
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 evidence27 rows
Agentic
Terminal-Bench 2.0
Claude Sonnet 4.659.1%SourceGemini 3.6 Flash—Not directly comparable
OSWorld-Verified
Claude Sonnet 4.672.1%SourceGemini 3.6 Flash83%SourceGemini 3.6 Flash leads this result
Claw-Eval
Claude Sonnet 4.667.8%SourceGemini 3.6 Flash—Not directly comparable
CyberGym
Claude Sonnet 4.665.2%SourceGemini 3.6 Flash—Not directly comparable
Gert Labs
Claude Sonnet 4.662.92%SourceGemini 3.6 Flash—Not directly comparable
OSWorld 2.0
Claude Sonnet 4.68.3%SourceGemini 3.6 Flash—Not directly comparable
JobBench
Claude Sonnet 4.636.9%SourceGemini 3.6 Flash—Not directly comparable
Terminal-Bench 2.1 (Vals)
Claude Sonnet 4.657.3%SourceGemini 3.6 Flash73.8%SourceGemini 3.6 Flash leads this result
Coding
SWE-bench Verified
Claude Sonnet 4.679.6%SourceGemini 3.6 Flash—Not directly comparable
SWE-Rebench
Claude Sonnet 4.660.7%SourceGemini 3.6 Flash—Not directly comparable
React Native Evals
Claude Sonnet 4.680.6%SourceGemini 3.6 Flash—Not directly comparable
Vibe Code Bench
Claude Sonnet 4.651.48%SourceGemini 3.6 Flash—Not directly comparable
cursorBench31
Claude Sonnet 4.648.8%SourceGemini 3.6 Flash—Not directly comparable
FrontierCode 1.1 Main
Claude Sonnet 4.624.3%SourceGemini 3.6 Flash—Not directly comparable
LiveCodeBench (Vals)
Claude Sonnet 4.682.1%SourceGemini 3.6 Flash88.1%SourceGemini 3.6 Flash leads this result
SWE-bench (Vals)
Claude Sonnet 4.677.4%SourceGemini 3.6 Flash79.6%SourceGemini 3.6 Flash leads this result
deepSwe
Claude Sonnet 4.6—Gemini 3.6 Flash49%SourceNot directly comparable
cursorBench32
Claude Sonnet 4.6—Gemini 3.6 Flash53.5%SourceNot directly comparable
Knowledge
GPQA
Claude Sonnet 4.689.9%SourceGemini 3.6 Flash—Not directly comparable
SuperGPQA
Claude Sonnet 4.695%SourceGemini 3.6 Flash—Not directly comparable
MMLU-Pro
Claude Sonnet 4.679.2%SourceGemini 3.6 Flash—Not directly comparable
HLE
Claude Sonnet 4.649%SourceGemini 3.6 Flash—Not directly comparable
GPQA Diamond (Vals)
Claude Sonnet 4.685.6%SourceGemini 3.6 Flash93.4%SourceGemini 3.6 Flash leads this result
MMLU-Pro (Vals)
Claude Sonnet 4.687.3%SourceGemini 3.6 Flash89.3%SourceGemini 3.6 Flash leads this result
Math
Multimodal
CharXiv
Claude Sonnet 4.677.4%SourceGemini 3.6 Flash—Not directly comparable
Frequently asked questions
Which is better, Claude Sonnet 4.6 or Gemini 3.6 Flash?
Gemini 3.6 Flash has the higher public score estimate, 70.11 versus 64.21, 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 4.6 or Gemini 3.6 Flash?
Gemini 3.6 Flash leads the public coding lane, 58.9 to 52.4, with Supported evidence for both models, although the 90% intervals overlap.
Which is better for agentic tasks, Claude Sonnet 4.6 or Gemini 3.6 Flash?
Gemini 3.6 Flash leads the public agentic tasks lane, 50.7 to 45, with Supported evidence for both models, although the 90% intervals overlap.
Which costs less, Claude Sonnet 4.6 or Gemini 3.6 Flash?
For the stated presets, chat costs $0.0105 on Claude Sonnet 4.6 and $0.00525 on Gemini 3.6 Flash; repository review costs $0.195 and $0.0975; the cache-heavy agent loop costs $0.81 and $0.135. Claude Sonnet 4.6 does not fit this workload in one request. Claude Sonnet 4.6 has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, Claude Sonnet 4.6 or Gemini 3.6 Flash?
Gemini 3.6 Flash has the larger documented context window: 1M, compared with 200K.
Related comparisons
Last updated September 4, 2026
Watch Claude Sonnet 4.6 vs Gemini 3.6 Flash
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.