Agentic
Like-for-like- Claude Opus 5.5
- 82.7
- Supported · #1/156
- Gemini 3 Flash
- 36.1
- Supported · #137/156
- Basis
- BenchAlign lane · 11 vs 4 public rows
- Reading
- Claude Opus 5.5 leads
Claude Opus 5.5 vs Gemini 3 Flash
Decision reading
The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. Use the documented cost, context, and runtime rows instead.
0 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Updated September 22, 2026. Rank says Claude Opus 5.5 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
Both of these models will change. Get the price, version and retirement notices for the pair, each with its source. Follow model changes
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.
Agentic work
Tool use, computer use, and multi-step task completion
Claude Opus 5.5
Claude Opus 5.5 leads on the public agentic lane, 82.7 to 36.1, with Supported evidence for both models and non-overlapping 90% intervals.
Confidence: stronger
Chat turn cost
1K fresh input + 500 output tokens
Gemini 3 Flash
Gemini 3 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
Gemini 3 Flash
Gemini 3 Flash 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
Gemini 3 Flash
Gemini 3 Flash 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 Opus 5.5 is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Confidence: limited
Long documents
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
Confidence: documented
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.
76.0Claude Opus 5.542.4Gemini 3 Flash
Directional only · BenchAlign
Claude Opus 5.5 scores higher, but at least one score rests on Estimated evidence or a different benchmark set. Directional only, no winner.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
48 Claude Opus 5.5 only
11 Gemini 3 Flash only
- Shared results
- 0
- Claude Opus 5.5 only
- 48
- Gemini 3 Flash only
- 11
- Like-for-like categories
- 1 / 8
2 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
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
Directional only- Claude Opus 5.5
- 76.0
- Estimated · #4/159
- Gemini 3 Flash
- 42.4
- Supported · #112/159
- Basis
- BenchAlign lane · 9 vs 3 public rows
- Reading
- Directional only
Knowledge
Directional only- Claude Opus 5.5
- 81.5
- Estimated · #3/187
- Gemini 3 Flash
- 57.1
- Supported · #45/187
- Basis
- BenchAlign lane · 17 vs 2 public rows
- Reading
- Directional only
Reasoning
Not comparable- Claude Opus 5.5
- 78.5
- #4/19
- Gemini 3 Flash
- 59.0
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Claude Opus 5.5
- 88.8
- #3/50
- Gemini 3 Flash
- 75.8
- Unranked · 1 rankable row
- Basis
- Provisional lane · 1 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude Opus 5.5
- Not ranked
- Gemini 3 Flash
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Claude Opus 5.5
- Not ranked
- Gemini 3 Flash
- 64.7
- #70/124
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- Claude Opus 5.5
- Not ranked
- Gemini 3 Flash
- 50.0
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 0 vs 2 weighted rows
- Reading
- Not comparable
| Category | Claude Opus 5.5 | Gemini 3 Flash | Basis | Reading |
|---|---|---|---|---|
| Agentic | 82.7Supported · #1/156 | 36.1Supported · #137/156 | Like-for-likeBenchAlign lane · 11 vs 4 public rows | Claude Opus 5.5 leads |
| Coding | 76.0Estimated · #4/159 | 42.4Supported · #112/159 | Directional onlyBenchAlign lane · 9 vs 3 public rows | Directional only |
| Knowledge | 81.5Estimated · #3/187 | 57.1Supported · #45/187 | Directional onlyBenchAlign lane · 17 vs 2 public rows | Directional only |
| Reasoning | 78.5#4/19 | 59.0Unranked · 2 rankable rows | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | 88.8#3/50 | 75.8Unranked · 1 rankable row | Not comparableProvisional lane · 1 vs 0 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | Not ranked | 64.7#70/124 | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | Not ranked | 50.0Unranked · 2 rankable rows | Not comparableProvisional lane · 0 vs 2 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.
A shared-evidence shape is not available.
BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.
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 Opus 5.5
- $0.014
- Fits in one request
- Gemini 3 Flash
- $0.002
- Fits in one request
Gemini 3 Flash has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Claude Opus 5.5
- $0.26
- Fits in one request
- Gemini 3 Flash
- $0.034
- Fits in one request
Gemini 3 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 Opus 5.5
- $0.32
- Fits in one request
- Gemini 3 Flash
- $0.05
- Fits in one request
Gemini 3 Flash has the lower modeled cost
Costs use the listed standard API rates.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationClaude Opus 5.5Gemini 3 Flash
Context window
Maximum documented context; output-token limits may be lower.
Claude Opus 5.5
Gemini 3 Flash
API model ID
Claude Opus 5.5
claude-opus-5-5
Anthropic Claude Opus 5.5 model documentationGemini 3 Flash
gemini-3-flash-preview
Google Gemini API pricingCached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Claude Opus 5.5
$0.2 per 1M cached input tokens
Claude Opus 5.5 model documentationGemini 3 Flash
$0.05 per 1M cached input tokens
Google Gemini API pricingDocumented inputs
Claude Opus 5.5
Gemini 3 Flash
Not sourced
Documented outputs
Claude Opus 5.5
Gemini 3 Flash
Not sourced
Provider availability
Claude Opus 5.5
Generally Available · Claude API, Amazon Bedrock, Google Cloud, Microsoft Foundry, Claude Platform on AWS
Anthropic Claude Opus 5.5 model documentationGemini 3 Flash
Not sourced
Reasoning profile
Claude Opus 5.5
Reasoning
Gemini 3 Flash
Non-Reasoning
Weight access
Claude Opus 5.5
Proprietary
Gemini 3 Flash
Proprietary
License
Claude Opus 5.5
Proprietary
Gemini 3 Flash
Proprietary
Release date
Claude Opus 5.5
2026-09-22
Gemini 3 Flash
2025-12-01
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
- The public evidence has no benchmark result shared by both models, so it does not support a quality verdict.
- Workload cost
- Repository review: $0.26 vs $0.034. Cache-heavy agent loop: $0.32 vs $0.05.
- Context tradeoff
- Both models list 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 evidence59 rows
Agentic
Terminal-Bench 4.0
Claude Opus 5.566.40%SourceGemini 3 Flash—Not directly comparable
Terminal-Bench-Science 0.1
Claude Opus 5.558.7%SourceGemini 3 Flash—Not directly comparable
AutomationBench
Claude Opus 5.540.0%SourceGemini 3 Flash—Not directly comparable
HLE w/ tools
Claude Opus 5.567.7%SourceGemini 3 Flash—Not directly comparable
OSWorld 2.0
Claude Opus 5.548.7%SourceGemini 3 Flash—Not directly comparable
LAB all-pass (Harvey held-out)
Claude Opus 5.58.3%SourceGemini 3 Flash—Not directly comparable
LAB criterion-pass (Harvey held-out)
Claude Opus 5.591.2%SourceGemini 3 Flash—Not directly comparable
Toolathlon-Verified
Claude Opus 5.577.8%SourceGemini 3 Flash—Not directly comparable
Toolathlon Verified Pass@3
Claude Opus 5.582.4%SourceGemini 3 Flash—Not directly comparable
Toolathlon Verified Pass³
Claude Opus 5.572.2%SourceGemini 3 Flash—Not directly comparable
Toolathlon Verified avg. turns
Claude Opus 5.526.9 turnsSourceGemini 3 Flash—Not directly comparable
Claw-Eval
Claude Opus 5.5—Gemini 3 Flash49.2%SourceNot directly comparable
Gert Labs
Claude Opus 5.5—Gemini 3 Flash56.63%SourceNot directly comparable
JobBench
Claude Opus 5.5—Gemini 3 Flash11.4%SourceNot directly comparable
Terminal-Bench 2.1 (Vals)
Claude Opus 5.5—Gemini 3 Flash53.9%SourceNot directly comparable
Coding
FrontierCode 1.1 Main
Claude Opus 5.554.4%SourceGemini 3 Flash—Not directly comparable
cursorBench40
Claude Opus 5.557.8%SourceGemini 3 Flash—Not directly comparable
SWE-bench Pro
Claude Opus 5.589.9%SourceGemini 3 Flash—Not directly comparable
SWE Multilingual
Claude Opus 5.593.9%SourceGemini 3 Flash—Not directly comparable
SWE Multimodal
Claude Opus 5.561.4%SourceGemini 3 Flash—Not directly comparable
DeepSWE
Claude Opus 5.574.2%SourceGemini 3 Flash—Not directly comparable
FrontierCode 1.1 Extended
Claude Opus 5.563.6%SourceGemini 3 Flash—Not directly comparable
FrontierSWE v2
Claude Opus 5.562.3%SourceGemini 3 Flash—Not directly comparable
ProgramBench
Claude Opus 5.591.2%SourceGemini 3 Flash—Not directly comparable
Vibe Code Bench
Claude Opus 5.5—Gemini 3 Flash20.20%SourceNot directly comparable
LiveCodeBench (Vals)
Claude Opus 5.5—Gemini 3 Flash85.6%SourceNot directly comparable
SWE-bench (Vals)
Claude Opus 5.5—Gemini 3 Flash75.0%SourceNot directly comparable
Multimodal
Chartography (tools)
Claude Opus 5.589.0%SourceGemini 3 Flash—Not directly comparable
Chartography (no tools)
Claude Opus 5.564.4%SourceGemini 3 Flash—Not directly comparable
BenchCAD Vision2Code (no tools)
Claude Opus 5.50.730SourceGemini 3 Flash—Not directly comparable
BenchCAD Vision2Code (tools)
Claude Opus 5.50.962SourceGemini 3 Flash—Not directly comparable
Biomedical image analysis
Claude Opus 5.571.4%SourceGemini 3 Flash—Not directly comparable
OfficeQA
Claude Opus 5.578.9%SourceGemini 3 Flash—Not directly comparable
OfficeQA Pro
Claude Opus 5.567.7%SourceGemini 3 Flash—Not directly comparable
Knowledge
HLE
Claude Opus 5.567.7%SourceGemini 3 Flash—Not directly comparable
HLE w/o tools
Claude Opus 5.564.4%SourceGemini 3 Flash—Not directly comparable
HealthBench (raw)
Claude Opus 5.568.1%SourceGemini 3 Flash—Not directly comparable
HealthBench (length-adjusted)
Claude Opus 5.560.6%SourceGemini 3 Flash—Not directly comparable
HealthBench Professional
Claude Opus 5.565.6%SourceGemini 3 Flash—Not directly comparable
HealthBench Professional (raw)
Claude Opus 5.577.1%SourceGemini 3 Flash—Not directly comparable
BioMysteryBench (human-solvable)
Claude Opus 5.589.3%SourceGemini 3 Flash—Not directly comparable
BioMysteryBench (human-difficult)
Claude Opus 5.550.0%SourceGemini 3 Flash—Not directly comparable
SpatialBench Verified
Claude Opus 5.572.0%SourceGemini 3 Flash—Not directly comparable
SingleCellBench
Claude Opus 5.561.2%SourceGemini 3 Flash—Not directly comparable
Morphology-to-molecule matching
Claude Opus 5.534.0%SourceGemini 3 Flash—Not directly comparable
Medicinal chemistry
Claude Opus 5.563.5%SourceGemini 3 Flash—Not directly comparable
Protein Design
Claude Opus 5.560.2%SourceGemini 3 Flash—Not directly comparable
Protein Design library ranking
Claude Opus 5.556.0%SourceGemini 3 Flash—Not directly comparable
De novo protein-binder design
Claude Opus 5.582.6%SourceGemini 3 Flash—Not directly comparable
Protocols (troubleshooting)
Claude Opus 5.573.7%SourceGemini 3 Flash—Not directly comparable
Protocols (understanding)
Claude Opus 5.569.0%SourceGemini 3 Flash—Not directly comparable
GPQA Diamond (Vals)
Claude Opus 5.5—Gemini 3 Flash87.9%SourceNot directly comparable
MMLU-Pro (Vals)
Claude Opus 5.5—Gemini 3 Flash88.6%SourceNot directly comparable
Multilingual
Math
ArXivMath Aug. 2026 (no tools)
Claude Opus 5.591.2%SourceGemini 3 Flash—Not directly comparable
ArXivMath Aug. 2026 (tools)
Claude Opus 5.596.9%SourceGemini 3 Flash—Not directly comparable
FrontierMath v2 (Tiers 1-3)
Claude Opus 5.5—Gemini 3 Flash35.640%SourceNot directly comparable
FrontierMath v2 (Tier 4)
Claude Opus 5.5—Gemini 3 Flash4.167%SourceNot directly comparable
Questions
Which is better, Claude Opus 5.5 or Gemini 3 Flash?
The public evidence has no benchmark result shared by both models, so it does not support a quality verdict. The page therefore keeps the decision tied to the specific documented workload.
Which is better for coding, Claude Opus 5.5 or Gemini 3 Flash?
Claude Opus 5.5 scores higher for coding on the public lane, 76 to 42.4. Claude Opus 5.5 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 Opus 5.5 or Gemini 3 Flash?
Claude Opus 5.5 leads the public agentic tasks lane, 82.7 to 36.1, with Supported evidence for both models and non-overlapping 90% intervals.
Which costs less, Claude Opus 5.5 or Gemini 3 Flash?
For the stated presets, chat costs $0.014 on Claude Opus 5.5 and $0.002 on Gemini 3 Flash; repository review costs $0.26 and $0.034; the cache-heavy agent loop costs $0.32 and $0.05. Costs use the listed standard API rates.
Which has the larger context window, Claude Opus 5.5 or Gemini 3 Flash?
Both models list the same context window, 1M.
Related comparisons
Last updated September 22, 2026
Watch Claude Opus 5.5 vs Gemini 3 Flash
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.