Agentic
Not comparable- Claude Opus 5
- 77.4
- Supported · #2/151
- Gemini 3 Pro Deep Think
- Not ranked
- Basis
- BenchAlign lane · 19 vs 0 public rows
- Reading
- Not comparable
Claude Opus 5 vs Gemini 3 Pro Deep Think
Updated September 4, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
Claude Opus 5 has the higher public score, 80.66 versus 60.67, and the 90% score intervals do not overlap.
1 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.
No workload recommendation clears the current evidence threshold.
Use the matched evidence, workload costs, and sourced specifications below instead of treating a point score as a universal answer.
Show secondary and unsupported calls
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Gemini 3 Pro Deep Think is not ranked on the public lane for coding, so no winner is named for coding.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Gemini 3 Pro Deep Think is not ranked on the public lane for agentic, so no winner is named for agentic.
Confidence: limited
Long documents
Prompts that approach the documented context limit
Not enough matched evidence
A complete context comparison is not sourced.
Confidence: limited
Chat turn cost
1K fresh input + 500 output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Repository review cost
50K fresh input + 3K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
72 Claude Opus 5 only
1 Shared
- Shared results
- 1
- Claude Opus 5 only
- 72
- Gemini 3 Pro Deep Think only
- 0
- Like-for-like categories
- 0 / 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
Not comparable- Claude Opus 5
- 75.6
- Supported · #3/183
- Gemini 3 Pro Deep Think
- Not ranked
- Basis
- BenchAlign lane · 16 vs 0 public rows
- Reading
- Not comparable
Reasoning
Not comparable- Claude Opus 5
- 75.6
- #13/22
- Gemini 3 Pro Deep Think
- 32.8
- Unranked · 1 rankable row
- Basis
- Provisional lane · 2 vs 1 weighted rows
- Reading
- Not comparable
Knowledge
Not comparable- Claude Opus 5
- 82.1
- Supported · #3/181
- Gemini 3 Pro Deep Think
- Not ranked
- Basis
- BenchAlign lane · 19 vs 0 public rows
- Reading
- Not comparable
Math
Not comparable- Claude Opus 5
- Not ranked
- Gemini 3 Pro Deep Think
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude Opus 5
- Not ranked
- Gemini 3 Pro Deep Think
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Claude Opus 5
- 88.7
- #2/48
- Gemini 3 Pro Deep Think
- Not ranked
- Basis
- Provisional lane · 1 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Claude Opus 5
- Not ranked
- Gemini 3 Pro Deep Think
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | Claude Opus 5 | Gemini 3 Pro Deep Think | Basis | Reading |
|---|---|---|---|---|
| Agentic | 77.4Supported · #2/151 | Not ranked | Not comparableBenchAlign lane · 19 vs 0 public rows | Not comparable |
| Coding | 75.6Supported · #3/183 | Not ranked | Not comparableBenchAlign lane · 16 vs 0 public rows | Not comparable |
| Reasoning | 75.6#13/22 | 32.8Unranked · 1 rankable row | Not comparableProvisional lane · 2 vs 1 weighted rows | Not comparable |
| Knowledge | 82.1Supported · #3/181 | Not ranked | Not comparableBenchAlign lane · 19 vs 0 public rows | Not comparable |
| Math | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | 88.7#2/48 | Not ranked | Not comparableProvisional lane · 1 vs 0 weighted rows | Not comparable |
| Instruction following | Not ranked | 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.
ARC-AGI-2
Reasoning
Claude Opus 5: 90.4%Gemini 3 Pro Deep Think: 45.1%Normalized gap 45.3Claude Opus 5 source Gemini 3 Pro Deep Think 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 Opus 5
- $0.0175
- Fits in one request
- Gemini 3 Pro Deep Think
- API rate not published
- Fit state unavailable
Gemini 3 Pro Deep Think has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- Claude Opus 5
- $0.325
- Fits in one request
- Gemini 3 Pro Deep Think
- API rate not published
- Fit state unavailable
Gemini 3 Pro Deep Think has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Claude Opus 5
- $0.45
- Fits in one request
- Gemini 3 Pro Deep Think
- API rate not published
- Fit state unavailable
- Cached-input rate unavailable
Gemini 3 Pro Deep Think has no comparable published API token rate.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationClaude Opus 5Gemini 3 Pro Deep Think
Context window
Maximum documented context; output-token limits may be lower.
Claude Opus 5
Gemini 3 Pro Deep Think
Not sourced
Google Gemini 3 Deep Think launchAPI model ID
Claude Opus 5
claude-opus-5
Anthropic model overviewGemini 3 Pro Deep Think
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Claude Opus 5
$0.5 per 1M cached input tokens
Claude API pricingGemini 3 Pro Deep Think
No comparable hosted API rate
Documented inputs
Claude Opus 5
text, image
Anthropic model overviewGemini 3 Pro Deep Think
Not sourced
Documented outputs
Claude Opus 5
Gemini 3 Pro Deep Think
Not sourced
Provider availability
Claude Opus 5
Generally Available · Claude API
Anthropic model overviewGemini 3 Pro Deep Think
Limited Access · Gemini app for Google AI Ultra, Gemini API early-access program
Google Gemini 3 Deep Think launchReasoning profile
Claude Opus 5
Reasoning
Gemini 3 Pro Deep Think
Reasoning
Weight access
Claude Opus 5
Proprietary
Gemini 3 Pro Deep Think
Proprietary
License
Claude Opus 5
Proprietary
Gemini 3 Pro Deep Think
Proprietary
Release date
Claude Opus 5
2026-07-24
Gemini 3 Pro Deep Think
2026-02-12
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
- Claude Opus 5 has the higher public score, 80.66 versus 60.67, and the 90% score intervals do not overlap.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- Context tradeoff
- A complete documented context comparison is not available.
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 evidence73 rows
Agentic
Terminal-Bench 3.0
Claude Opus 542.7%SourceGemini 3 Pro Deep Think—Not directly comparable
BrowseComp
Claude Opus 590.8%SourceGemini 3 Pro Deep Think—Not directly comparable
HLE w/ tools
Claude Opus 564.7%SourceGemini 3 Pro Deep Think—Not directly comparable
DeepSearchQA
Claude Opus 595.0%SourceGemini 3 Pro Deep Think—Not directly comparable
DRACO
Claude Opus 588.6%SourceGemini 3 Pro Deep Think—Not directly comparable
BrowseComp (10-agent, prerelease)
Claude Opus 593.6%SourceGemini 3 Pro Deep Think—Not directly comparable
OSWorld 2.0
Claude Opus 570.6%SourceGemini 3 Pro Deep Think—Not directly comparable
MCP Atlas
Claude Opus 585.8%SourceGemini 3 Pro Deep Think—Not directly comparable
MCP-Atlas claim coverage
Claude Opus 589.1%SourceGemini 3 Pro Deep Think—Not directly comparable
LAB all-pass (Anthropic harness)
Claude Opus 523.58%SourceGemini 3 Pro Deep Think—Not directly comparable
LAB criterion-pass (Anthropic harness)
Claude Opus 593.74%SourceGemini 3 Pro Deep Think—Not directly comparable
LAB all-pass (Harvey held-out)
Claude Opus 511.7%SourceGemini 3 Pro Deep Think—Not directly comparable
LAB criterion-pass (Harvey held-out)
Claude Opus 594.1%SourceGemini 3 Pro Deep Think—Not directly comparable
Toolathlon-Verified
Claude Opus 580.6%SourceGemini 3 Pro Deep Think—Not directly comparable
Toolathlon Verified Pass@3
Claude Opus 587.0%SourceGemini 3 Pro Deep Think—Not directly comparable
Toolathlon Verified Pass³
Claude Opus 573.1%SourceGemini 3 Pro Deep Think—Not directly comparable
Toolathlon Verified avg. turns
Claude Opus 523.5 turnsSourceGemini 3 Pro Deep Think—Not directly comparable
AutomationBench
Claude Opus 526.0%SourceGemini 3 Pro Deep Think—Not directly comparable
Terminal-Bench 2.1 (Vals)
Claude Opus 584.6%SourceGemini 3 Pro Deep Think—Not directly comparable
Coding
Bug Hunt Bench
Claude Opus 527 fixesSourceGemini 3 Pro Deep Think—Not directly comparable
SWE-bench Verified
Claude Opus 596%SourceGemini 3 Pro Deep Think—Not directly comparable
SWE-bench Pro
Claude Opus 579.2%SourceGemini 3 Pro Deep Think—Not directly comparable
SWE Multilingual
Claude Opus 589.5%SourceGemini 3 Pro Deep Think—Not directly comparable
SWE Multimodal
Claude Opus 559.4%SourceGemini 3 Pro Deep Think—Not directly comparable
deepSwe
Claude Opus 568.8%SourceGemini 3 Pro Deep Think—Not directly comparable
FrontierCode 1.1 Main
Claude Opus 553.4%SourceGemini 3 Pro Deep Think—Not directly comparable
FrontierCode 1.1 Extended
Claude Opus 563.6%SourceGemini 3 Pro Deep Think—Not directly comparable
FrontierSWE v2
Claude Opus 552.0%SourceGemini 3 Pro Deep Think—Not directly comparable
ProgramBench (episode 1)
Claude Opus 583.0%SourceGemini 3 Pro Deep Think—Not directly comparable
ProgramBench
Claude Opus 593.0%SourceGemini 3 Pro Deep Think—Not directly comparable
cursorBench32
Claude Opus 570.0%SourceGemini 3 Pro Deep Think—Not directly comparable
VulcanBench v3
Claude Opus 587.0%SourceGemini 3 Pro Deep Think—Not directly comparable
VulcanBench CII v1
Claude Opus 596.4%SourceGemini 3 Pro Deep Think—Not directly comparable
LiveCodeBench (Vals)
Claude Opus 589.0%SourceGemini 3 Pro Deep Think—Not directly comparable
SWE-bench (Vals)
Claude Opus 597.0%SourceGemini 3 Pro Deep Think—Not directly comparable
Reasoning
Knowledge
HLE
Claude Opus 564.7%SourceGemini 3 Pro Deep Think—Not directly comparable
HLE w/o tools
Claude Opus 556.3%SourceGemini 3 Pro Deep Think—Not directly comparable
HLE-Verified
Claude Opus 554.4%SourceGemini 3 Pro Deep Think—Not directly comparable
LABBench2
Claude Opus 584.2%SourceGemini 3 Pro Deep Think—Not directly comparable
HealthBench (raw)
Claude Opus 567.1%SourceGemini 3 Pro Deep Think—Not directly comparable
HealthBench (length-adjusted)
Claude Opus 557.8%SourceGemini 3 Pro Deep Think—Not directly comparable
HealthBench Professional
Claude Opus 559.8%SourceGemini 3 Pro Deep Think—Not directly comparable
HealthBench Professional (raw)
Claude Opus 573.4%SourceGemini 3 Pro Deep Think—Not directly comparable
BioMysteryBench (human-solvable)
Claude Opus 590.1%SourceGemini 3 Pro Deep Think—Not directly comparable
BioMysteryBench (human-difficult)
Claude Opus 549.4%SourceGemini 3 Pro Deep Think—Not directly comparable
SpatialBench Verified
Claude Opus 572.5%SourceGemini 3 Pro Deep Think—Not directly comparable
SingleCellBench
Claude Opus 560.6%SourceGemini 3 Pro Deep Think—Not directly comparable
ProteinGym Hard
Claude Opus 547.7%SourceGemini 3 Pro Deep Think—Not directly comparable
Protein Design
Claude Opus 542.5%SourceGemini 3 Pro Deep Think—Not directly comparable
Organic chemistry V2
Claude Opus 561.6%SourceGemini 3 Pro Deep Think—Not directly comparable
Protocols (troubleshooting)
Claude Opus 561.1%SourceGemini 3 Pro Deep Think—Not directly comparable
Protocols (understanding)
Claude Opus 578.4%SourceGemini 3 Pro Deep Think—Not directly comparable
GPQA Diamond (Vals)
Claude Opus 593.4%SourceGemini 3 Pro Deep Think—Not directly comparable
MMLU-Pro (Vals)
Claude Opus 591.6%SourceGemini 3 Pro Deep Think—Not directly comparable
Math
IMO 2026
Claude Opus 542/42SourceGemini 3 Pro Deep Think—Not directly comparable
RiemannBench (no tools)
Claude Opus 560.0%SourceGemini 3 Pro Deep Think—Not directly comparable
RiemannBench (tools)
Claude Opus 579.0%SourceGemini 3 Pro Deep Think—Not directly comparable
ArXivMath Jun. 2026 (no tools)
Claude Opus 590.8%SourceGemini 3 Pro Deep Think—Not directly comparable
ArXivMath Jun. 2026 (tools)
Claude Opus 591.3%SourceGemini 3 Pro Deep Think—Not directly comparable
Multilingual
Multimodal
Chartography (no tools)
Claude Opus 529.6%SourceGemini 3 Pro Deep Think—Not directly comparable
Chartography (tools)
Claude Opus 583.0%SourceGemini 3 Pro Deep Think—Not directly comparable
BenchCAD Vision2Code (no tools)
Claude Opus 50.366SourceGemini 3 Pro Deep Think—Not directly comparable
BenchCAD Vision2Code (tools)
Claude Opus 50.821SourceGemini 3 Pro Deep Think—Not directly comparable
GDP.pdf (no tools)
Claude Opus 583.4%SourceGemini 3 Pro Deep Think—Not directly comparable
GDP.pdf (tools)
Claude Opus 585.5%SourceGemini 3 Pro Deep Think—Not directly comparable
OfficeQA
Claude Opus 578.1%SourceGemini 3 Pro Deep Think—Not directly comparable
OfficeQA Pro
Claude Opus 566.9%SourceGemini 3 Pro Deep Think—Not directly comparable
Frequently asked questions
Which is better, Claude Opus 5 or Gemini 3 Pro Deep Think?
Claude Opus 5 has the higher public score, 80.66 versus 60.67, and the 90% score intervals do not overlap. That is the clearest overall quality signal in the current public data.
Which is better for coding, Claude Opus 5 or Gemini 3 Pro Deep Think?
Gemini 3 Pro Deep Think is not ranked on the public lane for coding, so no winner is named for coding.
Which is better for agentic tasks, Claude Opus 5 or Gemini 3 Pro Deep Think?
Gemini 3 Pro Deep Think is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.
Which costs less, Claude Opus 5 or Gemini 3 Pro Deep Think?
Both models do not have comparable published API token rates, so this page does not name a universal price winner.
Which has the larger context window, Claude Opus 5 or Gemini 3 Pro Deep Think?
A complete documented context-window comparison is not available.
Related comparisons
Last updated September 4, 2026
Watch Claude Opus 5 vs Gemini 3 Pro Deep Think
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.