Coding work
Code generation, repair, and software-engineering tasks
Claude Opus 5
Claude Opus 5 leads on the public coding lane, 72.8 to 60.3, with Supported evidence for both models, although the 90% intervals overlap.
Confidence: limited
Claude Opus 5 vs Gemini 3.7 Flash
Updated September 27, 2026. Rank says Claude Opus 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
Decision reading
Claude Opus 5 has the higher public score, 79.81 versus 67.66, and the 90% score intervals do not overlap. 18 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
- Shared results
- 18
- Claude Opus 5 only
- 56
- Gemini 3.7 Flash only
- 7
- Like-for-like categories
- 3 / 8
Supported: Claude Opus 5 and Gemini 3.7 FlashHow 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
Claude Opus 5
Claude Opus 5 leads on the public agentic lane, 77.4 to 58.6, with Supported evidence for both models and non-overlapping 90% intervals.
Confidence: strongerChat turn cost
1K fresh input + 500 output tokens
Gemini 3.7 Flash
Gemini 3.7 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
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Gemini 3.7 Flash
Gemini 3.7 Flash has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-ratesRepository review cost
50K fresh input + 3K output tokens
Gemini 3.7 Flash
Gemini 3.7 Flash has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-ratesLong 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.
72.8Claude Opus 560.3Gemini 3.7 Flash
Like-for-like · BenchAlign v5.7
Claude Opus 5 leads the like-for-like coding row, although the 90% intervals overlap.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
Same basis rules as the category table below
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
56 Claude Opus 5 only
18 Shared
7 Gemini 3.7 Flash only
1 category rests 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.
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 2.0Agentic
Normalized gap 22.7Claude Opus 5:70.6%Gemini 3.7 Flash:47.9%ARC-AGI-2Reasoning
Normalized gap 5.8Claude Opus 5:90.4%Gemini 3.7 Flash:84.6%AutomationBenchAgentic
Normalized gap 4.4Claude Opus 5:26.0%Gemini 3.7 Flash:30.4%MMLU-Pro (Vals)Knowledge
Normalized gap 1.5Claude Opus 5:91.6%Gemini 3.7 Flash:90.1%LiveCodeBench (Vals)Coding
Normalized gap 0.3Claude Opus 5:89.0%Gemini 3.7 Flash:88.7%
Bars run 0–100 on each benchmark’s normalized display scale
Category results, on a stated basis
Each row shows the public-lane category score for both models: the BenchAlign v5.7 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.
Agentic
Like-for-like- Claude Opus 5
- 77.4
- Supported · #3/105
- Gemini 3.7 Flash
- 58.6
- Supported · #20/105
- Basis
- BenchAlign v5.7 lane · 20 vs 7 public rows
- Reading
- Claude Opus 5 leads
Coding
Like-for-like- Claude Opus 5
- 72.8
- Supported · #5/135
- Gemini 3.7 Flash
- 60.3
- Supported · #17/135
- Basis
- BenchAlign v5.7 lane · 16 vs 6 public rows
- Reading
- Claude Opus 5 leads · intervals overlap
Knowledge
Like-for-like- Claude Opus 5
- 81.4
- Supported · #5/158
- Gemini 3.7 Flash
- 71.1
- Supported · #10/158
- Basis
- BenchAlign v5.7 lane · 19 vs 6 public rows
- Reading
- Claude Opus 5 leads · intervals overlap
Multimodal
Directional only- Claude Opus 5
- 88.8
- #2/50
- Gemini 3.7 Flash
- 82.6
- #10/50
- Basis
- Provisional lane · 1 vs 1 weighted rows
- Reading
- Directional only
Reasoning
Not comparable- Claude Opus 5
- 77.3
- #6/19
- Gemini 3.7 Flash
- 77.8
- Unranked · 5 rankable rows
- Basis
- Provisional lane · 2 vs 1 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude Opus 5
- Not ranked
- Gemini 3.7 Flash
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Claude Opus 5
- Not ranked
- Gemini 3.7 Flash
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- Claude Opus 5
- Not ranked
- Gemini 3.7 Flash
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | Claude Opus 5 | Gemini 3.7 Flash | Basis | Reading |
|---|---|---|---|---|
| Agentic | 77.4Supported · #3/105 | 58.6Supported · #20/105 | Like-for-likeBenchAlign v5.7 lane · 20 vs 7 public rows | Claude Opus 5 leads |
| Coding | 72.8Supported · #5/135 | 60.3Supported · #17/135 | Like-for-likeBenchAlign v5.7 lane · 16 vs 6 public rows | Claude Opus 5 leads · intervals overlap |
| Knowledge | 81.4Supported · #5/158 | 71.1Supported · #10/158 | Like-for-likeBenchAlign v5.7 lane · 19 vs 6 public rows | Claude Opus 5 leads · intervals overlap |
| Multimodal | 88.8#2/50 | 82.6#10/50 | Directional onlyProvisional lane · 1 vs 1 weighted rows | Directional only |
| Reasoning | 77.3#6/19 | 77.8Unranked · 5 rankable rows | Not comparableProvisional lane · 2 vs 1 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 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 v5.7) 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 Opus 5
- $0.0175
- Fits in one request
- Gemini 3.7 Flash
- $0.00262
- Fits in one request
Gemini 3.7 Flash has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Claude Opus 5
- $0.325
- Fits in one request
- Gemini 3.7 Flash
- $0.04875
- Fits in one request
Gemini 3.7 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
- $0.45
- Fits in one request
- Gemini 3.7 Flash
- $0.0675
- Fits in one request
Gemini 3.7 Flash has the lower modeled cost
Costs use the listed standard API rates.
Cached input falls back to the list input rate only where a cached rate is unpublished
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationClaude Opus 5Gemini 3.7 Flash
Context window
Maximum documented context; output-token limits may be lower.
Claude Opus 5
Gemini 3.7 Flash
API model ID
Claude Opus 5
claude-opus-5
Anthropic model overviewGemini 3.7 Flash
gemini-3.7-flash
Google Gemini 3.7 Flash API documentationCached-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 3.7 Flash
$0.075 per 1M cached input tokens
Google Gemini API pricingDocumented inputs
Claude Opus 5
text, image
Anthropic model overviewGemini 3.7 Flash
text, image, video, audio, pdf
Google Gemini 3.7 Flash API documentationDocumented outputs
Claude Opus 5
Gemini 3.7 Flash
Provider availability
Claude Opus 5
Generally Available · Claude API
Anthropic model overviewGemini 3.7 Flash
Generally Available · Gemini API, Google AI Studio, Gemini App - Spark, Gemini Enterprise App, Gemini Enterprise Agent Platform, Google Antigravity
Google DeepMind Gemini 3.7 Flash model cardReasoning profile
Claude Opus 5
Reasoning
Gemini 3.7 Flash
Reasoning
Weight access
Claude Opus 5
Proprietary
Gemini 3.7 Flash
Proprietary
License
Claude Opus 5
Proprietary
Gemini 3.7 Flash
Proprietary
Release date
Claude Opus 5
2026-07-24
Gemini 3.7 Flash
2026-08-13
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, 79.81 versus 67.66, and the 90% score intervals do not overlap.
- Workload cost
- Repository review: $0.325 vs $0.04875. Cache-heavy agent loop: $0.45 vs $0.0675.
- Context tradeoff
- Both models list 1M.
Run the same representative tasks against both endpoints before changing production traffic.
Questions
Which is better, Claude Opus 5 or Gemini 3.7 Flash?
Claude Opus 5 has the higher public score, 79.81 versus 67.66, 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 3.7 Flash?
Claude Opus 5 leads the public coding lane, 72.8 to 60.3, with Supported evidence for both models, although the 90% intervals overlap.
Which is better for agentic tasks, Claude Opus 5 or Gemini 3.7 Flash?
Claude Opus 5 leads the public agentic tasks lane, 77.4 to 58.6, with Supported evidence for both models and non-overlapping 90% intervals.
Which costs less, Claude Opus 5 or Gemini 3.7 Flash?
For the stated presets, chat costs $0.0175 on Claude Opus 5 and $0.00263 on Gemini 3.7 Flash; repository review costs $0.325 and $0.04875; the cache-heavy agent loop costs $0.45 and $0.0675. Costs use the listed standard API rates.
Which has the larger context window, Claude Opus 5 or Gemini 3.7 Flash?
Both models list the same context window, 1M.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence81 rows
Agentic
Terminal-Bench 3.0
Claude Opus 542.7%SourceGemini 3.7 Flash14.9%SourceClaude Opus 5 leads this result
BrowseComp
Claude Opus 590.8%SourceGemini 3.7 Flash—Not directly comparable
HLE w/ tools
Claude Opus 564.7%SourceGemini 3.7 Flash—Not directly comparable
DeepSearchQA
Claude Opus 595.0%SourceGemini 3.7 Flash—Not directly comparable
DRACO
Claude Opus 588.6%SourceGemini 3.7 Flash—Not directly comparable
BrowseComp (10-agent, prerelease)
Claude Opus 593.6%SourceGemini 3.7 Flash—Not directly comparable
OSWorld 2.0
Claude Opus 570.6%SourceGemini 3.7 Flash47.9%SourceClaude Opus 5 leads this result
MCP Atlas
Claude Opus 585.8%SourceGemini 3.7 Flash—Not directly comparable
MCP-Atlas claim coverage
Claude Opus 589.1%SourceGemini 3.7 Flash—Not directly comparable
LAB all-pass (Anthropic harness)
Claude Opus 523.58%SourceGemini 3.7 Flash—Not directly comparable
LAB criterion-pass (Anthropic harness)
Claude Opus 593.74%SourceGemini 3.7 Flash—Not directly comparable
LAB all-pass (Harvey held-out)
Claude Opus 511.7%SourceGemini 3.7 Flash—Not directly comparable
LAB criterion-pass (Harvey held-out)
Claude Opus 594.1%SourceGemini 3.7 Flash—Not directly comparable
Toolathlon-Verified
Claude Opus 580.6%SourceGemini 3.7 Flash—Not directly comparable
Toolathlon Verified Pass@3
Claude Opus 587.0%SourceGemini 3.7 Flash—Not directly comparable
Toolathlon Verified Pass³
Claude Opus 573.1%SourceGemini 3.7 Flash—Not directly comparable
Toolathlon Verified avg. turns
Claude Opus 523.5 turnsSourceGemini 3.7 Flash—Not directly comparable
AutomationBench
Claude Opus 526.0%SourceGemini 3.7 Flash30.4%SourceGemini 3.7 Flash leads this result
Terminal-Bench 2.1 (Vals)
Claude Opus 584.6%SourceGemini 3.7 Flash77.5%SourceClaude Opus 5 leads this result
ApprenticeBench
Shared sourceClaude Opus 536%Gemini 3.7 Flash16%Claude Opus 5 leads this result
Terminal-Bench 2.1
Claude Opus 5—Gemini 3.7 Flash85.8%SourceNot directly comparable
Agents' Last Exam
Claude Opus 5—Gemini 3.7 Flash26.3%SourceNot directly comparable
Coding
Bug Hunt Bench
Claude Opus 527 fixesSourceGemini 3.7 Flash—Not directly comparable
SWE-bench Verified
Claude Opus 596%SourceGemini 3.7 Flash—Not directly comparable
SWE-bench Pro
Claude Opus 579.2%SourceGemini 3.7 Flash—Not directly comparable
SWE Multilingual
Claude Opus 589.5%SourceGemini 3.7 Flash—Not directly comparable
SWE Multimodal
Claude Opus 559.4%SourceGemini 3.7 Flash—Not directly comparable
DeepSWE
Claude Opus 568.8%SourceGemini 3.7 Flash65.3%SourceClaude Opus 5 leads this result
FrontierCode 1.1 Main
Claude Opus 553.4%SourceGemini 3.7 Flash43.6%SourceClaude Opus 5 leads this result
FrontierCode 1.1 Extended
Claude Opus 563.6%SourceGemini 3.7 Flash—Not directly comparable
FrontierSWE v2
Shared sourceClaude Opus 552.0%Gemini 3.7 Flash20.3%Claude Opus 5 leads this result
ProgramBench (episode 1)
Claude Opus 583.0%SourceGemini 3.7 Flash—Not directly comparable
ProgramBench
Claude Opus 593.0%SourceGemini 3.7 Flash—Not directly comparable
cursorBench32
Claude Opus 570.0%SourceGemini 3.7 Flash—Not directly comparable
VulcanBench v3
Claude Opus 587.0%SourceGemini 3.7 Flash—Not directly comparable
VulcanBench CII v1
Claude Opus 596.4%SourceGemini 3.7 Flash—Not directly comparable
LiveCodeBench (Vals)
Claude Opus 589.0%SourceGemini 3.7 Flash88.7%SourceClaude Opus 5 leads this result
SWE-bench (Vals)
Claude Opus 597.0%SourceGemini 3.7 Flash80.8%SourceClaude Opus 5 leads this result
Terminal-Bench 2.1
Claude Opus 5—Gemini 3.7 Flash85.8%SourceNot directly comparable
Reasoning
ARC-AGI-1
Claude Opus 597.50%SourceGemini 3.7 Flash95.50%SourceClaude Opus 5 leads this result
ARC-AGI-2
Claude Opus 590.4%SourceGemini 3.7 Flash84.6%SourceClaude Opus 5 leads this result
ARC-AGI-3
Claude Opus 530.2%SourceGemini 3.7 Flash—Not directly comparable
MRCR v2 64K-128K
Claude Opus 5—Gemini 3.7 Flash97%SourceNot directly comparable
Multimodal
Chartography (no tools)
Claude Opus 529.6%SourceGemini 3.7 Flash—Not directly comparable
Chartography (tools)
Claude Opus 583.0%SourceGemini 3.7 Flash—Not directly comparable
BenchCAD Vision2Code (no tools)
Claude Opus 50.366SourceGemini 3.7 Flash—Not directly comparable
BenchCAD Vision2Code (tools)
Claude Opus 50.821SourceGemini 3.7 Flash—Not directly comparable
GDP.pdf (no tools)
Claude Opus 583.4%SourceGemini 3.7 Flash—Not directly comparable
GDP.pdf (tools)
Claude Opus 585.5%SourceGemini 3.7 Flash—Not directly comparable
OfficeQA
Claude Opus 578.1%SourceGemini 3.7 Flash—Not directly comparable
OfficeQA Pro
Claude Opus 566.9%SourceGemini 3.7 Flash—Not directly comparable
CharXiv w/o tools
Claude Opus 5—Gemini 3.7 Flash84.5%SourceNot directly comparable
CharXiv
Claude Opus 5—Gemini 3.7 Flash88.7%SourceNot directly comparable
LVBench
Claude Opus 5—Gemini 3.7 Flash85.4%SourceNot directly comparable
Knowledge
HLE
Claude Opus 564.7%SourceGemini 3.7 Flash—Not directly comparable
HLE w/o tools
Claude Opus 556.3%SourceGemini 3.7 Flash—Not directly comparable
HLE-Verified
Shared sourceClaude Opus 554.4%Gemini 3.7 Flash53.6%Claude Opus 5 leads this result
LABBench2
Shared sourceClaude Opus 584.2%Gemini 3.7 Flash82.1%Claude Opus 5 leads this result
HealthBench (raw)
Claude Opus 567.1%SourceGemini 3.7 Flash—Not directly comparable
HealthBench (length-adjusted)
Claude Opus 557.8%SourceGemini 3.7 Flash—Not directly comparable
HealthBench Professional
Claude Opus 559.8%SourceGemini 3.7 Flash—Not directly comparable
HealthBench Professional (raw)
Claude Opus 573.4%SourceGemini 3.7 Flash—Not directly comparable
BioMysteryBench (human-solvable)
Claude Opus 590.1%SourceGemini 3.7 Flash87.1%SourceClaude Opus 5 leads this result
BioMysteryBench (human-difficult)
Claude Opus 549.4%SourceGemini 3.7 Flash43.5%SourceClaude Opus 5 leads this result
SpatialBench Verified
Claude Opus 572.5%SourceGemini 3.7 Flash—Not directly comparable
SingleCellBench
Claude Opus 560.6%SourceGemini 3.7 Flash—Not directly comparable
ProteinGym Hard
Claude Opus 547.7%SourceGemini 3.7 Flash—Not directly comparable
Protein Design
Claude Opus 542.5%SourceGemini 3.7 Flash—Not directly comparable
Organic chemistry V2
Claude Opus 561.6%SourceGemini 3.7 Flash—Not directly comparable
Protocols (troubleshooting)
Claude Opus 561.1%SourceGemini 3.7 Flash—Not directly comparable
Protocols (understanding)
Claude Opus 578.4%SourceGemini 3.7 Flash—Not directly comparable
GPQA Diamond (Vals)
Claude Opus 593.4%SourceGemini 3.7 Flash93.9%SourceGemini 3.7 Flash leads this result
MMLU-Pro (Vals)
Claude Opus 591.6%SourceGemini 3.7 Flash90.1%SourceClaude Opus 5 leads this result
Multilingual
Math
IMO 2026
Claude Opus 542/42SourceGemini 3.7 Flash—Not directly comparable
RiemannBench (no tools)
Claude Opus 560.0%SourceGemini 3.7 Flash—Not directly comparable
RiemannBench (tools)
Claude Opus 579.0%SourceGemini 3.7 Flash—Not directly comparable
ArXivMath Jun. 2026 (no tools)
Claude Opus 590.8%SourceGemini 3.7 Flash—Not directly comparable
ArXivMath Jun. 2026 (tools)
Claude Opus 591.3%SourceGemini 3.7 Flash—Not directly comparable
81 public results · 18 shared
Watch Claude Opus 5 vs Gemini 3.7 Flash
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.
Last updated September 27, 2026