Skip to main content

AnthropicGoogleLLM matchup

Claude Opus 5vs.Gemini 3.7 Flash

Which one is better?

Claude Opus 5 performs better than Gemini 3.7 Flash.

Opus 5 ahead
IntelligenceOverall index, 100 points = average
117.3

Claude Opus 5

Rank 10

107.7

Gemini 3.7 Flash

Rank 17

about as fast
SpeedTokens per second
65

Claude Opus 5

76

Gemini 3.7 Flash

Price$ per 1M tokens
$10

Claude Opus 5

n/a

Gemini 3.7 Flash

Popularity0 to 100
81

Claude Opus 5

Rank 18 of 504

n/a

Gemini 3.7 Flash

Choose Claude Opus 5 for

HealthCodingFinanceLegalMathematicsGeneralKnowledgeMultimodal (not certain)

Choose Gemini 3.7 Flash for

Reasoning

Where is the difference?

Strengths at a glance

Opus 5Gemini 3.7 FlashMedian of all ranked models

11013015090CodingOpus 5ReasoningGemini 3.7FlashMathematicsOpus 5KnowledgeOpus 5AgentslevelGeneralOpus 5Multimodalslightly Opus5FinanceOpus 5LegalOpus 5HealthOpus 5
CodingOpus 5 ahead
Opus 5118.3Rank 9
Gemini 3.7 Flash97.7Rank 41
Median of ranked models87.5

95 % range: Opus 5 114.6 to 122.1, Gemini 3.7 Flash 93.1 to 102.2.

AreaOpus 5Gemini 3.7 Flash

The same values and verdicts as the bars below. In the close-up the net starts at 90 points, just below the weaker model's lowest value; the reference group average is 100.

Opus 5 is ahead in 7 of 10 areas, Gemini 3.7 Flash in 1.

Opus 5 ahead: 7Opus 5 slightly ahead: 1level: 1Gemini 3.7 Flash ahead: 1

Areas in the overall index
CodingOpus 5 +21118.3 to 97.7
MathematicsOpus 5 +13113.5 to 100.2
GeneralOpus 5 +12116.4 to 104.1
ReasoningGemini 3.7 Flash +10107.6 to 117.9
KnowledgeOpus 5 +9121.9 to 112.7
Multimodalleaning Opus 5not certain · 3 tests each
Agentslevel112.0 to 112.8
Specialist fields
HealthOpus 5 +23130.0 to 106.6
FinanceOpus 5 +14119.0 to 104.8
LegalOpus 5 +14116.3 to 102.8

Bar length shows the gap in index points (full width 15 points, one standard deviation of the reference group). Solid means clearly ahead, hatched not certain yet, a thin grey bar level.

Show 3 more areas that do not count toward the overall index
Cybersecuritytoo little data112.7 to 86.1
Searchonly Opus 5 has a score
Productivityonly Opus 5 has a score

Bar length shows the gap in index points (full width 15 points, one standard deviation of the reference group). Solid means clearly ahead, hatched not certain yet, a thin grey bar level.

Which model for which task?

Everyday tasks, translated from the area values above. Each row names the values it rests on.

Writing and debugging codeOpus 5Coding 118.3 to 97.7
Maths and data analysisdepends on the partMathematics 113.5 to 100.2, Reasoning 107.6 to 117.9
Facts and researchOpus 5Knowledge 121.9 to 112.7, Search without a score for Gemini 3.7 Flash
Agents and workflowslevelAgents 112.0 to 112.8
Fast chat repliesabout the same65 to 76 tokens per second
Security analysisopenCybersecurity 112.7 to 86.1 (too little data)
Finance, legal and medical textsOpus 5Finance 119.0 to 104.8, Legal 116.3 to 102.8, Health 130.0 to 106.6
Images, screenshots and PDFsleaning Opus 5Multimodal 115.5 to 112.2

Claude Opus 5 vs. Gemini 3.7 Flash in our own test

The same prompt for both models. We show the latest attempt without fixes; it does not count toward the overall index.

Pelican on a bicycle

Prompt

Generate an SVG of a pelican riding a bicycle

Task origin: Simon Willison

Claude Opus 5

Claude Opus 5: Pelican on a bicycle
A community classic for free-form SVG drawing.

Oct 1, 2026 · 63 s · $0.14

Test details
Run date
Oct 1, 2026
API provider
openrouter
Requested API model
anthropic/claude-opus-5
Reasoning setting
high
Token limit including reasoning
8,192 tokens
Output tokens
5,423 tokens
Cost of the attempt
$0.1357
Response time
63 s
API model reported in response
anthropic/claude-opus-5
Pinned endpoint
Anthropic | anthropic/claude-opus-5-20260723
Temperature
Provider default
Test protocol
community-visual-tests-v1
Technical checks
Passed, not a quality rating

Visually reviewed. This individual test does not establish overall model quality.

Earlier attempts (1)

  • Sep 7, 2026API request failedReasoning setting: high

Gemini 3.7 Flash

The response reached the token limit. No complete recording is available.

Oct 5, 2026 · 29 s · $0.03

Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.

Test details
Run date
Oct 5, 2026
API provider
openrouter
Requested API model
google/gemini-3.7-flash
Reasoning setting
high
Token limit including reasoning
8,192 tokens
Output tokens
8,188 tokens
Cost of the attempt
$0.0307
Response time
28.8 s
API model reported in response
google/gemini-3.7-flash
Pinned endpoint
Google AI Studio | google/gemini-3.7-flash-20260813
Temperature
Provider default
Test protocol
community-visual-tests-v1
Technical checks
Failed

Earlier attempts (3)

  • Oct 2, 2026API request failedReasoning setting: high
  • Oct 1, 2026API request failedReasoning setting: high
  • Sep 7, 2026API request failedReasoning setting: high
SVG short test

SVG short test

One SVG task with the same fixed settings for every model, without hidden thinking.

Prompt

Return only one standalone SVG of a pelican riding a bicycle. Use viewBox="0 0 800 600", simple shapes, two clearly visible wheels and a recognizable pelican with a long beak. At most 30 SVG elements and 1800 characters. No Markdown, explanations, comments, scripts, animation, CSS or external resources.

Claude Opus 5

Unavailable in this round

Gemini 3.7 Flash

Unavailable in this round

Claude Opus 5 and Gemini 3.7 Flash in the overall index

Every model with a place in the overall index, both models of this matchup highlighted. You can add or hide other models.

Overall index (Gradually Meta-Score v6)

20 of 95 models

Claude Fable 5.2max130.9
Gemini 4 Carbonhigh127.0
Claude Opus 5.5max125.7
Claude Fable 5.1max124.1
Claude Sonnet 5.5max121.9
Gemini 4 Argonhigh121.2
GPT-6 Astramax119.6
Muse Wonder Fullmax118.4
GPT-6.1 Solmax117.5
Claude Opus 5max117.3
Muse Wondermax113.7
Claude Fable 5max112.8
Kimi K3.1 Promax112.6
Muse Ember 1.0max110.5
GPT-5.6 Solmax109.3
GPT-6 Solmax108.4
Gemini 3.7 Flashhigh107.7
DeepSeek V4.1 Flash 1017max107.1
GPT-6.1 Terramax106.5
Gemini 3.8 Flashhigh106.4

Popularity compared

How often the models are searched for, used and mentioned, on a scale from 0 to 100.

Gemini 3.7 Flash has no popularity score yet.

Over time

Weekly values from October 18, 2026 to November 16, 2026

Claude Opus 5Gemini 3.7 Flash

All data side by side

The better value is bold. For the overall index only when the gap is clear.

MetricClaude Opus 5Gemini 3.7 Flash
Intelligence
Overall indexpoints, 100 = reference group average, higher is better117.3107.7
RankRank 10 of 95Rank 17 of 95
Price per 1M tokens
Inputwhat you send$5n/a
Outputwhat the model writes$25n/a
Cost per task (own tests)average of 2 original-protocol tasks both models passed (SVG short test not included)$0.13$0.042
Speed
Tokens per second6576
Popularity
Popularitysearch, usage and mentions, 0 to 10081Rank 18 of 504n/a
Technical
Context windowhow much text the model reads at once1 M tokens≈ 1,500 A4 pages1.05 M tokens≈ 1,570 A4 pages
Knowledge cutoffMay 2026March 2026
ReleasedJul 24, 2026Aug 13, 2026
AvailabilityActiveDiscontinued
Open weightsnono

Prices without caching or batch discounts · Page count as a rule of thumb from Artificial Analysis

Is there a better choice?

Successor of Opus 5Claude Opus 5.5

Overall index 125.7, rank 3$4 input and $20 output per 1M tokens

Gemini 3.7 Flash vs. Claude Opus 5.5
Successor of Gemini 3.7 FlashGemini 3.8 Flash

Overall index 106.4, rank 20$0.75 input and $3.75 output per 1M tokens

Opus 5 vs. Gemini 3.8 Flash
Best model in the overall indexClaude Fable 5.2

Overall index 130.9, rank 1$8 input and $40 output per 1M tokens

Opus 5 vs. Claude Fable 5.2

Shared benchmarks

Single results from the same benchmark version, task and metric. A value is bold only with the same test setup and a clear gap.

A: Claude Opus 5B: Gemini 3.7 Flash

Code MigrationOverall · higher is betterTest setup not documented as identicalClaude Opus 5: 57.5%Gemini 3.7 Flash: 34.8%Vals AIAs of 10/29/2026
CyberBench v1.1Overall · higher is betterTest setup not documented as identicalClaude Opus 5: 65.4%Gemini 3.7 Flash: 43.8%Vals AIAs of 11/05/2026
EMBOverall · higher is betterTest setup not documented as identicalClaude Opus 5: 73.6%Gemini 3.7 Flash: 71.3%Vals AIAs of 10/20/2026
Finance Agent (v2)Overall · higher is betterTest setup not documented as identicalClaude Opus 5: 58.6%Gemini 3.7 Flash: 59.0%Vals AIAs of 10/29/2026
GDPval-AAOverall · higher is betterClaude Opus 5: 1,604.0 eloGemini 3.7 Flash: 1,403.7 eloArtificial AnalysisAs of 11/07/2026
GPQA DiamondOverall · higher is betterTest setup not documented as identicalClaude Opus 5: 93.4%Gemini 3.7 Flash: 93.9%Vals AIAs of 09/01/2026
IOIOverall · higher is betterTest setup not documented as identicalClaude Opus 5: 84.3%Gemini 3.7 Flash: 67.8%Vals AIAs of 10/29/2026
Legal Research BenchOverall · All-pass · higher is betterTest setup not documented as identicalClaude Opus 5: 55.3%Gemini 3.7 Flash: 34.6%Vals AIAs of 11/05/2026
LegalBenchOverall · higher is betterTest setup not documented as identicalClaude Opus 5: 87.0%Gemini 3.7 Flash: 87.3%Vals AIAs of 10/13/2026
LiveCodeBenchOverall · higher is betterTest setup not documented as identicalClaude Opus 5: 89.0%Gemini 3.7 Flash: 88.7%Vals AIAs of 09/01/2026
Show 54 more benchmarks
LMArena Code Arena WebDevOverall · higher is betterTest setup not documented as identicalClaude Opus 5: 1,691Gemini 3.7 Flash: 1,588LMArenaAs of 11/11/2026
LMArena Text, Style ControlOverall · higher is betterTest setup not documented as identicalClaude Opus 5: 1,489Gemini 3.7 Flash: 1,489LMArenaAs of 11/11/2026
LMArena Vision, Style ControlOverall · higher is betterClaude Opus 5: 1,285Gemini 3.7 Flash: 1,294LMArenaAs of 11/09/2026
MedCodeOverall · higher is betterTest setup not documented as identicalClaude Opus 5: 63.6%Gemini 3.7 Flash: 53.4%Vals AIAs of 10/29/2026
MedScribeOverall · higher is betterTest setup not documented as identicalClaude Opus 5: 91.0%Gemini 3.7 Flash: 83.9%Vals AIAs of 10/29/2026
MMLU ProOverall · higher is betterTest setup not documented as identicalClaude Opus 5: 91.6%Gemini 3.7 Flash: 90.1%Vals AIAs of 09/01/2026
MMMU ProOverall · higher is betterTest setup not documented as identicalClaude Opus 5: 89.9%Gemini 3.7 Flash: 89.0%Vals AIAs of 09/01/2026
MMMU-ProOverall · higher is betterClaude Opus 5: 82.4%Gemini 3.7 Flash: 85.5%Artificial AnalysisAs of 11/07/2026
MortgageTaxOverall · higher is betterTest setup not documented as identicalClaude Opus 5: 72.1%Gemini 3.7 Flash: 66.7%Vals AIAs of 09/01/2026
ProgramBenchOverall · higher is betterTest setup not documented as identicalClaude Opus 5: 3%Gemini 3.7 Flash: 0%Vals AIAs of 11/05/2026
ProofBench v1.1Overall · higher is betterTest setup not documented as identicalClaude Opus 5: 99%Gemini 3.7 Flash: 58%Vals AIAs of 10/29/2026
SkillsBenchOverall · higher is betterTest setup not documented as identicalClaude Opus 5: 60.4%Gemini 3.7 Flash: 65.9%Vals AIAs of 10/29/2026
SRE BenchOverall · higher is betterTest setup not documented as identicalClaude Opus 5: 12.2%Gemini 3.7 Flash: 4.6%Vals AIAs of 11/05/2026
SWE-bench VerifiedOverall · higher is betterTest setup not documented as identicalClaude Opus 5: 97.0%Gemini 3.7 Flash: 80.8%Vals AIAs of 09/01/2026
Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identicalClaude Opus 5: 23.3%Gemini 3.7 Flash: 6.7%Vals AIAs of 11/05/2026
TaxEval v2Overall · higher is betterTest setup not documented as identicalClaude Opus 5: 75.1%Gemini 3.7 Flash: 74.7%Vals AIAs of 09/01/2026
Terminal-Bench 4.0Overall · higher is betterTest setup not documented as identicalClaude Opus 5: 53.5%Gemini 3.7 Flash: 12.1%Vals AIAs of 11/05/2026
Terminal-Bench-ScienceOverall · higher is betterTest setup not documented as identicalClaude Opus 5: 27.1%Gemini 3.7 Flash: 7.1%Vals AIAs of 11/05/2026
Vibe Code Bench v1.1Overall · higher is betterTest setup not documented as identicalClaude Opus 5: 88.4%Gemini 3.7 Flash: 70.4%Vals AIAs of 11/05/2026
Code MigrationCLI · higher is betterTest setup not documented as identicalClaude Opus 5: 53.3%Gemini 3.7 Flash: 23.5%Vals AIAs of 10/29/2026
CyberBench v1.1Patch · higher is betterTest setup not documented as identicalClaude Opus 5: 85.7%Gemini 3.7 Flash: 87.5%Vals AIAs of 11/05/2026
EMBComps · higher is betterTest setup not documented as identicalClaude Opus 5: 75.2%Gemini 3.7 Flash: 74.6%Vals AIAs of 10/20/2026
Finance Agent (v2)Adjustments · higher is betterTest setup not documented as identicalClaude Opus 5: 54.6%Gemini 3.7 Flash: 54.7%Vals AIAs of 10/29/2026
GPQA DiamondFew-Shot CoT · higher is betterTest setup not documented as identicalClaude Opus 5: 92.4%Gemini 3.7 Flash: 95.5%Vals AIAs of 09/01/2026
IOIIOI 2024 · higher is betterTest setup not documented as identicalClaude Opus 5: 100.0%Gemini 3.7 Flash: 72.8%Vals AIAs of 10/29/2026
Legal Research BenchAdministrative / Regulatory · All-pass · higher is betterTest setup not documented as identicalClaude Opus 5: 65.2%Gemini 3.7 Flash: 42.4%Vals AIAs of 11/05/2026
LegalBenchConclusion Tasks · higher is betterTest setup not documented as identicalClaude Opus 5: 91.6%Gemini 3.7 Flash: 91.1%Vals AIAs of 10/13/2026
LiveCodeBenchEasy · higher is betterTest setup not documented as identicalClaude Opus 5: 99.1%Gemini 3.7 Flash: 99.1%Vals AIAs of 09/01/2026
LMArena Code Arena WebDevHTML development · higher is betterTest setup not documented as identicalClaude Opus 5: 1,679Gemini 3.7 Flash: 1,593LMArenaAs of 11/11/2026
LMArena Text, Style ControlBusiness, management and finance · higher is betterTest setup not documented as identicalClaude Opus 5: 1,483Gemini 3.7 Flash: 1,486LMArenaAs of 11/11/2026
LMArena Vision, Style ControlChinese · higher is betterClaude Opus 5: 1,364Gemini 3.7 Flash: 1,363LMArenaAs of 11/09/2026
MMLU ProBiology · higher is betterTest setup not documented as identicalClaude Opus 5: 95.7%Gemini 3.7 Flash: 94.7%Vals AIAs of 09/01/2026
MortgageTaxNumerical Extraction · higher is betterTest setup not documented as identicalClaude Opus 5: 81.4%Gemini 3.7 Flash: 75.7%Vals AIAs of 09/01/2026
ProgramBenchAlmost Resolved · higher is betterTest setup not documented as identicalClaude Opus 5: 41.5%Gemini 3.7 Flash: 9.5%Vals AIAs of 11/05/2026
SkillsBenchNo Skills · higher is betterTest setup not documented as identicalClaude Opus 5: 45.2%Gemini 3.7 Flash: 44.9%Vals AIAs of 10/29/2026
SRE BenchCapability Score · higher is betterTest setup not documented as identicalClaude Opus 5: 31.1%Gemini 3.7 Flash: 14.2%Vals AIAs of 11/05/2026
SWE-bench Verified<15 min fix · higher is betterTest setup not documented as identicalClaude Opus 5: 98.5%Gemini 3.7 Flash: 87.1%Vals AIAs of 09/01/2026
Tax Agent BenchFact-Pattern Analysis · higher is betterTest setup not documented as identicalClaude Opus 5: 48.8%Gemini 3.7 Flash: 18.6%Vals AIAs of 11/05/2026
TaxEval v2Correctness · higher is betterTest setup not documented as identicalClaude Opus 5: 62.0%Gemini 3.7 Flash: 63.6%Vals AIAs of 09/01/2026
Terminal-Bench 4.0Hardware · higher is betterTest setup not documented as identicalClaude Opus 5: 33.3%Gemini 3.7 Flash: 13.3%Vals AIAs of 11/05/2026
Terminal-Bench-ScienceEarth Sciences · higher is betterTest setup not documented as identicalClaude Opus 5: 12.5%Gemini 3.7 Flash: 0.0%Vals AIAs of 11/05/2026
Code MigrationCOBOL · higher is betterTest setup not documented as identicalClaude Opus 5: 70.0%Gemini 3.7 Flash: 68.6%Vals AIAs of 10/29/2026
CyberBench v1.1PoC · higher is betterTest setup not documented as identicalClaude Opus 5: 45%Gemini 3.7 Flash: 0%Vals AIAs of 11/05/2026
EMBDataroom · higher is betterTest setup not documented as identicalClaude Opus 5: 87.7%Gemini 3.7 Flash: 86.5%Vals AIAs of 10/20/2026
Finance Agent (v2)All-Pass · higher is betterTest setup not documented as identicalClaude Opus 5: 47.7%Gemini 3.7 Flash: 47.5%Vals AIAs of 10/29/2026
GPQA DiamondZero-Shot CoT · higher is betterTest setup not documented as identicalClaude Opus 5: 94.4%Gemini 3.7 Flash: 92.4%Vals AIAs of 09/01/2026
IOIIOI 2025 · higher is betterTest setup not documented as identicalClaude Opus 5: 87.2%Gemini 3.7 Flash: 69.8%Vals AIAs of 10/29/2026
Legal Research BenchAdministrative / Regulatory · Weighted partial credit (weighted pass) · higher is betterTest setup not documented as identicalClaude Opus 5: 92.7%Gemini 3.7 Flash: 85.1%Vals AIAs of 11/05/2026
LegalBenchInterpretation Tasks · higher is betterTest setup not documented as identicalClaude Opus 5: 85.8%Gemini 3.7 Flash: 84.6%Vals AIAs of 10/13/2026
LiveCodeBenchHard · higher is betterTest setup not documented as identicalClaude Opus 5: 77.4%Gemini 3.7 Flash: 76.3%Vals AIAs of 09/01/2026
LMArena Code Arena WebDevImage to WebDev · higher is betterTest setup not documented as identicalClaude Opus 5: 1,664Gemini 3.7 Flash: 1,600LMArenaAs of 11/10/2026
LMArena Text, Style ControlChinese · higher is betterTest setup not documented as identicalClaude Opus 5: 1,547Gemini 3.7 Flash: 1,546LMArenaAs of 11/11/2026
LMArena Vision, Style ControlCreative writing with images · higher is betterClaude Opus 5: 1,271Gemini 3.7 Flash: 1,300LMArenaAs of 11/09/2026
MMLU ProBusiness · higher is betterTest setup not documented as identicalClaude Opus 5: 93.5%Gemini 3.7 Flash: 92.8%Vals AIAs of 09/01/2026

More comparisons

Compare Claude Opus 5 and Gemini 3.7 Flash with the models people compare them with most often.

Compare another matchup

The most popular comparisons

  1. 1Claude Sonnet 5.5 vs. Claude Opus 5
  2. 2Claude Opus 5 vs. DeepSeek-V4.1-Flash
  3. 3Claude Opus 5 vs. Gemini 3.8 Flash
  4. 4Claude Opus 5 vs. Kimi K3
  5. 5Claude Opus 5 vs. GLM-5.3-Flash
  6. 6Claude Opus 5 vs. GPT-6 Astra
  7. 7Claude Opus 5 vs. DeepSeek-V4-Pro
  8. 8Claude Opus 5 vs. Qwen 3.8 27B
  9. 9Claude Opus 5 vs. GLM-5.3
Show all 44 comparisons
  1. 10Claude Opus 5 vs. Grok 4.7
  2. 11Claude Opus 5 vs. DeepSeek V4.1 Flash 1017
  3. 12Claude Opus 5 vs. GPT-5.6 Terra
  4. 13Claude Opus 5 vs. Grok 4.6
  5. 14Claude Opus 5 vs. GPT-5.6 Luna
  6. 15Claude Haiku 5.5 vs. Claude Opus 5
  7. 16Claude Opus 5 vs. Muse Spark 1.3
  8. 17Claude Opus 5 vs. Mistral Large 4
  9. 18Claude Opus 5 vs. Claude Sonnet 5
  10. 19Claude Fable 5.2 vs. Claude Opus 5
  11. 20Claude Opus 5 vs. GPT-6 Sol
  12. 21Claude Opus 5 vs. Qwen 3.8 Max 0902
  13. 22Gemini 3.7 Flash vs. Qwen 3.8 27B
  14. 23GPT-6 Luna vs. Gemini 3.7 Flash
  15. 24Claude Opus 5 vs. Claude Sonnet 4.5
  16. 25Gemini 3.7 Flash vs. DeepSeek-V4-Flash
  17. 26Claude Haiku 5.5 vs. Gemini 3.7 Flash
  18. 27Gemini 3.7 Flash vs. Kimi K3
  19. 28GPT-5.6 Luna vs. Gemini 3.7 Flash
  20. 29Claude Sonnet 5.5 vs. Gemini 3.7 Flash
  21. 30Claude Sonnet 5 vs. Gemini 3.7 Flash
  22. 31Gemini 3.7 Flash vs. Gemini 3.5 Flash-Lite
  23. 32Gemini 3.7 Flash vs. DeepSeek V4.1 Flash 1017
  24. 33Gemini 3.7 Flash vs. Qwen 3.8 Max 0902
  25. 34GPT-5.6 Terra vs. Gemini 3.7 Flash
  26. 35Claude Opus 5 vs. Kimi K3.1 Pro
  27. 36Claude Sonnet 4.6 vs. Gemini 3.7 Flash
  28. 37Claude Opus 4.6 vs. Gemini 3.7 Flash
  29. 38Claude Opus 5 vs. Gemini 4 Carbon
  30. 39Claude Opus 5 vs. GPT-6.1 Sol
  31. 40Claude Opus 5 vs. Gemini 4 Argon
  32. 41Gemini 4 Carbon vs. Gemini 3.7 Flash
  33. 42GPT-6.1 Sol vs. Gemini 3.7 Flash
  34. 43Claude Opus 5 vs. GPT-6.1 Terra
  35. 44Claude Opus 5 vs. Muse Wonder Full