Enter opens the highlighted result. Esc closes.

Claude Haiku 5.5 vs Gemini 3.7 Flash

Claude Haiku 5.5 leads Gemini 3.7 Flash on coding, 70.7 to 58.0 on the Vibe Coding Index, and Claude Haiku 5.5 costs 7.5x less per output token ($0.50 vs $3.75 per million). Updated October 22, 2026; 53 benchmarks have a result for both.

Replace Claude Haiku 5.5 Replace Gemini 3.7 Flash
Claude Haiku 5.5Anthropic
Coding
70.7
Overall
67.6
Output $/M
$0.50
27
Gemini 3.7 FlashGoogle
Coding
58.0
Overall
65.7
Output $/M
$3.75
26
vs boards won of 53 shared

Claude Haiku 5.5 or Gemini 3.7 Flash: which to pick

Pick Claude Haiku 5.5 for coding: it scores 70.7 on the Vibe Coding Index against 58.0 for Gemini 3.7 Flash, though on 5 benchmarks against 6.

Pick Gemini 3.7 Flash for a larger context window (1.05M against 1M tokens) and work measured by LMArena WebDev or IOI (Vals AI), where it leads.

Model AClaude Haiku 5.5Anthropic70.7/1005 independent benchmarksNo cost per solved taskModel BGemini 3.7 FlashGoogle58.0/1006 independent benchmarks$1.78 per solved task
Shared results
53
Claude Haiku 5.5 only
10
Gemini 3.7 Flash only
61
Like-for-like categories
8 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
Claude Haiku 5.5 70.7 from 5 benchmarks, Gemini 3.7 Flash 58.0 from 6 benchmarks.
Widest category
Knowledge, 23.6 points apart on average over 2 shared benchmarks.
Widest single gap
SimpleQA Verified: Claude Haiku 5.5 23.8% against Gemini 3.7 Flash 69.2%, 45.4 points apart on a 0 to 100 scale.
Output price
Claude Haiku 5.5 $0.50 against Gemini 3.7 Flash $3.75 per million output tokens, 7.5x apart.
Context window
Claude Haiku 5.5 takes 1M tokens, Gemini 3.7 Flash 1.05M.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryClaude Haiku 5.5BarsGemini 3.7 FlashTies
Coding95
Intelligence20
Agentic work73
Reasoning07
Math40
Knowledge02
Web design25
General34
All shared boards2726
CodingLike-for-likeSix of these boards feed the Vibe Coding Index95
Coding benchmarks for Claude Haiku 5.5 and Gemini 3.7 Flash
BenchmarkClaude Haiku 5.5Gemini 3.7 FlashLeader
LiveBench coding91.4%80.5%Claude Haiku 5.5
LMArena WebDev15861591Gemini 3.7 Flash
AA Coding IndexNot measured71.5Only Gemini 3.7 Flash measured
LiveCodeBench (Vals AI)Not measured88.7%Only Gemini 3.7 Flash measured
SWE-bench Verified (Vals AI)Not measured80.8%Only Gemini 3.7 Flash measured
Terminal-Bench 4 (Vals AI)36.4%12.1%Claude Haiku 5.5
Vibe Code Bench (Vals AI)90.4%70.4%Claude Haiku 5.5
Code migration (Vals AI)44.6%34.8%Claude Haiku 5.5
ProgramBench (Vals AI)2.5%0.0%Claude Haiku 5.5
IOI (Vals AI)47.3%67.8%Gemini 3.7 Flash
Terminal-Bench 2.1 (Vals AI)Not measured77.5%Only Gemini 3.7 Flash measured
SWE-bench Multimodal (Vals AI)44.0%Not measuredOnly Claude Haiku 5.5 measured
Vibe Code Bench 1-100 (Vals AI)20.4%Not measuredOnly Claude Haiku 5.5 measured
SkillsBench (Vals AI)Not measured65.9%Only Gemini 3.7 Flash measured
CyberBench (Vals AI)75.5%43.8%Claude Haiku 5.5
SciCode55.0%59.8%Gemini 3.7 Flash
FrontierCode46.4%43.6%Claude Haiku 5.5
FrontierSWE43.8%20.3%Claude Haiku 5.5
ALE-BenchNot measured904.3Only Gemini 3.7 Flash measured
LMArena Text: codingNot measured1499Only Gemini 3.7 Flash measured
LMArena Text: software and ITNot measured1498Only Gemini 3.7 Flash measured
LMArena WebDev: React16051587Claude Haiku 5.5
LMArena WebDev: HTML15691593Gemini 3.7 Flash
LMArena WebDev: from an imageNot measured1599Only Gemini 3.7 Flash measured
SciCode9.2%13.8%Gemini 3.7 Flash
Neither model has a result on the other 14 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Haiku 5.5 and Gemini 3.7 Flash
BenchmarkClaude Haiku 5.5Gemini 3.7 FlashLeader
AA Intelligence Index43.439.6Claude Haiku 5.5
Epoch Capabilities Index159.3158.0Claude Haiku 5.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index73
Agentic work benchmarks for Claude Haiku 5.5 and Gemini 3.7 Flash
BenchmarkClaude Haiku 5.5Gemini 3.7 FlashLeader
Design Arena: agents building web appsNot measured1223Only Gemini 3.7 Flash measured
Design Arena: agents building full-stack appsNot measured1208Only Gemini 3.7 Flash measured
Design Arena: agents building mobile appsNot measured1230Only Gemini 3.7 Flash measured
Design Arena: agents building Android appsNot measured1243Only Gemini 3.7 Flash measured
Design Arena: agents building Godot gamesNot measured1264Only Gemini 3.7 Flash measured
Design Arena: agents building gamesNot measured1235Only Gemini 3.7 Flash measured
Design Arena: spreadsheetsNot measured1091Only Gemini 3.7 Flash measured
LiveBench research81.9%76.5%Claude Haiku 5.5
LiveBench browser80.0%56.0%Claude Haiku 5.5
LiveBench long agentic57.6%28.3%Claude Haiku 5.5
SREBench (Vals AI)5.7%4.6%Claude Haiku 5.5
Finance Agent (Vals AI)54.1%59.0%Gemini 3.7 Flash
Tax Agent Bench (Vals AI)31.9%22.8%Claude Haiku 5.5
Legal Research Bench (Vals AI)43.3%34.6%Claude Haiku 5.5
Harvey's Legal Agent Benchmark (Vals AI)4.2%Not measuredOnly Claude Haiku 5.5 measured
Excel Modeling Benchmark (Vals AI)59.0%71.3%Gemini 3.7 Flash
BioMysteryBench (Vals AI)70.4%Not measuredOnly Claude Haiku 5.5 measured
Terminal-Bench-Science (Vals AI)10.0%7.1%Claude Haiku 5.5
Vals Science Index38.5%Not measuredOnly Claude Haiku 5.5 measured
APEX-Agents56.1%67.8%Gemini 3.7 Flash
Remote Labor IndexNot measured5.0%Only Gemini 3.7 Flash measured
Vending-Bench 2$3,602Not measuredOnly Claude Haiku 5.5 measured
Neither model has a result on the other 19 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index07
Reasoning benchmarks for Claude Haiku 5.5 and Gemini 3.7 Flash
BenchmarkClaude Haiku 5.5Gemini 3.7 FlashLeader
GPQA DiamondNot measured93.9%Only Gemini 3.7 Flash measured
LiveBench reasoning82.4%87.8%Gemini 3.7 Flash
MysteryMechanism (Vals AI)35.1%Not measuredOnly Claude Haiku 5.5 measured
MMMU Pro (Vals AI)Not measured89.0%Only Gemini 3.7 Flash measured
GPQA Diamond (Artificial Analysis run)Not measured94.5%Only Gemini 3.7 Flash measured
Humanity's Last Exam (Artificial Analysis run)44.4%47.9%Gemini 3.7 Flash
GPQA Diamond (Epoch AI run)89.6%94.8%Gemini 3.7 Flash
ARC-AGI89.0%95.5%Gemini 3.7 Flash
ARC-AGI-261.3%84.6%Gemini 3.7 Flash
Chess puzzles55.0%66.0%Gemini 3.7 Flash
Mystery game puzzles30.0%37.0%Gemini 3.7 Flash
EBR-bench43.8%Not measuredOnly Claude Haiku 5.5 measured
LMArena Text: hard promptsNot measured1495Only Gemini 3.7 Flash measured
LMArena Text: expertNot measured1512Only Gemini 3.7 Flash measured
LMArena Text: hard prompts in EnglishNot measured1487Only Gemini 3.7 Flash measured
LMArena Vision: diagramsNot measured1329Only Gemini 3.7 Flash measured
LMArena Vision: homeworkNot measured1320Only Gemini 3.7 Flash measured
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index40
Math benchmarks for Claude Haiku 5.5 and Gemini 3.7 Flash
BenchmarkClaude Haiku 5.5Gemini 3.7 FlashLeader
OTIS Mock AIME98.9%97.2%Claude Haiku 5.5
FrontierMath, tiers 1 to 375.1%71.6%Claude Haiku 5.5
FrontierMath, tier 446.3%36.6%Claude Haiku 5.5
ProofBench89.0%58.0%Claude Haiku 5.5
LMArena Text: mathNot measured1511Only Gemini 3.7 Flash measured
LMArena Text: mathematical workNot measured1502Only Gemini 3.7 Flash measured
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index02
Knowledge benchmarks for Claude Haiku 5.5 and Gemini 3.7 Flash
BenchmarkClaude Haiku 5.5Gemini 3.7 FlashLeader
MMLU ProNot measured90.1%Only Gemini 3.7 Flash measured
LegalBench (Vals AI)Not measured87.3%Only Gemini 3.7 Flash measured
TaxEval (Vals AI)Not measured74.7%Only Gemini 3.7 Flash measured
MortgageTax (Vals AI)Not measured66.7%Only Gemini 3.7 Flash measured
MedCode (Vals AI)51.5%53.4%Gemini 3.7 Flash
SimpleQA Verified23.8%69.2%Gemini 3.7 Flash
LMArena Text: scienceNot measured1511Only Gemini 3.7 Flash measured
LMArena Text: medicine and healthcareNot measured1494Only Gemini 3.7 Flash measured
LMArena Text: legal and governmentNot measured1496Only Gemini 3.7 Flash measured
LMArena Text: business and financeNot measured1479Only Gemini 3.7 Flash measured
FACTS Benchmark SuiteNot measured71.2%Only Gemini 3.7 Flash measured
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index25
Web design benchmarks for Claude Haiku 5.5 and Gemini 3.7 Flash
BenchmarkClaude Haiku 5.5Gemini 3.7 FlashLeader
Design Arena: websites12621303Gemini 3.7 Flash
Design Arena: UI components12831295Gemini 3.7 Flash
Design Arena: game dev13151318Gemini 3.7 Flash
Design Arena: data viz12941315Gemini 3.7 Flash
Design Arena: 3D13421307Claude Haiku 5.5
Design Arena: all code categories12771307Gemini 3.7 Flash
Design Arena: SVGNot measured1283Only Gemini 3.7 Flash measured
Design Arena: ASCII artNot measured1278Only Gemini 3.7 Flash measured
LiveBench design83.1%73.2%Claude Haiku 5.5
GeneralLike-for-likePublic boards, shown as published, kept out of the index34
General benchmarks for Claude Haiku 5.5 and Gemini 3.7 Flash
BenchmarkClaude Haiku 5.5Gemini 3.7 FlashLeader
Vals Index58.7%Not measuredOnly Claude Haiku 5.5 measured
LiveBench data analysis53.1%68.0%Gemini 3.7 Flash
Public Benefits Bench (Vals AI)63.2%Not measuredOnly Claude Haiku 5.5 measured
SAGE (Vals AI)45.8%49.2%Gemini 3.7 Flash
MedScribe (Vals AI)89.5%83.9%Claude Haiku 5.5
Long context reasoning (AA-LCR)82.7%83.0%Gemini 3.7 Flash
DTBench95.0%96.8%Gemini 3.7 Flash
LMCA51.1%50.4%Claude Haiku 5.5
Furniture assembly47.5%26.7%Claude Haiku 5.5
LMArena TextNot measured1489Only Gemini 3.7 Flash measured
LMArena Text: instruction followingNot measured1484Only Gemini 3.7 Flash measured
LMArena Text: creative writingNot measured1488Only Gemini 3.7 Flash measured
LMArena VisionNot measured1314Only Gemini 3.7 Flash measured
LMArena Text: EnglishNot measured1483Only Gemini 3.7 Flash measured
LMArena Text: non-EnglishNot measured1487Only Gemini 3.7 Flash measured
LMArena Text: ChineseNot measured1552Only Gemini 3.7 Flash measured
LMArena Text: GermanNot measured1506Only Gemini 3.7 Flash measured
LMArena Text: JapaneseNot measured1511Only Gemini 3.7 Flash measured
LMArena Text: KoreanNot measured1481Only Gemini 3.7 Flash measured
LMArena Text: FrenchNot measured1500Only Gemini 3.7 Flash measured
LMArena Text: SpanishNot measured1495Only Gemini 3.7 Flash measured
LMArena Text: RussianNot measured1515Only Gemini 3.7 Flash measured
LMArena Text: PolishNot measured1503Only Gemini 3.7 Flash measured
LMArena Text: multi-turnNot measured1485Only Gemini 3.7 Flash measured
LMArena Text: longer queriesNot measured1492Only Gemini 3.7 Flash measured
LMArena Text: writing and languageNot measured1491Only Gemini 3.7 Flash measured
LMArena Text: entertainment and mediaNot measured1477Only Gemini 3.7 Flash measured
LMArena Vision: EnglishNot measured1309Only Gemini 3.7 Flash measured
LMArena Vision: ChineseNot measured1394Only Gemini 3.7 Flash measured
LMArena Vision: reading textNot measured1322Only Gemini 3.7 Flash measured
LMArena Vision: humorNot measured1299Only Gemini 3.7 Flash measured
LMArena Vision: creative writingNot measured1312Only Gemini 3.7 Flash measured
Neither model has a result on the other 14 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Haiku 5.5 and Gemini 3.7 Flash
BenchmarkClaude Haiku 5.5Gemini 3.7 FlashLeader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

Claude Haiku 5.5$0.0003Fits in one request
Gemini 3.7 Flash$0.0026Fits in one request

Claude Haiku 5.5 costs less

Repository review

50K input + 3K output tokens

Claude Haiku 5.5$0.0065Fits in one request
Gemini 3.7 Flash$0.049Fits in one request

Claude Haiku 5.5 costs less

Agent loop

200K input + 10K output tokens

Claude Haiku 5.5$0.025Fits in one request
Gemini 3.7 Flash$0.188Fits in one request

Claude Haiku 5.5 costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of Claude Haiku 5.5 and Gemini 3.7 Flash
SpecificationAnthropic Claude Haiku 5.5Google Gemini 3.7 Flash
MakerAnthropicGoogle
WeightsNo public weights listedNo public weights listed
ReleasedOctober 7, 2026August 13, 2026
Context window1M1.05M
Input $/Mtok$0.10$0.75
Output $/Mtok$0.50$3.75
Coding index70.758.0
Independent measurements behind it56
Cost per solved taskNot computable$1.78
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Haiku 5.5 better than Gemini 3.7 Flash for coding?

Pick Claude Haiku 5.5 for coding: it scores 70.7 on the Vibe Coding Index against 58.0 for Gemini 3.7 Flash, though on 5 benchmarks against 6. Pick Gemini 3.7 Flash for a larger context window (1.05M against 1M tokens) and work measured by LMArena WebDev or IOI (Vals AI), where it leads.

Which is cheaper, Claude Haiku 5.5 or Gemini 3.7 Flash?

Claude Haiku 5.5 costs $0.10 per million input tokens and $0.50 per million output tokens; Gemini 3.7 Flash costs $0.75 and $3.75. Cost per solved task is known for Gemini 3.7 Flash only.

Which has the bigger context window, Claude Haiku 5.5 or Gemini 3.7 Flash?

Gemini 3.7 Flash, with 1.05M tokens against 1M.

How many benchmarks is the Claude Haiku 5.5 vs Gemini 3.7 Flash comparison based on?

53 benchmarks have a result for both models as of October 22, 2026. Claude Haiku 5.5's coding index rests on 5 independent benchmarks and Gemini 3.7 Flash's on 6. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/claude-haiku-5-5-vs-gemini-3-7-flash" title="Claude Haiku 5.5 vs Gemini 3.7 Flash, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/claude-haiku-5-5-vs-gemini-3-7-flash">LLMBenchmark.ai, Claude Haiku 5.5 vs Gemini 3.7 Flash</a></p>