Gemini 3.7 Flash vs GPT-5.5

Updated September 27, 2026. Rank says GPT-5.5 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Decision reading

GPT-5.5 has the higher public score estimate, 69.13 versus 67.66, but the 90% score intervals overlap. Treat that as a lead, not a settled winner. 10 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A

Gemini 3.7 Flash

Google

67.66/100

Supported · Public rank #19

90% interval 63.0–72.3

Model B

GPT-5.5

OpenAI

69.13/100

Supported · Public rank #16

90% interval 63.4–74.8

Shared results: 10
Gemini 3.7 Flash only: 15
GPT-5.5 only: 29
Like-for-like categories: 3 / 8

Supported: Gemini 3.7 Flash and GPT-5.5How 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.

Coding work
Code generation, repair, and software-engineering tasks
GPT-5.5
GPT-5.5 leads on the public coding lane, 64.1 to 60.3, with Supported evidence for both models, although the 90% intervals overlap.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
GPT-5.5
GPT-5.5 leads on the public agentic lane, 60.1 to 58.6, with Supported evidence for both models, although the 90% intervals overlap.
Confidence: limited
Chat 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-rates
Repository 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-rates
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.

Pick the job you would use them for

The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.

60.3Gemini 3.7 Flash64.1GPT-5.5

Like-for-like · BenchAlign v5.7

GPT-5.5 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.

Open the coding leaderboard Shortlist models for this job

Same basis rules as the category table below

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 34.9
Gemini 3.7 Flash:47.9%
GPT-5.5:13.0%
Gemini 3.7 Flash source GPT-5.5 source
LiveCodeBench (Vals)Coding
Normalized gap 3.4
Gemini 3.7 Flash:88.7%
GPT-5.5:85.3%
Gemini 3.7 Flash source GPT-5.5 source
MMLU-Pro (Vals)Knowledge
Normalized gap 2.0
Gemini 3.7 Flash:90.1%
GPT-5.5:88.1%
Gemini 3.7 Flash source GPT-5.5 source
ARC-AGI-2Reasoning
Normalized gap 0.4
Gemini 3.7 Flash:84.6%
GPT-5.5:85%
Gemini 3.7 Flash source GPT-5.5 source

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

Gemini 3.7 Flash: 58.6; Supported · #20/105
GPT-5.5: 60.1; Supported · #15/105
Basis: BenchAlign v5.7 lane · 7 vs 14 public rows
Reading: GPT-5.5 leads · intervals overlap

Coding

Like-for-like

Gemini 3.7 Flash: 60.3; Supported · #17/135
GPT-5.5: 64.1; Supported · #11/135
Basis: BenchAlign v5.7 lane · 6 vs 9 public rows
Reading: GPT-5.5 leads · intervals overlap

Knowledge

Like-for-like

Gemini 3.7 Flash: 71.1; Supported · #10/158
GPT-5.5: 70.0; Supported · #12/158
Basis: BenchAlign v5.7 lane · 6 vs 6 public rows
Reading: Gemini 3.7 Flash leads · intervals overlap

Multimodal

Directional only

Gemini 3.7 Flash: 82.6; #10/50
GPT-5.5: 71.4; #20/50
Basis: Provisional lane · 1 vs 2 weighted rows
Reading: Directional only

Reasoning

Not comparable

Gemini 3.7 Flash: 77.8; Unranked · 5 rankable rows
GPT-5.5: 65.9; #10/19
Basis: Provisional lane · 1 vs 2 weighted rows
Reading: Not comparable

Multilingual

Not comparable

Gemini 3.7 Flash: Not ranked
GPT-5.5: Not ranked
Basis: Provisional lane · 0 vs 0 weighted rows
Reading: Not comparable

Instruction following

Not comparable

Gemini 3.7 Flash: Not ranked
GPT-5.5: 91.9; #7/124
Basis: Provisional lane · 0 vs 0 weighted rows
Reading: Not comparable

Math

Not comparable

Gemini 3.7 Flash: Not ranked
GPT-5.5: 69.4; Unranked · 3 rankable rows
Basis: Provisional lane · 0 vs 2 weighted rows
Reading: Not comparable

Category scores with the server-provided evidence basis for Gemini 3.7 Flash and GPT-5.5
Category	Gemini 3.7 Flash	GPT-5.5	Basis	Reading
Agentic	58.6Supported · #20/105	60.1Supported · #15/105	Like-for-likeBenchAlign v5.7 lane · 7 vs 14 public rows	GPT-5.5 leads · intervals overlap
Coding	60.3Supported · #17/135	64.1Supported · #11/135	Like-for-likeBenchAlign v5.7 lane · 6 vs 9 public rows	GPT-5.5 leads · intervals overlap
Knowledge	71.1Supported · #10/158	70.0Supported · #12/158	Like-for-likeBenchAlign v5.7 lane · 6 vs 6 public rows	Gemini 3.7 Flash leads · intervals overlap
Multimodal	82.6#10/50	71.4#20/50	Directional onlyProvisional lane · 1 vs 2 weighted rows	Directional only
Reasoning	77.8Unranked · 5 rankable rows	65.9#10/19	Not comparableProvisional lane · 1 vs 2 weighted rows	Not comparable
Multilingual	Not ranked	Not ranked	Not comparableProvisional lane · 0 vs 0 weighted rows	Not comparable
Instruction following	Not ranked	91.9#7/124	Not comparableProvisional lane · 0 vs 0 weighted rows	Not comparable
Math	Not ranked	69.4Unranked · 3 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 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

Gemini 3.7 Flash: $0.00262; Fits in one request
GPT-5.5: $0.02; 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

Gemini 3.7 Flash: $0.04875; Fits in one request
GPT-5.5: $0.34; 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

Gemini 3.7 Flash: $0.0675; Fits in one request
GPT-5.5: $0.5; 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.

SpecificationGemini 3.7 FlashGPT-5.5

Context window

Maximum documented context; output-token limits may be lower.

Gemini 3.7 Flash

Google Gemini 3.7 Flash API documentation

GPT-5.5

OpenAI pricing

API model ID

Gemini 3.7 Flash

gemini-3.7-flash

Google Gemini 3.7 Flash API documentation

GPT-5.5

gpt-5.5

OpenAI pricing

Cached-input rate

A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.

Gemini 3.7 Flash

$0.075 per 1M cached input tokens

Google Gemini API pricing

GPT-5.5

$0.5 per 1M cached input tokens

OpenAI pricing

Documented inputs

Gemini 3.7 Flash

text, image, video, audio, pdf

Google Gemini 3.7 Flash API documentation

GPT-5.5

Not sourced

Documented outputs

Gemini 3.7 Flash

text

Google Gemini 3.7 Flash API documentation

GPT-5.5

Not sourced

Provider availability

Gemini 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 card

GPT-5.5

Not sourced

Reasoning profile

Gemini 3.7 Flash

Reasoning

GPT-5.5

Reasoning

Weight access

Gemini 3.7 Flash

Proprietary

GPT-5.5

Proprietary

License

Gemini 3.7 Flash

Proprietary

GPT-5.5

Proprietary

Release date

Gemini 3.7 Flash

2026-08-13

GPT-5.5

2026-04-23

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: GPT-5.5 has the higher public score estimate, 69.13 versus 67.66, but the 90% score intervals overlap.
Workload cost: Repository review: $0.04875 vs $0.34. Cache-heavy agent loop: $0.0675 vs $0.5.
Context tradeoff: Both models list 1M.

Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, Gemini 3.7 Flash or GPT-5.5?

GPT-5.5 has the higher public score estimate, 69.13 versus 67.66, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.

Which is better for coding, Gemini 3.7 Flash or GPT-5.5?

GPT-5.5 leads the public coding lane, 64.1 to 60.3, with Supported evidence for both models, although the 90% intervals overlap.

Which is better for agentic tasks, Gemini 3.7 Flash or GPT-5.5?

GPT-5.5 leads the public agentic tasks lane, 60.1 to 58.6, with Supported evidence for both models, although the 90% intervals overlap.

Which costs less, Gemini 3.7 Flash or GPT-5.5?

For the stated presets, chat costs $0.00263 on Gemini 3.7 Flash and $0.02 on GPT-5.5; repository review costs $0.04875 and $0.34; the cache-heavy agent loop costs $0.0675 and $0.5. Costs use the listed standard API rates.

Which has the larger context window, Gemini 3.7 Flash or GPT-5.5?

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 evidence54 rows

Agentic

Terminal-Bench 2.1
Gemini 3.7 Flash85.8%
Source
GPT-5.5—
Not directly comparable
Terminal-Bench 3.0
Gemini 3.7 Flash14.9%
Source
GPT-5.5—
Not directly comparable
AutomationBench
Gemini 3.7 Flash30.4%
Source
GPT-5.5—
Not directly comparable
OSWorld 2.0
Gemini 3.7 Flash47.9%
Source
GPT-5.513.0%
Source
Gemini 3.7 Flash leads this result
Agents' Last Exam
Gemini 3.7 Flash26.3%
Source
GPT-5.5—
Not directly comparable
Terminal-Bench 2.1 (Vals)
Gemini 3.7 Flash77.5%
Source
GPT-5.576.4%
Source
Gemini 3.7 Flash leads this result
ApprenticeBench
Shared source
Gemini 3.7 Flash16%
GPT-5.520%
GPT-5.5 leads this result
Terminal-Bench 2.0
Gemini 3.7 Flash—
GPT-5.582%
Source
Not directly comparable
CyberGym
Gemini 3.7 Flash—
GPT-5.581.8%
Source
Not directly comparable
BrowseComp
Gemini 3.7 Flash—
GPT-5.584.4%
Source
Not directly comparable
OSWorld-Verified
Gemini 3.7 Flash—
GPT-5.578.7%
Source
Not directly comparable
MCP Atlas
Gemini 3.7 Flash—
GPT-5.575.3%
Source
Not directly comparable
Toolathlon
Gemini 3.7 Flash—
GPT-5.555.6%
Source
Not directly comparable
τ²-bench results
Gemini 3.7 Flash—
GPT-5.598%
Source
Not directly comparable
Gert Labs
Gemini 3.7 Flash—
GPT-5.572.93%
Source
Not directly comparable
ResearchClawBench
Gemini 3.7 Flash—
GPT-5.517.0%
Source
Not directly comparable
JobBench
Gemini 3.7 Flash—
GPT-5.542.7%
Source
Not directly comparable
ExploitGym
Gemini 3.7 Flash—
GPT-5.513.4%
Source
Not directly comparable

Coding

FrontierCode 1.1 Main
Gemini 3.7 Flash43.6%
Source
GPT-5.543.0%
Source
Gemini 3.7 Flash leads this result
DeepSWE
Gemini 3.7 Flash65.3%
Source
GPT-5.5—
Not directly comparable
Terminal-Bench 2.1
Gemini 3.7 Flash85.8%
Source
GPT-5.5—
Not directly comparable
FrontierSWE v2
Gemini 3.7 Flash20.3%
Source
GPT-5.5—
Not directly comparable
LiveCodeBench (Vals)
Gemini 3.7 Flash88.7%
Source
GPT-5.585.3%
Source
Gemini 3.7 Flash leads this result
SWE-bench (Vals)
Gemini 3.7 Flash80.8%
Source
GPT-5.582.6%
Source
GPT-5.5 leads this result
SWE-bench Pro
Gemini 3.7 Flash—
GPT-5.558.6%
Source
Not directly comparable
Terminal-Bench 2.0
Gemini 3.7 Flash—
GPT-5.582.0%
Source
Not directly comparable
Vibe Code Bench
Gemini 3.7 Flash—
GPT-5.569.85%
Source
Not directly comparable
React Native Evals
Gemini 3.7 Flash—
GPT-5.584.7%
Source
Not directly comparable
cursorBench31
Gemini 3.7 Flash—
GPT-5.559.2%
Source
Not directly comparable
cursorBench32
Gemini 3.7 Flash—
GPT-5.558.4%
Source
Not directly comparable

Reasoning

MRCR v2 64K-128K
Gemini 3.7 Flash97%
Source
GPT-5.583.1%
Source
Gemini 3.7 Flash leads this result
ARC-AGI-1
Gemini 3.7 Flash95.50%
Source
GPT-5.5—
Not directly comparable
ARC-AGI-2
Gemini 3.7 Flash84.6%
Source
GPT-5.585%
Source
GPT-5.5 leads this result
MRCR v2 128K-256K
Gemini 3.7 Flash—
GPT-5.587.5%
Source
Not directly comparable
ARC-AGI-3
Gemini 3.7 Flash—
GPT-5.50.4%
Source
Not directly comparable

Multimodal

CharXiv w/o tools
Gemini 3.7 Flash84.5%
Source
GPT-5.5—
Not directly comparable
CharXiv
Gemini 3.7 Flash88.7%
Source
GPT-5.5—
Not directly comparable
LVBench
Gemini 3.7 Flash85.4%
Source
GPT-5.5—
Not directly comparable
MMMU-Pro
Gemini 3.7 Flash—
GPT-5.581.2%
Source
Not directly comparable
MMMU-Pro w/ Python
Gemini 3.7 Flash—
GPT-5.583.2%
Source
Not directly comparable
OfficeQA Pro
Gemini 3.7 Flash—
GPT-5.554.1%
Source
Not directly comparable

Knowledge

HLE-Verified
Gemini 3.7 Flash53.6%
Source
GPT-5.5—
Not directly comparable
LABBench2
Gemini 3.7 Flash82.1%
Source
GPT-5.5—
Not directly comparable
BioMysteryBench (human-solvable)
Gemini 3.7 Flash87.1%
Source
GPT-5.5—
Not directly comparable
BioMysteryBench (human-difficult)
Gemini 3.7 Flash43.5%
Source
GPT-5.5—
Not directly comparable
GPQA Diamond (Vals)
Gemini 3.7 Flash93.9%
Source
GPT-5.593.2%
Source
Gemini 3.7 Flash leads this result
MMLU-Pro (Vals)
Gemini 3.7 Flash90.1%
Source
GPT-5.588.1%
Source
Gemini 3.7 Flash leads this result
GPQA
Gemini 3.7 Flash—
GPT-5.593.6%
Source
Not directly comparable
GPQA-D
Gemini 3.7 Flash—
GPT-5.593.6%
Source
Not directly comparable
HLE
Gemini 3.7 Flash—
GPT-5.552.2%
Source
Not directly comparable
HLE w/o tools
Gemini 3.7 Flash—
GPT-5.541.4%
Source
Not directly comparable

Math

FrontierMath (legacy)
Gemini 3.7 Flash—
GPT-5.551.7%
Source
Not directly comparable
FrontierMath v2 (Tiers 1-3)
Gemini 3.7 Flash—
GPT-5.551.700%
Source
Not directly comparable
FrontierMath v2 (Tier 4)
Gemini 3.7 Flash—
GPT-5.535.400%
Source
Not directly comparable

54 public results · 10 shared

Related comparisons

Compare API pricing Read the methodology Open the model selector

Watch Gemini 3.7 Flash vs GPT-5.5

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 2,000+ readers.

Last updated September 27, 2026

Gemini 3.7 Flash vs GPT-5.5

Decision reading

Which one for your work

Coding work

Agentic work

Chat turn cost

Cache-heavy agent loop cost

Repository review cost

Long documents

Which one for a specific job

What is actually comparable

Shape of the matched evidence

Category results, on a stated basis

Agentic

Coding

Knowledge

Multimodal

Reasoning

Multilingual

Instruction following

Math

What each workload costs

Chat turn

Repository review

Cache-heavy agent loop

Specification differences

Context window

API model ID

Cached-input rate

Documented inputs

Documented outputs

Provider availability

Reasoning profile

Weight access

License

Release date

If you already use one of these models

Questions

Which is better, Gemini 3.7 Flash or GPT-5.5?

Which is better for coding, Gemini 3.7 Flash or GPT-5.5?

Which is better for agentic tasks, Gemini 3.7 Flash or GPT-5.5?

Which costs less, Gemini 3.7 Flash or GPT-5.5?

Which has the larger context window, Gemini 3.7 Flash or GPT-5.5?

Benchmark evidence

Agentic

Coding

Reasoning

Multimodal

Knowledge

Math

Related comparisons

Watch Gemini 3.7 Flash vs GPT-5.5