Coding
Like-for-like- Gemini 3.5 Flash
- 57.7
- Supported · #34/183
- Gemini 3.5 Flash-Lite
- 43.6
- Supported · #121/183
- Basis
- BenchAlign lane · 7 vs 4 public rows
- Reading
- Gemini 3.5 Flash leads · intervals overlap
Gemini 3.5 Flash vs Gemini 3.5 Flash-Lite
Updated September 4, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
Gemini 3.5 Flash has the higher public score estimate, 70.01 versus 60.5, 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.
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.
Coding work
Code generation, repair, and software-engineering tasks
Gemini 3.5 Flash
Gemini 3.5 Flash leads on the public coding lane, 57.7 to 43.6, with Supported evidence for both models, although the 90% intervals overlap.
Confidence: limited
Chat turn cost
1K fresh input + 500 output tokens
Gemini 3.5 Flash-Lite
Gemini 3.5 Flash-Lite has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Gemini 3.5 Flash-Lite
Gemini 3.5 Flash-Lite 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
Repository review cost
50K fresh input + 3K output tokens
Gemini 3.5 Flash-Lite
Gemini 3.5 Flash-Lite has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Gemini 3.5 Flash-Lite is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
Confidence: limited
Long documents
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
Confidence: documented
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
17 Gemini 3.5 Flash only
10 Shared
- Shared results
- 10
- Gemini 3.5 Flash only
- 17
- Gemini 3.5 Flash-Lite only
- 0
- Like-for-like categories
- 2 / 8
2 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
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.
Knowledge
Like-for-like- Gemini 3.5 Flash
- 68.5
- Supported · #19/181
- Gemini 3.5 Flash-Lite
- 53.0
- Supported · #71/181
- Basis
- BenchAlign lane · 4 vs 2 public rows
- Reading
- Gemini 3.5 Flash leads · intervals overlap
Agentic
Directional only- Gemini 3.5 Flash
- 50.6
- Supported · #61/151
- Gemini 3.5 Flash-Lite
- 43.4
- Estimated · #104/151
- Basis
- BenchAlign lane · 8 vs 3 public rows
- Reading
- Directional only
Multimodal
Directional only- Gemini 3.5 Flash
- 85.9
- #6/48
- Gemini 3.5 Flash-Lite
- 76.1
- #16/48
- Basis
- Provisional lane · 2 vs 0 weighted rows
- Reading
- Directional only
Reasoning
Not comparable- Gemini 3.5 Flash
- 60.3
- #17/22
- Gemini 3.5 Flash-Lite
- 60.8
- Unranked · 3 rankable rows
- Basis
- Provisional lane · 2 vs 1 weighted rows
- Reading
- Not comparable
Math
Not comparable- Gemini 3.5 Flash
- 55.2
- Unranked · 2 rankable rows
- Gemini 3.5 Flash-Lite
- Not ranked
- Basis
- Provisional lane · 2 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Gemini 3.5 Flash
- Not ranked
- Gemini 3.5 Flash-Lite
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Gemini 3.5 Flash
- 86.9
- #34/120
- Gemini 3.5 Flash-Lite
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | Gemini 3.5 Flash | Gemini 3.5 Flash-Lite | Basis | Reading |
|---|---|---|---|---|
| Coding | 57.7Supported · #34/183 | 43.6Supported · #121/183 | Like-for-likeBenchAlign lane · 7 vs 4 public rows | Gemini 3.5 Flash leads · intervals overlap |
| Knowledge | 68.5Supported · #19/181 | 53.0Supported · #71/181 | Like-for-likeBenchAlign lane · 4 vs 2 public rows | Gemini 3.5 Flash leads · intervals overlap |
| Agentic | 50.6Supported · #61/151 | 43.4Estimated · #104/151 | Directional onlyBenchAlign lane · 8 vs 3 public rows | Directional only |
| Multimodal | 85.9#6/48 | 76.1#16/48 | Directional onlyProvisional lane · 2 vs 0 weighted rows | Directional only |
| Reasoning | 60.3#17/22 | 60.8Unranked · 3 rankable rows | Not comparableProvisional lane · 2 vs 1 weighted rows | Not comparable |
| Math | 55.2Unranked · 2 rankable rows | Not ranked | Not comparableProvisional lane · 2 vs 0 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | 86.9#34/120 | 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.
Terminal-Bench 2.0
Agentic
Gemini 3.5 Flash: 76.2%Gemini 3.5 Flash-Lite: 54%Normalized gap 22.2Gemini 3.5 Flash source Gemini 3.5 Flash-Lite sourceLiveCodeBench (Vals)
Coding
Gemini 3.5 Flash: 87.6%Gemini 3.5 Flash-Lite: 79.0%Normalized gap 8.6Gemini 3.5 Flash source Gemini 3.5 Flash-Lite sourceMRCRv2
Reasoning
Gemini 3.5 Flash: 77.3%Gemini 3.5 Flash-Lite: 72.2%Normalized gap 5.1Gemini 3.5 Flash source Gemini 3.5 Flash-Lite sourceOSWorld-Verified
Agentic
Gemini 3.5 Flash: 78.4%Gemini 3.5 Flash-Lite: 74%Normalized gap 4.4Gemini 3.5 Flash source Gemini 3.5 Flash-Lite sourceMMLU-Pro (Vals)
Knowledge
Gemini 3.5 Flash: 89.5%Gemini 3.5 Flash-Lite: 85.8%Normalized gap 3.7Gemini 3.5 Flash source Gemini 3.5 Flash-Lite 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
- Gemini 3.5 Flash
- $0.006
- Fits in one request
- Gemini 3.5 Flash-Lite
- $0.00155
- Fits in one request
Gemini 3.5 Flash-Lite has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Gemini 3.5 Flash
- $0.102
- Fits in one request
- Gemini 3.5 Flash-Lite
- $0.0225
- Fits in one request
Gemini 3.5 Flash-Lite 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 3.5 Flash
- $0.15
- Fits in one request
- Gemini 3.5 Flash-Lite
- $0.037
- Fits in one request
Gemini 3.5 Flash-Lite has the lower modeled cost
Costs use the listed standard API rates.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationGemini 3.5 FlashGemini 3.5 Flash-Lite
Context window
Maximum documented context; output-token limits may be lower.
Gemini 3.5 Flash
Gemini 3.5 Flash-Lite
API model ID
Gemini 3.5 Flash
gemini-3.5-flash
Google Gemini API pricingGemini 3.5 Flash-Lite
gemini-3.5-flash-lite
Google Gemini 3.5 Flash-Lite model documentationCached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Gemini 3.5 Flash
$0.15 per 1M cached input tokens
Google Gemini API pricingGemini 3.5 Flash-Lite
$0.03 per 1M cached input tokens
Google Gemini API pricingDocumented inputs
Gemini 3.5 Flash
Not sourced
Gemini 3.5 Flash-Lite
text, image, video, audio, pdf
Google Gemini 3.5 Flash-Lite model documentationDocumented outputs
Gemini 3.5 Flash
Not sourced
Gemini 3.5 Flash-Lite
Provider availability
Gemini 3.5 Flash
Not sourced
Gemini 3.5 Flash-Lite
Generally Available · Gemini API, Google AI Studio
Google latest Gemini model guideReasoning profile
Gemini 3.5 Flash
Reasoning
Gemini 3.5 Flash-Lite
Reasoning
Weight access
Gemini 3.5 Flash
Proprietary
Gemini 3.5 Flash-Lite
Proprietary
License
Gemini 3.5 Flash
Proprietary
Gemini 3.5 Flash-Lite
Proprietary
Release date
Gemini 3.5 Flash
2026-05-19
Gemini 3.5 Flash-Lite
2026-07-21
If you already use one of these models
- Deployment change
- Both entries list Google as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
- Quality signal
- Gemini 3.5 Flash has the higher public score estimate, 70.01 versus 60.5, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.102 vs $0.0225. Cache-heavy agent loop: $0.15 vs $0.037.
- Context tradeoff
- Both models list 1M.
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 evidence27 rows
Agentic
Terminal-Bench 2.0
Gemini 3.5 Flash76.2%SourceGemini 3.5 Flash-Lite54%SourceGemini 3.5 Flash leads this result
MCP Atlas
Gemini 3.5 Flash83.6%SourceGemini 3.5 Flash-Lite—Not directly comparable
Toolathlon
Gemini 3.5 Flash56.5%SourceGemini 3.5 Flash-Lite—Not directly comparable
OSWorld-Verified
Gemini 3.5 Flash78.4%SourceGemini 3.5 Flash-Lite74%SourceGemini 3.5 Flash leads this result
Finance Agent v2
Gemini 3.5 Flash57.9%SourceGemini 3.5 Flash-Lite—Not directly comparable
Gert Labs
Gemini 3.5 Flash61.85%SourceGemini 3.5 Flash-Lite—Not directly comparable
ResearchClawBench
Gemini 3.5 Flash18.0%SourceGemini 3.5 Flash-Lite—Not directly comparable
Terminal-Bench 2.1 (Vals)
Gemini 3.5 Flash74.2%SourceGemini 3.5 Flash-Lite50.2%SourceGemini 3.5 Flash leads this result
Coding
Terminal-Bench 2.0
Gemini 3.5 Flash76.2%SourceGemini 3.5 Flash-Lite54.0%SourceGemini 3.5 Flash leads this result
SWE-bench Pro
Gemini 3.5 Flash55.1%SourceGemini 3.5 Flash-Lite54.2%SourceGemini 3.5 Flash leads this result
Vibe Code Bench
Gemini 3.5 Flash48.68%SourceGemini 3.5 Flash-Lite—Not directly comparable
cursorBench31
Gemini 3.5 Flash49.8%SourceGemini 3.5 Flash-Lite—Not directly comparable
cursorBench32
Gemini 3.5 Flash48.8%SourceGemini 3.5 Flash-Lite—Not directly comparable
LiveCodeBench (Vals)
Gemini 3.5 Flash87.6%SourceGemini 3.5 Flash-Lite79.0%SourceGemini 3.5 Flash leads this result
SWE-bench (Vals)
Gemini 3.5 Flash78.8%SourceGemini 3.5 Flash-Lite75.0%SourceGemini 3.5 Flash leads this result
Reasoning
Knowledge
GPQA-D
Gemini 3.5 Flash92.7%SourceGemini 3.5 Flash-Lite—Not directly comparable
HLE
Gemini 3.5 Flash40.2%SourceGemini 3.5 Flash-Lite—Not directly comparable
GPQA Diamond (Vals)
Gemini 3.5 Flash92.7%SourceGemini 3.5 Flash-Lite83.8%SourceGemini 3.5 Flash leads this result
MMLU-Pro (Vals)
Gemini 3.5 Flash89.5%SourceGemini 3.5 Flash-Lite85.8%SourceGemini 3.5 Flash leads this result
Math
Multimodal
Frequently asked questions
Which is better, Gemini 3.5 Flash or Gemini 3.5 Flash-Lite?
Gemini 3.5 Flash has the higher public score estimate, 70.01 versus 60.5, 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 3.5 Flash or Gemini 3.5 Flash-Lite?
Gemini 3.5 Flash leads the public coding lane, 57.7 to 43.6, with Supported evidence for both models, although the 90% intervals overlap.
Which is better for agentic tasks, Gemini 3.5 Flash or Gemini 3.5 Flash-Lite?
Gemini 3.5 Flash scores higher for agentic tasks on the public lane, 50.6 to 43.4. Gemini 3.5 Flash-Lite is scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
Which costs less, Gemini 3.5 Flash or Gemini 3.5 Flash-Lite?
For the stated presets, chat costs $0.006 on Gemini 3.5 Flash and $0.00155 on Gemini 3.5 Flash-Lite; repository review costs $0.102 and $0.0225; the cache-heavy agent loop costs $0.15 and $0.037. Costs use the listed standard API rates.
Which has the larger context window, Gemini 3.5 Flash or Gemini 3.5 Flash-Lite?
Both models list the same context window, 1M.
Related comparisons
Last updated September 4, 2026
Watch Gemini 3.5 Flash vs Gemini 3.5 Flash-Lite
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.