Enter opens the highlighted result. Esc closes.

Nova Lite 1.0 vs Gemini 2.5 Flash

Updated October 21, 2026. 40 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Nova Lite 1.0 Replace Gemini 2.5 Flash
Nova Lite 1.0Amazon
Coding
No data
Overall
6.7
Output $/M
$0.24
0
Gemini 2.5 FlashGoogle
Coding
No data
Overall
15.5
Output $/M
$2.50
40
vs boards won of 40 shared

Decision reading

Neither model has a coding score yet, so the two cannot be ranked on coding.

Nova Lite 1.0 has the edge where output tokens cost 10.4x less, and where what matters is LiveCodeBench (Artificial Analysis run) or Terminal-Bench Hard (Artificial Analysis run), where it leads.

Model ANova Lite 1.0AmazonNot benchmarkedNo coding benchmarkNo cost per solved taskModel BGemini 2.5 FlashGoogleNot benchmarkedNo coding benchmark$0.466 per solved task
Shared results
40
Nova Lite 1.0 only
1
Gemini 2.5 Flash only
29
Like-for-like categories
7 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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
Nova Lite 1.0 not benchmarked, Gemini 2.5 Flash not benchmarked.
Widest category
Math, 48.7 points apart on average over 4 shared benchmarks.
Widest single gap
AIME 2025 (Artificial Analysis run): Nova Lite 1.0 7.0% against Gemini 2.5 Flash 73.3%, 66.3 points apart on a 0 to 100 scale.
Output price
Nova Lite 1.0 $0.24 against Gemini 2.5 Flash $2.50 per million output tokens, 10.4x apart.
Context window
Nova Lite 1.0 takes 300K tokens, Gemini 2.5 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
CategoryNova Lite 1.0BarsGemini 2.5 FlashTies
Coding04
Intelligence01
Agentic work01
Reasoning05
Math04
Knowledge05
General020
All shared boards040
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
Coding benchmarks for Nova Lite 1.0 and Gemini 2.5 Flash
BenchmarkNova Lite 1.0Gemini 2.5 FlashLeader
SWE-bench VerifiedNot measured28.7%Only Gemini 2.5 Flash measured
LiveCodeBench (Artificial Analysis run)16.7%69.5%Gemini 2.5 Flash
Terminal-Bench Hard (Artificial Analysis run)0.8%13.6%Gemini 2.5 Flash
Terminal-BenchNot measured17.1%Only Gemini 2.5 Flash measured
LMArena Text: coding12391423Gemini 2.5 Flash
LMArena Text: software and IT12411425Gemini 2.5 Flash
Neither model has a result on the other 32 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Nova Lite 1.0 and Gemini 2.5 Flash
BenchmarkNova Lite 1.0Gemini 2.5 FlashLeader
AA Intelligence Index6.715.5Gemini 2.5 Flash
Epoch Capabilities IndexNot measured142.9Only Gemini 2.5 Flash measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Nova Lite 1.0 and Gemini 2.5 Flash
BenchmarkNova Lite 1.0Gemini 2.5 FlashLeader
τ²-Bench Telecom17.5%31.6%Gemini 2.5 Flash
BALROGNot measured33.5%Only Gemini 2.5 Flash measured
Vending-Bench 2Not measured$549Only Gemini 2.5 Flash measured
Neither model has a result on the other 36 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
Reasoning benchmarks for Nova Lite 1.0 and Gemini 2.5 Flash
BenchmarkNova Lite 1.0Gemini 2.5 FlashLeader
GPQA Diamond (Artificial Analysis run)43.3%79.0%Gemini 2.5 Flash
Humanity's Last Exam (Artificial Analysis run)4.3%12.1%Gemini 2.5 Flash
ARC-AGINot measured33.3%Only Gemini 2.5 Flash measured
ARC-AGI-2Not measured2.5%Only Gemini 2.5 Flash measured
SimpleBenchNot measured41.2%Only Gemini 2.5 Flash measured
LMArena Text: hard prompts12201422Gemini 2.5 Flash
LMArena Text: expert12011426Gemini 2.5 Flash
LMArena Text: hard prompts in English12261420Gemini 2.5 Flash
LMArena Vision: diagramsNot measured1245Only Gemini 2.5 Flash measured
LMArena Vision: homeworkNot measured1244Only Gemini 2.5 Flash measured
Neither model has a result on the other 11 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index04
Math benchmarks for Nova Lite 1.0 and Gemini 2.5 Flash
BenchmarkNova Lite 1.0Gemini 2.5 FlashLeader
AA Math Index7.073.3Gemini 2.5 Flash
AIME 2025 (Artificial Analysis run)7.0%73.3%Gemini 2.5 Flash
LMArena Text: math12271411Gemini 2.5 Flash
LMArena Text: mathematical work12351422Gemini 2.5 Flash
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index05
Knowledge benchmarks for Nova Lite 1.0 and Gemini 2.5 Flash
BenchmarkNova Lite 1.0Gemini 2.5 FlashLeader
MedCode (Vals AI)Not measured40.4%Only Gemini 2.5 Flash measured
MMLU Pro (Artificial Analysis run)59.0%83.2%Gemini 2.5 Flash
MMLU77.0%Not measuredOnly Nova Lite 1.0 measured
LMArena Text: science12321433Gemini 2.5 Flash
LMArena Text: medicine and healthcare12131428Gemini 2.5 Flash
LMArena Text: legal and government12381430Gemini 2.5 Flash
LMArena Text: business and finance12191404Gemini 2.5 Flash
Neither model has a result on the other 10 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Web design benchmarks for Nova Lite 1.0 and Gemini 2.5 Flash
BenchmarkNova Lite 1.0Gemini 2.5 FlashLeader
Design Arena: websitesNot measured1074Only Gemini 2.5 Flash measured
Design Arena: UI componentsNot measured1005Only Gemini 2.5 Flash measured
Design Arena: game devNot measured1005Only Gemini 2.5 Flash measured
Design Arena: data vizNot measured1060Only Gemini 2.5 Flash measured
Design Arena: 3DNot measured1021Only Gemini 2.5 Flash measured
Design Arena: all code categoriesNot measured1059Only Gemini 2.5 Flash measured
Design Arena: SVGNot measured1020Only Gemini 2.5 Flash measured
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index020
General benchmarks for Nova Lite 1.0 and Gemini 2.5 Flash
BenchmarkNova Lite 1.0Gemini 2.5 FlashLeader
SAGE (Vals AI)Not measured44.8%Only Gemini 2.5 Flash measured
MedScribe (Vals AI)Not measured83.0%Only Gemini 2.5 Flash measured
IFBench34.1%50.3%Gemini 2.5 Flash
Long context reasoning (AA-LCR)19.0%65.3%Gemini 2.5 Flash
DTBenchNot measured76.5%Only Gemini 2.5 Flash measured
LMCANot measured27.5%Only Gemini 2.5 Flash measured
LMArena Text12291417Gemini 2.5 Flash
LMArena Text: instruction following12051405Gemini 2.5 Flash
LMArena Text: creative writing11971400Gemini 2.5 Flash
LMArena Vision9901235Gemini 2.5 Flash
LMArena Text: English12431418Gemini 2.5 Flash
LMArena Text: non-English12081409Gemini 2.5 Flash
LMArena Text: Chinese12251449Gemini 2.5 Flash
LMArena Text: German12291417Gemini 2.5 Flash
LMArena Text: Japanese11531396Gemini 2.5 Flash
LMArena Text: Korean11531385Gemini 2.5 Flash
LMArena Text: French12381432Gemini 2.5 Flash
LMArena Text: Spanish12261422Gemini 2.5 Flash
LMArena Text: Russian12161415Gemini 2.5 Flash
LMArena Text: PolishNot measured1413Only Gemini 2.5 Flash measured
LMArena Text: multi-turn11991408Gemini 2.5 Flash
LMArena Text: longer queries12341419Gemini 2.5 Flash
LMArena Text: writing and language12111405Gemini 2.5 Flash
LMArena Text: entertainment and media11761393Gemini 2.5 Flash
LMArena Vision: English9991239Gemini 2.5 Flash
LMArena Vision: ChineseNot measured1284Only Gemini 2.5 Flash measured
LMArena Vision: reading textNot measured1237Only Gemini 2.5 Flash measured
LMArena Vision: humorNot measured1225Only Gemini 2.5 Flash measured
LMArena Vision: captioningNot measured1277Only Gemini 2.5 Flash measured
LMArena Vision: recognizing thingsNot measured1252Only Gemini 2.5 Flash measured
LMArena Vision: creative writingNot measured1241Only Gemini 2.5 Flash measured
Neither model has a result on the other 15 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Nova Lite 1.0 and Gemini 2.5 Flash
BenchmarkNova Lite 1.0Gemini 2.5 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

Nova Lite 1.0$0.0002Fits in one request
Gemini 2.5 Flash$0.0015Fits in one request

Nova Lite 1.0 costs less

Repository review

50K input + 3K output tokens

Nova Lite 1.0$0.0037Fits in one request
Gemini 2.5 Flash$0.022Fits in one request

Nova Lite 1.0 costs less

Agent loop

200K input + 10K output tokens

Nova Lite 1.0$0.014Fits in one request
Gemini 2.5 Flash$0.085Fits in one request

Nova Lite 1.0 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 Nova Lite 1.0 and Gemini 2.5 Flash
SpecificationAmazon Nova Lite 1.0Google Gemini 2.5 Flash
MakerAmazonGoogle
WeightsNo public weights listedNo public weights listed
ReleasedDecember 5, 2024June 17, 2025
Context window300K1.05M
Input $/Mtok$0.06$0.30
Output $/Mtok$0.24$2.50
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computable$0.466
SourceOpenRouter listingOpenRouter listing

Questions

Is Nova Lite 1.0 better than Gemini 2.5 Flash for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Nova Lite 1.0 has the edge where output tokens cost 10.4x less, and where what matters is LiveCodeBench (Artificial Analysis run) or Terminal-Bench Hard (Artificial Analysis run), where it leads.

Which is cheaper, Nova Lite 1.0 or Gemini 2.5 Flash?

Nova Lite 1.0 costs $0.06 per million input tokens and $0.24 per million output tokens; Gemini 2.5 Flash costs $0.30 and $2.50. Cost per solved task is known for Gemini 2.5 Flash only.

Which has the bigger context window, Nova Lite 1.0 or Gemini 2.5 Flash?

Gemini 2.5 Flash, with 1.05M tokens against 300K.

How many benchmarks is the Nova Lite 1.0 vs Gemini 2.5 Flash comparison based on?

40 benchmarks have a result for both models as of October 21, 2026. Nova Lite 1.0's coding index rests on 0 independent benchmarks and Gemini 2.5 Flash's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next