Enter opens the highlighted result. Esc closes.

Nova 2 Lite vs GPT-4

Nova 2 Lite leads GPT-4 on the Artificial Analysis Intelligence Index, 13.4 to 6.7, and Nova 2 Lite costs 24.0x less per output token ($2.50 vs $60.00 per million). Updated October 21, 2026; 30 benchmarks have a result for both.

Replace Nova 2 Lite Replace GPT-4
Nova 2 LiteAmazon
Coding
No data
Overall
No data
Output $/M
$2.50
30
GPT-4OpenAI
Coding
No data
Overall
No data
Output $/M
$60.00
0
vs boards won of 30 shared

Nova 2 Lite or GPT-4: which to pick

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

Pick Nova 2 Lite for output tokens 24.0x cheaper ($2.50 vs $60.00 per million) and a larger context window (1M against 8K tokens).

Model ANova 2 LiteAmazonNot benchmarkedNo coding benchmarkNo cost per solved taskModel BGPT-4OpenAINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
30
Nova 2 Lite only
1
GPT-4 only
15
Like-for-like categories
6 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
Nova 2 Lite not benchmarked, GPT-4 not benchmarked.
Widest category
Knowledge, 34.9 points apart on average over 4 shared benchmarks.
Widest single gap
LMArena Text: medicine and healthcare: Nova 2 Lite 1386 against GPT-4 1145, 40.1 points apart on a 0 to 100 scale.
Output price
Nova 2 Lite $2.50 against GPT-4 $60.00 per million output tokens, 24.0x apart.
Context window
Nova 2 Lite takes 1M tokens, GPT-4 8K.

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 2 LiteBarsGPT-4Ties
Coding30
Intelligence10
Reasoning30
Math20
Knowledge40
General170
All shared boards300
CodingLike-for-likeSix of these boards feed the Vibe Coding Index30
Coding benchmarks for Nova 2 Lite and GPT-4
BenchmarkNova 2 LiteGPT-4Leader
SWE-bench VerifiedNot measured22.4%Only GPT-4 measured
SWE-bench LiteNot measured39.7%Only GPT-4 measured
SWE-bench (full test set)Not measured12.5%Only GPT-4 measured
AA Coding Index23.013.1Nova 2 Lite
ALE-Bench236.3Not measuredOnly Nova 2 Lite measured
LMArena Text: coding13851209Nova 2 Lite
LMArena Text: software and IT13941195Nova 2 Lite
Neither model has a result on the other 32 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for Nova 2 Lite and GPT-4
BenchmarkNova 2 LiteGPT-4Leader
AA Intelligence Index13.46.7Nova 2 Lite
Epoch Capabilities IndexNot measured125.7Only GPT-4 measured
Agentic workNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Agentic work benchmarks for Nova 2 Lite and GPT-4
BenchmarkNova 2 LiteGPT-4Leader
Neither model has a result on 41 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index30
Reasoning benchmarks for Nova 2 Lite and GPT-4
BenchmarkNova 2 LiteGPT-4Leader
GPQA Diamond (Artificial Analysis run)Not measured34.9%Only GPT-4 measured
BIG-Bench HardNot measured75.1%Only GPT-4 measured
LMArena Text: hard prompts13641200Nova 2 Lite
LMArena Text: expert13591149Nova 2 Lite
LMArena Text: hard prompts in English13851209Nova 2 Lite
Neither model has a result on the other 17 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for Nova 2 Lite and GPT-4
BenchmarkNova 2 LiteGPT-4Leader
GSM8KNot measured92.0%Only GPT-4 measured
LMArena Text: math13591230Nova 2 Lite
LMArena Text: mathematical work13691228Nova 2 Lite
Neither model has a result on the other 10 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
Knowledge benchmarks for Nova 2 Lite and GPT-4
BenchmarkNova 2 LiteGPT-4Leader
MMLU Pro (Artificial Analysis run)Not measured56.2%Only GPT-4 measured
MMLUNot measured86.4%Only GPT-4 measured
AI2 Reasoning ChallengeNot measured96.3%Only GPT-4 measured
LMArena Text: science13821177Nova 2 Lite
LMArena Text: medicine and healthcare13861145Nova 2 Lite
LMArena Text: legal and government13591191Nova 2 Lite
LMArena Text: business and finance13691145Nova 2 Lite
Neither model has a result on the other 11 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for Nova 2 Lite and GPT-4
BenchmarkNova 2 LiteGPT-4Leader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index170
General benchmarks for Nova 2 Lite and GPT-4
BenchmarkNova 2 LiteGPT-4Leader
IFBenchNot measured33.2%Only GPT-4 measured
DTBenchNot measured62.7%Only GPT-4 measured
LMCANot measured17.1%Only GPT-4 measured
HellaSwagNot measured95.3%Only GPT-4 measured
WinoGrandeNot measured87.5%Only GPT-4 measured
LMArena Text13621206Nova 2 Lite
LMArena Text: instruction following13351201Nova 2 Lite
LMArena Text: creative writing12921191Nova 2 Lite
LMArena Text: English13851220Nova 2 Lite
LMArena Text: non-English13371194Nova 2 Lite
LMArena Text: Chinese13641184Nova 2 Lite
LMArena Text: German13431198Nova 2 Lite
LMArena Text: Japanese12731137Nova 2 Lite
LMArena Text: Korean12811087Nova 2 Lite
LMArena Text: French13811220Nova 2 Lite
LMArena Text: Spanish13751197Nova 2 Lite
LMArena Text: Russian13421195Nova 2 Lite
LMArena Text: Polish13271265Nova 2 Lite
LMArena Text: multi-turn13381206Nova 2 Lite
LMArena Text: longer queries13351190Nova 2 Lite
LMArena Text: writing and language13181219Nova 2 Lite
LMArena Text: entertainment and media13091184Nova 2 Lite
Neither model has a result on the other 24 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Nova 2 Lite and GPT-4
BenchmarkNova 2 LiteGPT-4Leader
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 2 Lite$0.0015Fits in one request
GPT-4$0.060Fits in one request

Nova 2 Lite costs less

Repository review

50K input + 3K output tokens

Nova 2 Lite$0.022Fits in one request
GPT-4$1.68Exceeds the context window

Nova 2 Lite costs less

Agent loop

200K input + 10K output tokens

Nova 2 Lite$0.085Fits in one request
GPT-4$6.60Exceeds the context window

Nova 2 Lite 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 2 Lite and GPT-4
SpecificationAmazon Nova 2 LiteOpenAI GPT-4
MakerAmazonOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedDecember 2, 2025May 28, 2023
Context window1M8K
Input $/Mtok$0.30$30.00
Output $/Mtok$2.50$60.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Nova 2 Lite better than GPT-4 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Nova 2 Lite for output tokens 24.0x cheaper ($2.50 vs $60.00 per million) and a larger context window (1M against 8K tokens).

Which is cheaper, Nova 2 Lite or GPT-4?

Nova 2 Lite costs $0.30 per million input tokens and $2.50 per million output tokens; GPT-4 costs $30.00 and $60.00. Cost per solved task is known for neither of them.

Which has the bigger context window, Nova 2 Lite or GPT-4?

Nova 2 Lite, with 1M tokens against 8K.

How many benchmarks is the Nova 2 Lite vs GPT-4 comparison based on?

30 benchmarks have a result for both models as of October 21, 2026. Nova 2 Lite's coding index rests on 0 independent benchmarks and GPT-4's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next