Nova 2 Lite vs GPT-3.5 Turbo (older v0613)
GPT-3.5 Turbo (older v0613) costs 1.3x less per output token than Nova 2 Lite ($2.00 vs $2.50 per million). Updated October 22, 2026; no benchmark has tested both models yet.
- Coding
- No data
- Overall
- No data
- Output $/M
- $2.50
- Coding
- No data
- Overall
- No data
- Output $/M
- $2.00
Nova 2 Lite or GPT-3.5 Turbo (older v0613): which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Nova 2 Lite for a larger context window (1M against 4K tokens).
No benchmark has tested both yet. Nova 2 Lite has results on AA Coding Index, ALE-Bench and LMArena Text: coding; GPT-3.5 Turbo (older v0613) on GSM8K, MMLU and WinoGrande. Compare them on price and context instead.
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.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
No call
Only Nova 2 Lite has a AA Intelligence Index result, 13.4.
Directional only
Long documents
Listed context window
Nova 2 Lite
Nova 2 Lite takes 1M tokens against 4K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Nova 2 Lite
Nova 2 Lite $0.0015, GPT-3.5 Turbo (older v0613) $0.0020 per turn.
List prices
At a glance
- Coding index
- Nova 2 Lite not benchmarked, GPT-3.5 Turbo (older v0613) not benchmarked.
- Widest category
- None yet: no category has been tested on both models.
- Widest single gap
- None yet: no benchmark has tested both models.
- Output price
- Nova 2 Lite $2.50 against GPT-3.5 Turbo (older v0613) $2.00 per million output tokens, 1.3x apart.
- Context window
- Nova 2 Lite takes 1M tokens, GPT-3.5 Turbo (older v0613) 4K.
Benchmark by benchmark
Every board either model has a result on, a category to a fold; bars are each result on a 0 to 100 scale. Only one model is measured on each, so no row names a leader.
CodingDirectional onlySix of these boards feed the Vibe Coding Index4 boards measured
| Benchmark | Nova 2 Lite | GPT-3.5 Turbo (older v0613) | Leader |
|---|---|---|---|
| AA Coding Index | 23.0 | Not measured | Only Nova 2 Lite measured |
| ALE-Bench | 236.3 | Not measured | Only Nova 2 Lite measured |
| LMArena Text: coding | 1385 | Not measured | Only Nova 2 Lite measured |
| LMArena Text: software and IT | 1394 | Not measured | Only Nova 2 Lite measured |
| Neither model has a result on the other 39 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | Nova 2 Lite | GPT-3.5 Turbo (older v0613) | Leader |
|---|---|---|---|
| AA Intelligence Index | 13.4 | Not measured | Only Nova 2 Lite measured |
| Neither model has a result on the other 1 board here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index3 boards measured
| Benchmark | Nova 2 Lite | GPT-3.5 Turbo (older v0613) | Leader |
|---|---|---|---|
| LMArena Text: hard prompts | 1364 | Not measured | Only Nova 2 Lite measured |
| LMArena Text: expert | 1359 | Not measured | Only Nova 2 Lite measured |
| LMArena Text: hard prompts in English | 1385 | Not measured | Only Nova 2 Lite measured |
| Neither model has a result on the other 20 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index3 boards measured
| Benchmark | Nova 2 Lite | GPT-3.5 Turbo (older v0613) | Leader |
|---|---|---|---|
| GSM8K | Not measured | 46.9% | Only GPT-3.5 Turbo (older v0613) measured |
| LMArena Text: math | 1359 | Not measured | Only Nova 2 Lite measured |
| LMArena Text: mathematical work | 1369 | Not measured | Only Nova 2 Lite measured |
| Neither model has a result on the other 11 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index5 boards measured
| Benchmark | Nova 2 Lite | GPT-3.5 Turbo (older v0613) | Leader |
|---|---|---|---|
| MMLU | Not measured | 68.9% | Only GPT-3.5 Turbo (older v0613) measured |
| LMArena Text: science | 1382 | Not measured | Only Nova 2 Lite measured |
| LMArena Text: medicine and healthcare | 1386 | Not measured | Only Nova 2 Lite measured |
| LMArena Text: legal and government | 1359 | Not measured | Only Nova 2 Lite measured |
| LMArena Text: business and finance | 1369 | Not measured | Only Nova 2 Lite measured |
| Neither model has a result on the other 15 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index18 boards measured
| Benchmark | Nova 2 Lite | GPT-3.5 Turbo (older v0613) | Leader |
|---|---|---|---|
| WinoGrande | Not measured | 81.6% | Only GPT-3.5 Turbo (older v0613) measured |
| LMArena Text | 1362 | Not measured | Only Nova 2 Lite measured |
| LMArena Text: instruction following | 1335 | Not measured | Only Nova 2 Lite measured |
| LMArena Text: creative writing | 1292 | Not measured | Only Nova 2 Lite measured |
| LMArena Text: English | 1385 | Not measured | Only Nova 2 Lite measured |
| LMArena Text: non-English | 1337 | Not measured | Only Nova 2 Lite measured |
| LMArena Text: Chinese | 1364 | Not measured | Only Nova 2 Lite measured |
| LMArena Text: German | 1343 | Not measured | Only Nova 2 Lite measured |
| LMArena Text: Japanese | 1273 | Not measured | Only Nova 2 Lite measured |
| LMArena Text: Korean | 1281 | Not measured | Only Nova 2 Lite measured |
| LMArena Text: French | 1381 | Not measured | Only Nova 2 Lite measured |
| LMArena Text: Spanish | 1375 | Not measured | Only Nova 2 Lite measured |
| LMArena Text: Russian | 1342 | Not measured | Only Nova 2 Lite measured |
| LMArena Text: Polish | 1327 | Not measured | Only Nova 2 Lite measured |
| LMArena Text: multi-turn | 1338 | Not measured | Only Nova 2 Lite measured |
| LMArena Text: longer queries | 1335 | Not measured | Only Nova 2 Lite measured |
| LMArena Text: writing and language | 1318 | Not measured | Only Nova 2 Lite measured |
| LMArena Text: entertainment and media | 1309 | Not measured | Only Nova 2 Lite measured |
| Neither model has a result on the other 30 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 costs less
Repository review
50K input + 3K output tokens
Nova 2 Lite costs less
Agent loop
200K input + 10K output tokens
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.
| Specification | Amazon Nova 2 Lite | OpenAI GPT-3.5 Turbo (older v0613) |
|---|---|---|
| Maker | Amazon | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | December 2, 2025 | January 25, 2024 |
| Context window | 1M | 4K |
| Input $/Mtok | $0.30 | $1.00 |
| Output $/Mtok | $2.50 | $2.00 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Nova 2 Lite better than GPT-3.5 Turbo (older v0613) for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Nova 2 Lite for a larger context window (1M against 4K tokens).
Which is cheaper, Nova 2 Lite or GPT-3.5 Turbo (older v0613)?
Nova 2 Lite costs $0.30 per million input tokens and $2.50 per million output tokens; GPT-3.5 Turbo (older v0613) costs $1.00 and $2.00. Cost per solved task is known for neither of them.
Which has the bigger context window, Nova 2 Lite or GPT-3.5 Turbo (older v0613)?
Nova 2 Lite, with 1M tokens against 4K.
Has any benchmark tested both Nova 2 Lite and GPT-3.5 Turbo (older v0613)?
No benchmark has tested both yet. Nova 2 Lite has results on AA Coding Index, ALE-Bench and LMArena Text: coding; GPT-3.5 Turbo (older v0613) on GSM8K, MMLU and WinoGrande. Compare them on price and context instead. Data as of October 22, 2026.