AmazonNova 2 Lite
Nova 2 Lite is an Amazon proprietary reasoning model, released 2 Dec 2025. Its best configuration ranks #412 of 785 on the BenchLeader Index at 48.9 ±3.7, in the lower half. The ± is the point: 303 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in coding (51) and lowest in agents & tools (40). At $0.935 per million tokens blended it is mid-priced. Output speed of 115 tokens per second puts it faster than most, with a first token in 0.7 s. Last measured 22 Oct 2026.
- Blended price
- $0.935/M
- $0.330 in · $2.75 out
- Output speed
- 115 tok/s
- OpenRouter traffic, 7-day median; not yet measured by Artificial Analysis
- First answer
- 0.65 s
- Context
- 1M
- Full answer
- –
- Cost per run
- –
- Released
- 2 Dec 2025
- Overall index49
- Reasoning51
- Coding51
- Agents & tools40
- Maths50
- Human preference50
Versions
Amazon has shipped 4 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| Nova 2 Litethis page | 2 Dec 2025 | 48.9 | #412 |
| Nova 2.0 Litethinking | 29 Oct 2025 | 49.1 | #407 |
| Nova Lite | 3 Dec 2024 | 38.3 | #717 |
| Nova Lite 1.0 | – | 42.2 | #605 |
How its index has moved
19 Sept 2026 to 21 Oct 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Hard Prompts | 1357#209 | Arena (LMArena) |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Coding | 1393#198 | Arena (LMArena) |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| BFCL Overall | 27.1%#59 | Berkeley Function Calling Leaderboard |
Maths
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Maths | 1330#209 | Arena (LMArena) |
Instruction following
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Instruction Followingnot in index | 1328#209 | Arena (LMArena) |
Human preference
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Text | 1335#221 | Arena (LMArena) | |
| Arena Creative Writingnot in index | 1270#247 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1323#222 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1334#223 | Arena (LMArena) |
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Amazon Bedrock | 102 tok/s | 0.65 s | $0.300 | $2.50 | 1M | – |
| Amazon Bedrock | 97 tok/s | 0.60 s | $0.300 | $2.50 | 1M | – |
Price history
The price above, per 1M tokens, every day it changed.
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.083 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0010 | $0.0009 | 3.3 s |
| Summarize a 30-page report | 12,000 / 600 | $0.0056 | $0.0034 | 5.9 s |
| Code edit | 6,000 / 1,500 | $0.0061 | $0.0050 | 13.7 s |
| Agentic coding session | 60,000 / 4,000 | $0.031 | $0.020 | 35.4 s |
| Structured extraction | 2,000 / 200 | $0.0012 | $0.0008 | 2.4 s |
See also
Questions people ask
- What are Nova 2 Lite's benchmark scores?
- As of 25 Oct 2026, Nova 2 Lite scores 48.9 ±3.7 on the BenchLeader Index, strongest in coding (51) and weakest in agents & tools (40). That rests on 5 independent benchmark results, and every score on this page links to its publisher.
- How does Nova 2 Lite rank?
- Nova 2 Lite is #412 of 785 ranked configurations on 25 Oct 2026. 303 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- How much does Nova 2 Lite cost per 1M tokens?
- As of 25 Oct 2026, Nova 2 Lite costs $0.330 per 1M input tokens and $2.75 per 1M output tokens, $0.935 blended (three input tokens per output token). The list price last changed on 9 Sept 2026.
- When was Nova 2 Lite released?
- Amazon released Nova 2 Lite on 2 Dec 2025.
Data as of 25 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Nova 2 Lite: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/nova-2-lite.