AmazonNova 2.0 Lite
Nova 2.0 Lite is an Amazon proprietary reasoning model, released 29 Oct 2025. Its best configuration (thinking reasoning effort) ranks #407 of 785 on the BenchLeader Index at 49.1 ±7.4, in the lower half. The ± is the point: 431 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 instruction following (70) and lowest in knowledge (37). At $0.850 per million tokens blended it is mid-priced. Output speed of 182 tokens per second puts it in the fastest quarter, with a first answer in 27.0 s. It has been measured at 4 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 29 Oct 2025.stale: no new result in six months
- Blended price
- $0.850/M
- $0.300 in · $2.50 out
- Output speed
- 182 tok/s
- measured by Artificial Analysis
- First answer
- 27 s
- Context
- 1M
- Full answer
- 30 s
- median, reasoning included
- Cost per run
- –
- Released
- 29 Oct 2025
- Overall index49
- Reasoning41
- Agents & tools48
- Knowledge37
- Instruction following70
- Multimodal46
- Long context55
- Composite44
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 Lite | 2 Dec 2025 | 48.9 | #412 |
| Nova 2.0 Litethinkingthis page | 29 Oct 2025 | 49.1 | #407 |
| Nova Lite | 3 Dec 2024 | 38.3 | #717 |
| Nova Lite 1.0 | – | 42.2 | #605 |
Reasoning-effort configurations
The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Not stated” collects results from publishers that did not say which setting they used; for a reasoning model that is usually its thinking mode, but we do not assume it. Pick a setting here or at the top of the page to see its price, speed and category scores.
| Effort | Index | Rank | Speed | First answer | Chat reply cost | Categories |
|---|---|---|---|---|---|---|
| no reasoning | 41.2 | #636 | 176 tok/s | 1.05 s | $0.0009 | Agents & tools 40 · Composite 39 · Instruction following 43 · Knowledge 35 · Long context 33 · Multimodal 31 · Reasoning 41 |
| low | 46.1 | #498 | 175 tok/s | 20 s | $0.0009 | Agents & tools 37 · Composite 43 · Instruction following 61 · Knowledge 37 · Long context 52 · Multimodal 41 · Reasoning 41 |
| medium | 48.6 | #421 | 177 tok/s | 23 s | $0.0009 | Agents & tools 49 · Composite 43 · Instruction following 68 · Knowledge 36 · Long context 55 · Multimodal 45 · Reasoning 41 |
| thinkingbest | 49.1 | #407 | 182 tok/s | 27 s | $0.0009 | Agents & tools 48 · Composite 44 · Instruction following 70 · Knowledge 37 · Long context 55 · Multimodal 46 · Reasoning 41 |
How its index has moved
9 Sept 2026 to 23 Oct 2026- thinking
- medium
- low
- no reasoning
The 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 | no reasoning | low | medium | thinking | Source | Trend |
|---|---|---|---|---|---|---|
| GPQA Diamond (AA)not in index | 60.3%#374 | 69.8%#301 | 76.8%#228 | 81.1%#183 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 2.9%#608 | 4.0%#548 | 9.0%#339 | 11.6%#291 | Artificial Analysis | |
| CritPt | 0.0%#315 | 0.0%#315 | 0.0%#315 | 0.3%#271 | Artificial Analysis |
Coding
| Benchmark | thinking | Source | Trend |
|---|---|---|---|
| Terminal-Bench 2.1 (AA)not in index | 16.1%#182 | Artificial Analysis |
Agents & tools
| Benchmark | no reasoning | low | medium | thinking | Source | Trend |
|---|---|---|---|---|---|---|
| Terminal-Bench Hard | 6.8%#249 | 3.8%#298 | 17.4%#178 | 16.7%#184 | Artificial Analysis | |
| τ²-Bench Telecom (AA)not in index | 62.0%#176 | 71.9%#150 | 75.7%#136 | 72.8%#147 | Artificial Analysis | |
| GDPval-AA v2.1not in index | – | – | – | 0.0%#124 | Artificial Analysis |
Knowledge
| Benchmark | no reasoning | low | medium | thinking | Source | Trend |
|---|---|---|---|---|---|---|
| AA-Omniscience | -59.8#464 | -54.1#425 | -57.0#442 | -55.0#435 | Artificial Analysis | |
| AA-Omniscience: accuracynot in index | 14.0%#445 | 17.6%#360 | 18.2%#344 | 19.0%#321 | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 14.1%#353 | 12.9%#368 | 8.2%#466 | 8.6%#455 | Artificial Analysis |
Instruction following
| Benchmark | no reasoning | low | medium | thinking | Source | Trend |
|---|---|---|---|---|---|---|
| IFBench | 40.5%#256 | 61.2%#121 | 68.5%#80 | 70.8%#64 | Artificial Analysis |
Multimodal
| Benchmark | no reasoning | low | medium | thinking | Source | Trend |
|---|---|---|---|---|---|---|
| MMMU-Pro | 49.0%#243 | 58.0%#221 | 62.5%#194 | 63.8%#188 | Artificial Analysis |
Long context
| Benchmark | no reasoning | low | medium | thinking | Source | Trend |
|---|---|---|---|---|---|---|
| AA-LCR | 18.7%#441 | 54.3%#304 | 60.0%#282 | 60.3%#279 | Artificial Analysis |
Composite
| Benchmark | no reasoning | low | medium | thinking | Source | Trend |
|---|---|---|---|---|---|---|
| AA Intelligence Index v4.3.2 | 8.7#428 | 11.8#344 | 12.5#328 | 13.4#310 | Artificial Analysis |
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. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0009 | – | 28.7 s |
| Summarize a 30-page report | 12,000 / 600 | $0.0051 | – | 30.3 s |
| Code edit | 6,000 / 1,500 | $0.0056 | – | 35.3 s |
| Agentic coding session | 60,000 / 4,000 | $0.028 | – | 49.0 s |
| Structured extraction | 2,000 / 200 | $0.0011 | – | 28.1 s |
See also
Questions people ask
- What are Nova 2.0 Lite's benchmark scores?
- As of 25 Oct 2026, Nova 2.0 Lite (thinking effort) scores 49.1 ±7.4 on the BenchLeader Index, strongest in instruction following (70) and weakest in knowledge (37). That rests on 7 independent benchmark results, and every score on this page links to its publisher.
- How does Nova 2.0 Lite rank?
- Nova 2.0 Lite (thinking effort) is #407 of 785 ranked configurations on 25 Oct 2026. 431 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 2.0 Lite cost per 1M tokens?
- As of 25 Oct 2026, Nova 2.0 Lite costs $0.300 per 1M input tokens and $2.50 per 1M output tokens, $0.850 blended (three input tokens per output token). The list price last changed on 17 Oct 2026.
- When was Nova 2.0 Lite released?
- Amazon released Nova 2.0 Lite on 29 Oct 2025. BenchLeader has results for it at 4 reasoning-effort settings.
Data as of 25 Oct 2026. Compare these configurations.
Cite as: BenchLeader, “Nova 2.0 Lite: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/nova-2-0-lite.