Nova 2.0 Lite
Nova 2.0 Lite is behind the leaders in instruction following, long context, multimodal tasks, coding, and reasoning. Too few results yet to rate agentic tasks, safety, math, multilingual tasks, or factuality.
Capability profile
Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.
Too few results yet to rate Agentic, Safety, Math, Multilingual or Factuality.
Price
$0.30input$2.50outputper million tokens
From Artificial Analysis · All prices
Evidence
67results on22benchmarks
- 4 independently verified
- 63 aggregator
From 2 sources · latest Oct 8, 2026 · How verification works
Nova 2.0 Lite benchmark results
67 results on 22 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
28.2% behind the leader1 of 3 ranked benchmarks measured
- IFBench70.75Oct 8, 2026aa_ifbench
31.6% behind the leader1 of 3 ranked benchmarks measured
- 60.33Oct 8, 2026
35.1% behind the leader1 of 6 ranked benchmarks measured
- MMMU-Pro63.76Oct 8, 2026aa_mmmu_pro
40.2% behind the leader3 of 10 ranked benchmarks measured
- SciCode36.92Sep 4, 2026aa_scicode
- Terminal-Bench Hard16.67Oct 8, 2026aa_terminalbench_hard
- Terminal-Bench 2.116.10Oct 8, 2026terminalbenchV21
Show 6 more coding resultsHide 6 coding results
- SciCode36.81Sep 4, 2026aa_scicode
- SciCode23.96Sep 4, 2026aa_scicode
- SciCode33.33Sep 4, 2026aa_scicode
- Terminal-Bench Hard17.42Oct 8, 2026aa_terminalbench_hard
- Terminal-Bench Hard3.79Oct 8, 2026aa_terminalbench_hard
- Terminal-Bench Hard6.82Oct 8, 2026aa_terminalbench_hard
41.7% behind the leader3 of 6 ranked benchmarks measured
- GPQA Diamond81.11Oct 8, 2026gpqa
- Humanity's Last Exam11.63Oct 8, 2026aa_hle
- 0.29Oct 8, 2026
Show 7 more reasoning resultsHide 7 reasoning results
- 0.00Oct 8, 2026
- GPQA Diamond76.77Oct 8, 2026gpqa
- GPQA Diamond69.80Oct 8, 2026gpqa
- GPQA Diamond60.30Oct 8, 2026gpqa
- Humanity's Last Exam8.99Oct 8, 2026aa_hle
- Humanity's Last Exam4.03Oct 8, 2026aa_hle
- Humanity's Last Exam2.87Oct 8, 2026aa_hle
0 of 7 ranked benchmarks measured
- 0.00Oct 8, 2026
- τ-Bench V3 · Banking6.80Aug 10, 2026tauBanking
- 7.07Jun 15, 2026
Show 1 more agentic resultHide 1 agentic result
- 0.41Jun 15, 2026
0 of 4 ranked benchmarks measured
- 5.10May 2, 2026
- AA-Omniscience · Accuracy18.17Oct 8, 2026omniscienceAccuracy
- AA-Omniscience · Non-hallucination8.19Oct 8, 2026omniscienceNonHallucination
Show 6 more factuality resultsHide 6 factuality results
- AA-Omniscience · Accuracy14.02Oct 8, 2026omniscienceAccuracy
- AA-Omniscience · Accuracy19.03Oct 8, 2026omniscienceAccuracy
- AA-Omniscience · Accuracy17.65Oct 8, 2026omniscienceAccuracy
- AA-Omniscience · Non-hallucination8.58Oct 8, 2026omniscienceNonHallucination
- AA-Omniscience · Non-hallucination12.87Oct 8, 2026omniscienceNonHallucination
- AA-Omniscience · Non-hallucination14.13Oct 8, 2026omniscienceNonHallucination
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- vectara_avg_summary_length94.10May 2, 2026Average Summary Length (Words)
- vectara_answer_rate99.60May 2, 2026Answer Rate
- vectara_factual_consistency94.90May 2, 2026Factual Consistency Rate
- -56.97Oct 8, 2026
- AA Intelligence12.48Oct 8, 2026aa_intelligence_index
- τ²-Bench Telecom (AA run)75.73Oct 8, 2026aa_tau2
Show 17 more resultsHide 17 results
- 3.13Aug 10, 2026
- 32.85Jun 18, 2026
- 27.77Jun 18, 2026
- 21.06Jun 18, 2026
- AA Intelligence13.37Oct 8, 2026aa_intelligence_index
- AA Intelligence11.80Oct 8, 2026aa_intelligence_index
- AA Intelligence8.74Oct 8, 2026aa_intelligence_index
- -54.98Oct 8, 2026
- -54.10Oct 8, 2026
- -59.82Oct 8, 2026
- Artificial Analysis Coding Index23.04Sep 9, 2026aa_coding_index
- 23.88Jun 18, 2026
- Artificial Analysis Coding Index12.53Jun 18, 2026aa_coding_index
- Artificial Analysis Coding Index13.64Jun 18, 2026aa_coding_index
- τ²-Bench Telecom (AA run)72.81Oct 8, 2026aa_tau2
- τ²-Bench Telecom (AA run)71.93Oct 8, 2026aa_tau2
- τ²-Bench Telecom (AA run)61.99Oct 8, 2026aa_tau2
Nova 2.0 Lite: common questions
Who makes Nova 2.0 Lite?
Nova 2.0 Lite is made by Amazon.
When was Nova 2.0 Lite released?
Nova 2.0 Lite was released on Oct 29, 2025, according to Artificial Analysis.
What is Nova 2.0 Lite good at?
Nova 2.0 Lite is behind the leaders in instruction following, long context, multimodal tasks, coding, and reasoning. Too few results yet to rate agentic tasks, safety, math, multilingual tasks, or factuality.
How much does Nova 2.0 Lite cost?
Nova 2.0 Lite costs $0.30 per million input tokens and $2.50 per million output tokens, according to Artificial Analysis. At a mix of three input tokens to one output token, it costs more than 55% of the 331 priced models we track.
How many benchmarks has Nova 2.0 Lite been tested on?
We track 67 results for Nova 2.0 Lite on 22 benchmarks from 2 sources, 4 of them independently verified. The latest was recorded on Oct 8, 2026.
About this record
Where Nova 2.0 Lite's numbers come from, and every name it appears under.
- Tracked since
- Apr 27, 2026
- Newest source mention
- Jul 20, 2026
Where the results come from
Verification: 67 scores · 4 independently verified · 63 aggregator-attributed. How these tiers are assigned
From 2 sources on 2 sites. Artificial Analysis supplies 63 of them; the 4 independently verified results come from 1 site. Bars are coloured by trust tier.
- artificialanalysis.ai63
- raw.githubusercontent.com4
Also known as
How our sources name Nova 2.0 Lite at each reasoning setting.
| Setting | Short form | API id |
|---|---|---|
| low | nova 2.0 lite (low) | nova-2-0-lite-reasoning-low |
| medium | Nova 2.0 Lite (medium) | nova-2-0-lite-reasoning-medium |
| high | nova 2.0 lite (high) | — |