Nova Lite
Nova Lite is behind the leaders in factuality and multimodal tasks. Too few results yet to rate reasoning, coding, agentic tasks, safety, long context, math, multilingual tasks, or instruction following.
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 Reasoning, Coding, Agentic, Safety, Long Context, Math, Multilingual or Instruction Following.
Price
$0.06input$0.24outputper million tokens
From Artificial Analysis · All prices
Evidence
43results on41benchmarks
- 13 independently verified
- 16 aggregator
- 14 vendor-reported
From 10 sources · latest Oct 8, 2026 · How verification works
Research
1 paper reference Nova LiteNova Lite benchmark results
43 results on 41 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
36.5% behind the leader3 of 4 ranked benchmarks measured
- 6.10May 2, 2026
- AA-Omniscience · Non-hallucination42.39Oct 8, 2026omniscienceNonHallucination
- AA-Omniscience · Accuracy9.80Oct 8, 2026omniscienceAccuracy
48.5% behind the leader2 of 6 ranked benchmarks measured
- 56.20Oct 7, 2026
- MMMU-Pro37.80Oct 8, 2026aa_mmmu_pro
0 of 6 ranked benchmarks measured
- 0.00Oct 8, 2026
- GPQA Diamond43.33Oct 8, 2026gpqa
- Humanity's Last Exam4.29Oct 8, 2026aa_hle
Show 1 more reasoning resultHide 1 reasoning result
- GPQA Diamond42.00Oct 7, 2026GPQA
0 of 10 ranked benchmarks measured
- LiveBench · Coding27.34Jun 17, 2026livebench_coding@2025-04-07
- Terminal-Bench Hard0.76Oct 8, 2026aa_terminalbench_hard
- SciCode13.89Sep 4, 2026aa_scicode
0 of 7 ranked benchmarks measured
- 0.00Jun 15, 2026
0 of 3 ranked benchmarks measured
- 19.00Oct 8, 2026
0 of 3 ranked benchmarks measured
- LiveBench · Instruction Following57.10Jun 17, 2026livebench_instruction_following@2025-04-07
- IFBench34.15Oct 8, 2026aa_ifbench
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- 92.80Jul 2, 2026
- 82.90Jul 2, 2026
- 35.24Jun 23, 2026
- 76.81Jun 23, 2026
- 69.31Jun 23, 2026
- 77.86Jun 23, 2026
Show 21 more resultsHide 21 results
- 5.85Jun 18, 2026
- AA Intelligence6.67Oct 8, 2026aa_intelligence_index
- -42.17Oct 8, 2026
- ARC-Challenge92.40Oct 7, 2026ARC-C
- 5.13Jun 18, 2026
- 82.40Oct 7, 2026
- BFCLv466.60Oct 7, 2026BFCL
- 86.80Oct 7, 2026
- 92.40Oct 7, 2026
- 80.20Oct 7, 2026
- 71.40Oct 7, 2026
- 94.50Oct 7, 2026
- 85.40Oct 7, 2026
- 89.70Aug 31, 2026
- livebench_language28.64Jun 17, 2026livebench_language@2025-04-07
- 40.40Oct 7, 2026
- 80.20Oct 7, 2026
- vectara_answer_rate99.90May 2, 2026Answer Rate
- vectara_avg_summary_length91.80May 2, 2026Average Summary Length (Words)
- vectara_factual_consistency93.90May 2, 2026Factual Consistency Rate
- τ²-Bench Telecom (AA run)17.54Oct 8, 2026aa_tau2
Nova Lite: common questions
Who makes Nova Lite?
Nova Lite is made by Amazon.
When was Nova Lite released?
Nova Lite was released on Dec 3, 2024, according to Artificial Analysis.
What is Nova Lite good at?
Nova Lite is behind the leaders in factuality and multimodal tasks. Too few results yet to rate reasoning, coding, agentic tasks, safety, long context, math, multilingual tasks, or instruction following.
How much does Nova Lite cost?
Nova Lite costs $0.06 per million input tokens and $0.24 per million output tokens, according to Artificial Analysis. At a mix of three input tokens to one output token, it is cheaper than 90% of the 330 priced models we track.
How many benchmarks has Nova Lite been tested on?
We track 43 results for Nova Lite on 41 benchmarks from 10 sources, 13 of them independently verified. The latest was recorded on Oct 8, 2026.
About this record
Where Nova Lite's numbers come from, and every name it appears under.
- Tracked since
- Jun 18, 2026
- Newest source mention
- Sep 2, 2026
Where the results come from
Verification: 43 scores · 13 independently verified · 16 aggregator-attributed · 14 vendor-reported. How these tiers are assigned
From 10 sources on 5 sites. Artificial Analysis supplies 16 of them; the 13 independently verified results come from 3 sites. Bars are coloured by trust tier.
- artificialanalysis.ai16
- api.llm-stats.com14
- storage.googleapis.com6
- raw.githubusercontent.com4
- huggingface.co3