Nova Pro
Nova Pro 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
$0.80input$3.20outputper million tokens
From Artificial Analysis · All prices
Evidence
43results on41benchmarks
- 13 independently verified
- 16 aggregator
- 14 vendor-reported
From 10 sources · latest Oct 7, 2026 · How verification works
Research
1 paper reference Nova ProNova Pro 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.
32.0% behind the leader3 of 4 ranked benchmarks measured
- 5.10May 2, 2026
- AA-Omniscience · Non-hallucination22.29Oct 7, 2026omniscienceNonHallucination
- AA-Omniscience · Accuracy16.87Oct 7, 2026omniscienceAccuracy
46.2% behind the leader2 of 6 ranked benchmarks measured
- 61.70Oct 6, 2026
- MMMU-Pro44.34Oct 7, 2026aa_mmmu_pro
0 of 6 ranked benchmarks measured
- 0.00Oct 7, 2026
- GPQA Diamond49.90Oct 7, 2026gpqa
- Humanity's Last Exam3.19Oct 7, 2026aa_hle
Show 1 more reasoning resultHide 1 reasoning result
- GPQA Diamond46.90Oct 6, 2026GPQA
0 of 10 ranked benchmarks measured
- LiveBench · Coding39.06Jun 17, 2026livebench_coding@2025-04-07
- Terminal-Bench Hard6.06Oct 7, 2026aa_terminalbench_hard
- SciCode20.83Sep 4, 2026aa_scicode
0 of 7 ranked benchmarks measured
- 0.00Jun 15, 2026
0 of 3 ranked benchmarks measured
- 21.00Oct 7, 2026
0 of 3 ranked benchmarks measured
- LiveBench · Instruction Following70.13Jun 17, 2026livebench_instruction_following@2025-04-07
- IFBench38.10Oct 7, 2026aa_ifbench
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- livebench_language41.09Jun 17, 2026livebench_language@2025-04-07
- 96.00May 10, 2026
- 40.52May 10, 2026
- 79.13May 10, 2026
- 75.84May 10, 2026
- 82.14May 10, 2026
Show 21 more resultsHide 21 results
- 4.68Jun 18, 2026
- AA Intelligence6.96Oct 7, 2026aa_intelligence_index
- -47.73Oct 7, 2026
- ARC-Challenge94.80Oct 6, 2026ARC-C
- 10.98Jun 18, 2026
- 86.90Oct 6, 2026
- BFCLv468.40Oct 6, 2026BFCL
- 89.20Oct 6, 2026
- 93.50Oct 6, 2026
- 85.40Oct 6, 2026
- 72.10Oct 6, 2026
- 87.00May 10, 2026
- 94.80Oct 6, 2026
- 89.00Oct 6, 2026
- 92.10Aug 31, 2026
- 41.60Oct 6, 2026
- 81.50Oct 6, 2026
- vectara_answer_rate99.30May 2, 2026Answer Rate
- vectara_avg_summary_length66.20May 2, 2026Average Summary Length (Words)
- vectara_factual_consistency94.90May 2, 2026Factual Consistency Rate
- τ²-Bench Telecom (AA run)14.04Oct 7, 2026aa_tau2
Nova Pro: common questions
Who makes Nova Pro?
Nova Pro is made by Amazon.
When was Nova Pro released?
Nova Pro was released on Dec 3, 2024, according to Artificial Analysis.
What is Nova Pro good at?
Nova Pro 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 Pro cost?
Nova Pro costs $0.80 per million input tokens and $3.20 per million output tokens, according to Artificial Analysis. At a mix of three input tokens to one output token, it costs more than 65% of the 328 priced models we track.
How many benchmarks has Nova Pro been tested on?
We track 43 results for Nova Pro on 41 benchmarks from 10 sources, 13 of them independently verified. The latest was recorded on Oct 7, 2026.
About this record
Where Nova Pro's numbers come from, and every name it appears under.
- Tracked since
- Apr 27, 2026
- Newest source mention
- Jul 7, 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