Nova 2.0 Pro Preview
Nova 2.0 Pro Preview is capable in instruction following; and behind the leaders in long context, multimodal tasks, and coding. Too few results yet to rate reasoning, 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 Reasoning, Agentic, Safety, Math, Multilingual or Factuality.
Price
$1.25input$10.00outputper million tokens
From Artificial Analysis · All prices
Evidence
49results on18benchmarks
- 49 aggregator
From 1 source · latest Oct 8, 2026 · How verification works
Nova 2.0 Pro Preview benchmark results
49 results on 18 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
21.3% behind the leader1 of 3 ranked benchmarks measured
- IFBench79.05Oct 8, 2026aa_ifbench
29.7% behind the leader1 of 3 ranked benchmarks measured
- 64.00Oct 8, 2026
34.6% behind the leader1 of 6 ranked benchmarks measured
- MMMU-Pro64.51Oct 8, 2026aa_mmmu_pro
Show 1 more multimodal resultHide 1 multimodal result
- MMMU-Pro62.72Oct 8, 2026aa_mmmu_pro
35.5% behind the leader3 of 10 ranked benchmarks measured
- SciCode42.71Sep 4, 2026aa_scicode
- Terminal-Bench Hard24.24Oct 8, 2026aa_terminalbench_hard
- Terminal-Bench 2.129.59Oct 8, 2026terminalbenchV21
Show 6 more coding resultsHide 6 coding results
- SciCode38.66Sep 4, 2026aa_scicode
- SciCode28.13Sep 4, 2026aa_scicode
- Terminal-Bench 2.119.48Oct 8, 2026terminalbenchV21
- Terminal-Bench 2.117.23Oct 8, 2026terminalbenchV21
- Terminal-Bench Hard17.42Oct 8, 2026aa_terminalbench_hard
- Terminal-Bench Hard16.67Oct 8, 2026aa_terminalbench_hard
0 of 6 ranked benchmarks measured
- 0.00Oct 8, 2026
- GPQA Diamond75.05Oct 8, 2026gpqa
- Humanity's Last Exam5.19Oct 8, 2026aa_hle
Show 4 more reasoning resultsHide 4 reasoning results
- GPQA Diamond63.64Oct 8, 2026gpqa
- GPQA Diamond78.48Oct 8, 2026gpqa
- Humanity's Last Exam3.94Oct 8, 2026aa_hle
- Humanity's Last Exam9.41Oct 8, 2026aa_hle
0 of 7 ranked benchmarks measured
- 0.00Oct 8, 2026
- τ-Bench V3 · Banking9.07Aug 10, 2026tauBanking
- τ-Bench V3 · Banking6.80Aug 10, 2026tauBanking
Show 1 more agentic resultHide 1 agentic result
- τ-Bench V3 · Banking7.63Aug 10, 2026tauBanking
0 of 4 ranked benchmarks measured
- AA-Omniscience · Accuracy22.00Oct 8, 2026omniscienceAccuracy
- AA-Omniscience · Non-hallucination12.14Oct 8, 2026omniscienceNonHallucination
- AA-Omniscience · Accuracy16.92Oct 8, 2026omniscienceAccuracy
Show 3 more factuality resultsHide 3 factuality results
- AA-Omniscience · Accuracy21.97Oct 8, 2026omniscienceAccuracy
- AA-Omniscience · Non-hallucination20.06Oct 8, 2026omniscienceNonHallucination
- AA-Omniscience · Non-hallucination8.99Oct 8, 2026omniscienceNonHallucination
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- τ²-Bench Telecom (AA run)90.64Oct 8, 2026aa_tau2
- AA Intelligence12.78Oct 8, 2026aa_intelligence_index
- -46.53Oct 8, 2026
- τ²-Bench Telecom (AA run)71.64Oct 8, 2026aa_tau2
- AA Intelligence9.96Oct 8, 2026aa_intelligence_index
- -49.50Oct 8, 2026
Show 9 more resultsHide 9 results
- 6.42Aug 10, 2026
- 2.85Aug 10, 2026
- 7.00Aug 10, 2026
- AA Intelligence14.16Oct 8, 2026aa_intelligence_index
- -49.05Oct 8, 2026
- Artificial Analysis Coding Index25.87Sep 9, 2026aa_coding_index
- Artificial Analysis Coding Index20.86Sep 9, 2026aa_coding_index
- Artificial Analysis Coding Index33.96Sep 9, 2026aa_coding_index
- τ²-Bench Telecom (AA run)92.69Oct 8, 2026aa_tau2
Nova 2.0 Pro Preview: common questions
Who makes Nova 2.0 Pro Preview?
Nova 2.0 Pro Preview is made by Amazon.
When was Nova 2.0 Pro Preview released?
Nova 2.0 Pro Preview was released on Nov 27, 2025, according to Artificial Analysis.
What is Nova 2.0 Pro Preview good at?
Nova 2.0 Pro Preview is capable in instruction following; and behind the leaders in long context, multimodal tasks, and coding. Too few results yet to rate reasoning, agentic tasks, safety, math, multilingual tasks, or factuality.
How much does Nova 2.0 Pro Preview cost?
Nova 2.0 Pro Preview costs $1.25 per million input tokens and $10.00 per million output tokens, according to Artificial Analysis. At a mix of three input tokens to one output token, it costs more than 78% of the 331 priced models we track.
How many benchmarks has Nova 2.0 Pro Preview been tested on?
We track 49 results for Nova 2.0 Pro Preview on 18 benchmarks from 1 source. The latest was recorded on Oct 8, 2026.
About this record
Where Nova 2.0 Pro Preview's numbers come from, and every name it appears under.
- Tracked since
- May 2, 2026
- Newest source mention
- Jul 20, 2026
Where the results come from
Verification: 49 scores · 0 independently verified · 49 aggregator-attributed. How these tiers are assigned
From 1 source on 1 site. Artificial Analysis supplies all of them. Bars are coloured by trust tier.
- artificialanalysis.ai49
Also known as
How our sources name Nova 2.0 Pro Preview at each reasoning setting.
| Setting | Short form | API id |
|---|---|---|
| low | Nova 2.0 Pro Preview (low) | nova-2-0-pro-reasoning-low |
| medium | nova 2.0 pro preview (medium) nova 2.0 pro preview (medium) (reasoning) Nova 2.0 Pro Preview (medium) (Non-Reasoning) | nova-2-0-pro-reasoning-medium |