Models / Nova 2 Lite
Nova 2 Lite
Nova 2 Lite trails most of the field on what it has been measured on; worth a look for simple, high-volume work where cost matters most. The cheapest model of similar intelligence is gpt-oss-20b, at $0.06 per million tokens against $0.85.
Results 16 Nov 2026 · 61 results · 5 sources
Test Nova 2 Lite on your prompt → It runs beside the models you could use instead, with every answer checked and costed.
- Price per million tokens
- $0.30 in · $2.50 out
Typical host on OpenRouter, 10 Nov 2026 · compare prices - Speed
- 233 tokens a second; on its test prompt the answer starts after 0.7 s, thinking time included
Artificial Analysis, on its usual API, at no reasoning; 177–233 across 4 settings - Intelligence Index
- 13.4
Artificial Analysis, at high reasoning; 8.7–13.4 across 4 settings - Spring Prompt overall
- Not ranked yet
needs our benchmarks and two groups of results - Developer
- Amazon, based in the US
Weights not published - Released
- 29 Oct 2025 (Artificial Analysis)
1,000,000 tokens of context
Where it stands among the models you could choose
Available models grouped by price, intelligence, speed and developer location. Retired models are excluded.
| Among | Intelligence Index | Spring Prompt overall | Price, blended | Speed |
|---|---|---|---|---|
| Models available today | 117th of 185Claude Opus 5.5 | – | $0.85 blended, 52nd percentilecheapest: Mistral Nemo | 11th of 65Nemotron 3.5 Super VL |
| Models priced $0.25–1 per million tokens | 33rd of 61MiMo-V2.6-Pro | – | sets this group | 4th of 20Gemini 3.5 Flash-Lite |
| Models with similar intelligence | sets this group | – | $0.85 blended, 71st percentilecheapest: gpt-oss-20b | 3rd of 10gpt-oss-20b |
| Models writing 200 or more tokens a second | 9th of 14Muse Spark 1.3 | – | $0.85 blended, 77th percentilecheapest: gpt-oss-20b | sets this group |
| Models from developers based in the US | 63rd of 92Claude Opus 5.5 | – | $0.85 blended, 38th percentilecheapest: Gemma 3 4B | 9th of 33Nemotron 3.5 Super VL |
The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.
How good is it, and for what?
Each use case ranks the available models its benchmarks measured, then those priced $0.25–1 per million tokens. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.
Product listingsTurning a sparse product feed and photos into listings that can go live
- CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is
- DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled
- SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending
- ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls
| Benchmark | Nova 2 Lite | Rank among available | Best available |
|---|---|---|---|
| Berkeley Function Calling Leaderboard (BFCL) V4BFCL: overall accuracy · reported | 27.1% | 30th of 36 | Claude Opus 4.5 77.5% |
| Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported | 16.1% | 84th of 107 | Claude Fable 5.1 91.4% |
- tau2-bench: has not measured this model.
- OpenHands Index: has not measured this model.
- Microsoft STATE-Bench: has not measured this model.
- Vending-Bench 2: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects
- APEX-Agents: has not measured this model.
- GDP.pdf: has not measured this model.
- Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge
| Benchmark | Nova 2 Lite | Rank among available | Best available |
|---|---|---|---|
| Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported | 13.4 | 117th of 185 | Claude Opus 5.5 57.6 |
| Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported | 11.6% | 122nd of 186 | Claude Opus 5.5 61.4% |
| Artificial AnalysisArtificial Analysis: GPQA Diamond · reported | 81.1% | 90th of 168 | GPT-6 Astra 96.3% |
WritingWhat people prefer in blind comparisons, and judged writing quality
| Benchmark | Nova 2 Lite | Rank among available | Best available |
|---|---|---|---|
| Arena (formerly LMArena)Arena Text: overall · reported | 1,335 | 126th of 153 | Gemini 4 Argon 1,525 |
| UGI LeaderboardUGI: writing score · reported | 23.5 | 121st of 124 | Gemini 3.8 Flash 78.6 |
Sticking to the factsSummarising without inventing things, and factual answers
| Benchmark | Nova 2 Lite | Rank among available | Best available |
|---|---|---|---|
| Vectara Hallucination LeaderboardVectara: hallucination rate · reported | 5.1% | 5th of 71 | GPT-5.4 nano 3.1% |
| Arena (formerly LMArena)Arena Text factuality: overall · reported | 1,380 | 104th of 109 | Gemini 4 Argon 1,511 |
- SimpleQA Verified (Epoch AI): has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess)
- BulletBench: has not measured this model.
Nearest alternatives
- Cheaper at similar intelligencegpt-oss-20b$0.06 blended · Intelligence Index 10.0Compare with Nova 2 Lite →
- Open weights at similar intelligencegpt-oss-20b$0.06 blended · Intelligence Index 10.0Compare with Nova 2 Lite →
Against Nova 2 Lite at $0.85 blended, Intelligence Index 13.4. "Similar intelligence" means within 4 points or better.
Where to run it
2 hosts on OpenRouter at the standard service tier, with a median of $0.85 blended per million tokens. Cheapest first.
| Host | Quantisation | Input | Output | Blended |
|---|---|---|---|---|
| Amazon Bedrock | not stated | $0.30 | $2.50 | $0.85 |
| Amazon Bedrock | not stated | $0.30 | $2.50 | $0.85 |
Prices per million tokens from OpenRouter's public endpoint list, checked 10 Nov 2026.
Against the alternatives
The models you would most likely weigh it against: the leaders of the groups above.
Scroll sideways to see every alternative.
| Nova 2 Lite | MiMo-V2.6-Pro most intelligent at $0.25–1 per million tokens | gpt-oss-20b cheapest with similar intelligence | Claude Opus 5.5 most intelligent available today | |
|---|---|---|---|---|
| Price per million tokens | $0.85 | $0.54 | $0.06 | $8.00 |
| Tokens a second | 233 | 43 | 277 | 96 |
| Intelligence Index | 13.4 | 46.3 | 10.0 | 57.6 |
| Spring Prompt overall | – | – | – | 82 |
| Rank among available models, by use case | ||||
| Product listings | – | – | – | 13th |
| Decks from an analysis | – | – | – | 7th |
| User surveys | – | – | – | 4th |
| Marketing planning | – | – | – | 9th |
| Agents and tool use | 131st of 159 | 23rd | 130th | 3rd |
| Professional work | – | – | – | 3rd |
| Reasoning and knowledge | 117th of 187 | 13th | 132nd | 1st |
| Writing | 154th of 169 | 23rd | 155th | 5th |
| Sticking to the facts | 70th of 139 | 10th | – | 3rd |
| Speed under pressure | – | – | – | – |
| Side by side → | Side by side → | Side by side → | ||
Shaded figures are better than Nova 2 Lite's. A dash means no result.
Where it has been measured
3rd fastest of the 10 models with similar intelligence. 33rd most intelligent of the 61 models priced $0.25–1 per million tokens. Among models available today, in the bottom quarter for agents and tool use, and writing.
- Arena (formerly LMArena)7 results
- Artificial Analysis38 results
- Berkeley Function Calling Leaderboard (BFCL) V48 results
- UGI Leaderboard6 results
- Vectara Hallucination Leaderboard2 results
- BulletBenchNot measured
- CatalogBenchNot measured
- DeckBenchNot measured
- ROASBenchNot measured
- SurveyBenchNot measured
- APEX-AgentsNot measured
- GDP.pdfNot measured
- Microsoft STATE-BenchNot measured
- OpenHands IndexNot measured
- Remote Labor IndexNot measured
- SimpleQA Verified (Epoch AI)Not measured
- tau2-benchNot measured
- Vending-Bench 2Not measured
Every result
61 published results from 5 sources, each in the source's own units, with the configuration that produced it.
Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 7 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Arena Text factuality: overallArena rating, higher is better | 1,380 1,374–1,386 |
162 of 182 | Nova 2 Lite | 2 Oct 2026 |
| Arena Text: business, management and financeArena rating, higher is better | 1,351 1,339–1,364 |
211 of 406 | Nova 2 Lite | 2 Oct 2026 |
| Arena Text: creative writingArena rating, higher is better | 1,269 1,254–1,284 |
274 of 411 | Nova 2 Lite | 2 Oct 2026 |
| Arena Text: expert promptsArena rating, higher is better | 1,352 1,332–1,373 |
217 of 363 | Nova 2 Lite | 2 Oct 2026 |
| Arena Text: instruction followingArena rating, higher is better | 1,327 1,317–1,337 |
225 of 413 | Nova 2 Lite | 2 Oct 2026 |
| Arena Text: overallArena rating, higher is better | 1,335 1,329–1,341 |
240 of 413 | Nova 2 Lite | 2 Oct 2026 |
| Arena Text: writing, literature and languageArena rating, higher is better | 1,298 1,287–1,310 |
261 of 412 | Nova 2 Lite | 2 Oct 2026 |
Not shown: Not an error rate: claims that cannot be checked on the web are skipped, and preference still carries most of the weight.
Artificial Analysis · reported by Artificial Analysis · 38 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better | 23.0 | 146 of 187 | Nova 2 Lite (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better | 8.7 | 343 of 413 | Nova 2 Lite (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better | 13.4 | 272 of 413 | Nova 2 Lite (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better | 11.8 | 295 of 413 | Nova 2 Lite (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better | 12.5 | 287 of 413 | Nova 2 Lite (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: GPQA Diamond% of questions, higher is better | 60.3% | 294 of 360 | Nova 2 Lite (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: GPQA Diamond% of questions, higher is better | 81.1% | 167 of 360 | Nova 2 Lite (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: GPQA Diamond% of questions, higher is better | 69.8% | 249 of 360 | Nova 2 Lite (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: GPQA Diamond% of questions, higher is better | 76.8% | 202 of 360 | Nova 2 Lite (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: Humanity's Last Exam% of questions, higher is better | 2.9% | 410 of 419 | Nova 2 Lite (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: Humanity's Last Exam% of questions, higher is better | 11.6% | 261 of 419 | Nova 2 Lite (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: Humanity's Last Exam% of questions, higher is better | 4.0% | 384 of 419 | Nova 2 Lite (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: Humanity's Last Exam% of questions, higher is better | 9.0% | 289 of 419 | Nova 2 Lite (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: IFBench% of instructions, higher is better | 40.5% | 201 of 288 | Nova 2 Lite (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: IFBench% of instructions, higher is better | 70.7% | 59 of 288 | Nova 2 Lite (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: IFBench% of instructions, higher is better | 61.2% | 101 of 288 | Nova 2 Lite (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: IFBench% of instructions, higher is better | 68.5% | 73 of 288 | Nova 2 Lite (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better | 18.7% | 368 of 407 | Nova 2 Lite (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better | 60.3% | 252 of 407 | Nova 2 Lite (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better | 54.3% | 265 of 407 | Nova 2 Lite (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better | 60.0% | 253 of 407 | Nova 2 Lite (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: Output speedtokens per second, higher is better | 233 | 14 of 137 | Nova 2 Lite (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: Output speedtokens per second, higher is better | 220 | 19 of 137 | Nova 2 Lite (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: Output speedtokens per second, higher is better | 177 | 26 of 137 | Nova 2 Lite (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: Output speedtokens per second, higher is better | 200 | 22 of 137 | Nova 2 Lite (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better | 16.1% | 150 of 188 | Nova 2 Lite (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better | 6.8% | 215 of 282 | Nova 2 Lite (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better | 16.7% | 166 of 282 | Nova 2 Lite (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better | 3.8% | 244 of 282 | Nova 2 Lite (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better | 17.4% | 161 of 282 | Nova 2 Lite (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: Time to first answer tokenseconds, lower is better | 0.73 | 19 of 137 | Nova 2 Lite (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: Time to first answer tokenseconds, lower is better | 23.6 | 88 of 137 | Nova 2 Lite (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: Time to first answer tokenseconds, lower is better | 15.5 | 76 of 137 | Nova 2 Lite (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: Time to first answer tokenseconds, lower is better | 26.7 | 93 of 137 | Nova 2 Lite (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: τ²-bench telecom% of tasks, higher is better | 62.0% | 147 of 286 | Nova 2 Lite (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: τ²-bench telecom% of tasks, higher is better | 72.8% | 120 of 286 | Nova 2 Lite (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: τ²-bench telecom% of tasks, higher is better | 71.9% | 123 of 286 | Nova 2 Lite (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: τ²-bench telecom% of tasks, higher is better | 75.7% | 111 of 286 | Nova 2 Lite (medium reasoning) | 20 Oct 2026 |
Not shown: Not your codebase or tools.
Berkeley Function Calling Leaderboard (BFCL) V4 · reported by Berkeley Function Calling Leaderboard (BFCL) V4 · 8 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| BFCL: irrelevance detection% correct, higher is better | 82.1% | 48 of 109 | Nova 2 Lite (bfcl fc) | 16 Dec 2025 |
| BFCL: memory% correct, higher is better | 2.4% | 100 of 109 | Nova 2 Lite (bfcl fc) | 16 Dec 2025 |
| BFCL: multi-turn tasks% correct, higher is better | 2.1% | 93 of 109 | Nova 2 Lite (bfcl fc) | 16 Dec 2025 |
| BFCL: overall accuracy% correct, higher is better | 27.1% | 80 of 109 | Nova 2 Lite (bfcl fc) | 16 Dec 2025 |
| BFCL: relevance detection% correct, higher is better | 75.0% | 62 of 109 | Nova 2 Lite (bfcl fc) | 16 Dec 2025 |
| BFCL: single-turn calls (curated)% correct, higher is better | 87.0% | 30 of 109 | Nova 2 Lite (bfcl fc) | 16 Dec 2025 |
| BFCL: single-turn calls (user-contributed)% correct, higher is better | 80.8% | 9 of 109 | Nova 2 Lite (bfcl fc) | 16 Dec 2025 |
| BFCL: web search% correct, higher is better | 5.0% | 63 of 109 | Nova 2 Lite (bfcl fc) | 16 Dec 2025 |
Not shown: Not general refusal or safety behaviour.
UGI Leaderboard · reported by UGI Leaderboard · 6 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| UGI: requested-length error% off the requested word count, lower is better | 46.0% | 317 of 379 | Nova 2 Lite (no reasoning) | 6 Dec 2025 |
| UGI: requested-length error% off the requested word count, lower is better | 45.0% | 315 of 379 | Nova 2 Lite (thinking reasoning) | 6 Dec 2025 |
| UGI: style adherencescore from 0 to 1, higher is better | 0.35 | 199 of 379 | Nova 2 Lite (no reasoning) | 6 Dec 2025 |
| UGI: style adherencescore from 0 to 1, higher is better | 0.34 | 233 of 379 | Nova 2 Lite (thinking reasoning) | 6 Dec 2025 |
| UGI: writing scorescore out of 100, higher is better | 23.5 | 326 of 379 | Nova 2 Lite (no reasoning) | 6 Dec 2025 |
| UGI: writing scorescore out of 100, higher is better | 23.4 | 327 of 379 | Nova 2 Lite (thinking reasoning) | 6 Dec 2025 |
Not shown: Not other format limits such as character counts or bullet counts.
Vectara Hallucination Leaderboard · reported by Vectara Hallucination Leaderboard · 2 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Vectara: answer rate% of documents, higher is better | 99.6% | 48 of 108 | Nova 2 Lite | 22 Sep 2026 |
| Vectara: hallucination rate% of summaries, lower is better | 5.1% | 10 of 108 | Nova 2 Lite | 22 Sep 2026 |
Not shown: Not a quality score: a low rate usually means content filters were triggered, and hallucination rates are measured on answered documents only.
Will Nova 2 Lite work for your product?
Benchmarks aren't your task. Paste the prompt your product uses and run it beside the models you could use instead, with every answer checked and costed.
New here? Your email starts a free trial. No credit card needed.