Model comparison
DeepSeek-R1 vs Nova 2 Lite
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 39.7 on the Noometry Index.
Last verified . 18 shared benchmarks.
DeepSeekSummary
- They share 18 benchmarks with published results for both. DeepSeek-R1 scores higher in 8 categories and Nova 2 Lite in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Nova 2 Lite leads 27.5 to 18.6.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 11.3% for DeepSeek-R1 and 5.1% for Nova 2 Lite.
- Nova 2 Lite is cheaper at $0.30 / $2.50 per million input/output tokens, against $0.50 / $2.15 for DeepSeek-R1.
- Nova 2 Lite accepts more context: 1M tokens versus 164K.
Side by side
| DeepSeek-R1 | Nova 2 Lite | |
|---|---|---|
| Provider | DeepSeek | Amazon |
| Noometry Index | 42.3 | 39.7 |
| Released | 2025-01-20 | 2025-12-01 |
| Weights | Proprietary | Proprietary |
| Context window | 164K | 1M |
| Max output | 64K | 64K |
| Input $ / M tokens | $0.50 | $0.30 |
| Output $ / M tokens | $2.15 | $2.50 |
| Results tracked | 52 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-R1 leads
DeepSeek-R1: 46.3 (#68), Nova 2 Lite: 40.7 (#134)
| Benchmark | DeepSeek-R1 | Nova 2 Lite |
|---|---|---|
| LMArena Coding | 1427 | 1385 |
| Aider Polyglot | 71.4% | — |
| SciCode | 35.7% | — |
| WeirdML | 41.6% | — |
| LiveBench Coding | 66.7% | — |
| ALE-Bench | 804.12 | — |
| AlgoTune | 1.7 | — |
Agentic & Tool Use DeepSeek-R1 leads
DeepSeek-R1: 30.7 (#75), Nova 2 Lite: 24.1 (#121)
| Benchmark | DeepSeek-R1 | Nova 2 Lite |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 27.1% |
| DeepResearch Bench | 35.1% | — |
| BALROG | 34.9% | — |
| METR Time Horizons | 53.8% | — |
Reasoning Nova 2 Lite leads
DeepSeek-R1: 18.6 (#278), Nova 2 Lite: 27.5 (#118)
| Benchmark | DeepSeek-R1 | Nova 2 Lite |
|---|---|---|
| LMArena Hard Prompts | 1416 | 1364 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 40.8% | — |
| Kagi LLM Benchmark | 69.4% | — |
| ARC-AGI-1 | 21.2% | — |
| CritPt | 1.1% | — |
| LiveBench Reasoning | 83.2% | — |
| LiveBench Data Analysis | 69.8% | — |
| Epoch Capabilities Index | 141.29 | — |
| ForecastBench | 60 | — |
| LiveBench | 71.6% | — |
Math DeepSeek-R1 leads
DeepSeek-R1: 43.8 (#79), Nova 2 Lite: 37.5 (#156)
| Benchmark | DeepSeek-R1 | Nova 2 Lite |
|---|---|---|
| LMArena Math | 1400 | 1359 |
| OTIS Mock AIME 2024-2025 | 66.4% | — |
| Omni-MATH | 42.4% | — |
| LiveBench Math | 80.7% | — |
| MATH Level 5 | 96.6% | — |
Knowledge DeepSeek-R1 leads
DeepSeek-R1: 44.5 (#87), Nova 2 Lite: 43.0 (#94)
| Benchmark | DeepSeek-R1 | Nova 2 Lite |
|---|---|---|
| Vectara Hallucination Rate | 11.3% | 5.1% |
| LMArena Expert | 1394 | 1358 |
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.3% | — |
| Confabulations | 12.7% | — |
| GPQA (HELM) | 66.6% | — |
Multilingual DeepSeek-R1 leads
DeepSeek-R1: 52.4 (#85), Nova 2 Lite: 47.1 (#153)
| Benchmark | DeepSeek-R1 | Nova 2 Lite |
|---|---|---|
| LMArena Non-English | 1412 | 1337 |
| LMArena Chinese | 1442 | 1364 |
| LMArena French | 1417 | 1381 |
| LMArena German | 1404 | 1343 |
| LMArena Japanese | 1391 | 1271 |
| LMArena Korean | 1360 | 1284 |
| LMArena Russian | 1423 | 1343 |
| LMArena Spanish | 1411 | 1373 |
Instruction Following DeepSeek-R1 leads
DeepSeek-R1: 72.0 (#143), Nova 2 Lite: 70.5 (#161)
| Benchmark | DeepSeek-R1 | Nova 2 Lite |
|---|---|---|
| LMArena Instruction Following | 1382 | 1335 |
| LiveBench Instruction Following | 80.5% | — |
| IFEval | 78.4% | — |
Long Context DeepSeek-R1 leads
DeepSeek-R1: 45.4 (#36), Nova 2 Lite: 40.6 (#150)
| Benchmark | DeepSeek-R1 | Nova 2 Lite |
|---|---|---|
| LMArena Longer Query | 1391 | 1335 |
| Fiction.LiveBench | 75% | — |
Writing & Preference DeepSeek-R1 leads
DeepSeek-R1: 61.4 (#88), Nova 2 Lite: 53.9 (#154)
| Benchmark | DeepSeek-R1 | Nova 2 Lite |
|---|---|---|
| LMArena Text | 1428 | 1362 |
| LMArena Creative Writing | 1405 | 1291 |
| LMArena Multi-Turn | 1405 | 1338 |
| Short-Story Creative Writing | 83% | — |
| EQ-Bench Creative Writing | 1500 | — |
| WildBench | 82.8% | — |
| LiveBench Language | 48.5% | — |
Frequently asked questions
Is DeepSeek-R1 better than Nova 2 Lite?
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 39.7 on the Noometry Index.
Which is cheaper, DeepSeek-R1 or Nova 2 Lite?
Nova 2 Lite is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; DeepSeek-R1 lists at $0.50 and $2.15.
Is DeepSeek-R1 or Nova 2 Lite better for coding?
DeepSeek-R1 scores higher on coding benchmarks: 46.3 versus 40.7 in the Noometry coding category.
Which has the bigger context window?
Nova 2 Lite does, with 1M tokens against 164K.
How many benchmarks do DeepSeek-R1 and Nova 2 Lite share?
18 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and Nova 2 Lite has 19.