Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs Nova 2 Lite
Nova 2 Lite has enough public results to be ranked (#161); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
DeepSeekSummary
- DeepSeek-V2 (MoE-236B, May 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2 (MoE-236B, May 2024) | Nova 2 Lite | |
|---|---|---|
| Provider | DeepSeek | Amazon |
| Noometry Index | 40.3 | 39.7 |
| Released | 2024-05-07 | 2025-12-01 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 64K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $2.50 |
| Results tracked | 10 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DeepSeek-V2 (MoE-236B, May 2024): 40.4 (#139), Nova 2 Lite: 40.7 (#134)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Nova 2 Lite |
|---|---|---|
| BigCodeBench Instruct | 48.9% | — |
| LMArena Coding | — | 1385 |
| BigCodeBench Complete | 59.4% | — |
Agentic & Tool Use Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Nova 2 Lite: 24.1 (#121)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Nova 2 Lite |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 27.1% |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Nova 2 Lite: 27.5 (#118)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Nova 2 Lite |
|---|---|---|
| LMArena Hard Prompts | — | 1364 |
| BIG-Bench Hard | 78.8% | — |
| Epoch Capabilities Index | 124.77 | — |
| HellaSwag | 87.1% | — |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |
Math Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Nova 2 Lite: 37.5 (#156)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Nova 2 Lite |
|---|---|---|
| LMArena Math | — | 1359 |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Nova 2 Lite: 43.0 (#94)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Nova 2 Lite |
|---|---|---|
| Vectara Hallucination Rate | — | 5.1% |
| LMArena Expert | — | 1358 |
| ARC (AI2) Challenge | 92.2% | — |
| MMLU | 78.4% | — |
| TriviaQA | 80% | — |
Multilingual Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Nova 2 Lite: 47.1 (#153)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Nova 2 Lite |
|---|---|---|
| LMArena Non-English | — | 1337 |
| LMArena Chinese | — | 1364 |
| LMArena French | — | 1381 |
| LMArena German | — | 1343 |
| LMArena Japanese | — | 1271 |
| LMArena Korean | — | 1284 |
| LMArena Russian | — | 1343 |
| LMArena Spanish | — | 1373 |
Instruction Following Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Nova 2 Lite: 70.5 (#161)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Nova 2 Lite |
|---|---|---|
| LMArena Instruction Following | — | 1335 |
Long Context Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Nova 2 Lite: 40.6 (#150)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Nova 2 Lite |
|---|---|---|
| LMArena Longer Query | — | 1335 |
Writing & Preference Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Nova 2 Lite: 53.9 (#154)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Nova 2 Lite |
|---|---|---|
| LMArena Text | — | 1362 |
| LMArena Creative Writing | — | 1291 |
| LMArena Multi-Turn | — | 1338 |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than Nova 2 Lite?
Nova 2 Lite has enough public results to be ranked (#161); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is DeepSeek-V2 (MoE-236B, May 2024) or Nova 2 Lite better for coding?
They score almost the same on coding (40.4 vs 40.7); test both on your own repository before choosing.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and Nova 2 Lite share?
0 benchmarks have published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and Nova 2 Lite has 19.