Model comparison
Nova 2 Lite vs Qwen3.5 122B-A10B
Qwen3.5 122B-A10B is the stronger model overall, scoring 41.6 to 39.0 on the Noometry Index.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Nova 2 Lite scores higher in 3 categories and Qwen3.5 122B-A10B in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.5 122B-A10B leads 60.2 to 54.1.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 5.1% for Nova 2 Lite and 11.2% for Qwen3.5 122B-A10B.
- Nova 2 Lite is cheaper at $0.30 / $2.50 per million input/output tokens, against $0.40 / $3.20 for Qwen3.5 122B-A10B.
- Nova 2 Lite accepts more context: 1M tokens versus 262K.
- Qwen3.5 122B-A10B has downloadable open weights; the other is API-only.
Side by side
| Nova 2 Lite | Qwen3.5 122B-A10B | |
|---|---|---|
| Provider | Amazon | Alibaba (Qwen) |
| Noometry Index | 39.0 | 41.6 |
| Released | 2025-12-01 | 2026-02-23 |
| Weights | Proprietary | Open |
| Context window | 1M | 262K |
| Max output | 64K | 66K |
| Input $ / M tokens | $0.30 | $0.40 |
| Output $ / M tokens | $2.50 | $3.20 |
| Results tracked | 19 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nova 2 Lite leads
Nova 2 Lite: 40.1 (#131), Qwen3.5 122B-A10B: 38.8 (#155)
| Benchmark | Nova 2 Lite | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Coding | 1386 | 1436 |
| LMArena WebDev | — | 1360 |
| SciCode | — | 35.6% |
Agentic & Tool Use Not comparable
Nova 2 Lite: 23.9 (#114), Qwen3.5 122B-A10B: —
| Benchmark | Nova 2 Lite | Qwen3.5 122B-A10B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | — |
Reasoning Too close to call
Nova 2 Lite: 26.4 (#120), Qwen3.5 122B-A10B: 26.4 (#121)
| Benchmark | Nova 2 Lite | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Hard Prompts | 1364 | 1421 |
| NYT Connections (extended) | — | 51.7% |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 51.2% |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 84.3% |
| LMCA | — | 32.2% |
Math Qwen3.5 122B-A10B leads
Nova 2 Lite: 34.8 (#154), Qwen3.5 122B-A10B: 36.4 (#114)
| Benchmark | Nova 2 Lite | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Math | 1359 | 1432 |
Knowledge Nova 2 Lite leads
Nova 2 Lite: 42.5 (#88), Qwen3.5 122B-A10B: 38.2 (#138)
| Benchmark | Nova 2 Lite | Qwen3.5 122B-A10B |
|---|---|---|
| Vectara Hallucination Rate | 5.1% | 11.2% |
| LMArena Expert | 1360 | 1431 |
Multimodal Not comparable
Nova 2 Lite: —, Qwen3.5 122B-A10B: 39.0 (#52)
| Benchmark | Nova 2 Lite | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Vision | — | 1245 |
Multilingual Qwen3.5 122B-A10B leads
Nova 2 Lite: 47.3 (#148), Qwen3.5 122B-A10B: 51.8 (#101)
| Benchmark | Nova 2 Lite | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Non-English | 1337 | 1400 |
| LMArena Chinese | 1364 | 1462 |
| LMArena French | 1381 | 1442 |
| LMArena German | 1343 | 1425 |
| LMArena Japanese | 1273 | 1364 |
| LMArena Korean | 1284 | 1353 |
| LMArena Russian | 1343 | 1400 |
| LMArena Spanish | 1372 | 1423 |
Instruction Following Qwen3.5 122B-A10B leads
Nova 2 Lite: 70.7 (#156), Qwen3.5 122B-A10B: 74.0 (#109)
| Benchmark | Nova 2 Lite | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Instruction Following | 1335 | 1399 |
Long Context Qwen3.5 122B-A10B leads
Nova 2 Lite: 40.6 (#145), Qwen3.5 122B-A10B: 43.0 (#105)
| Benchmark | Nova 2 Lite | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Longer Query | 1335 | 1410 |
Writing & Preference Qwen3.5 122B-A10B leads
Nova 2 Lite: 54.1 (#150), Qwen3.5 122B-A10B: 60.2 (#98)
| Benchmark | Nova 2 Lite | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Text | 1362 | 1417 |
| LMArena Creative Writing | 1291 | 1369 |
| LMArena Multi-Turn | 1338 | 1416 |
Frequently asked questions
Is Nova 2 Lite better than Qwen3.5 122B-A10B?
Qwen3.5 122B-A10B is the stronger model overall, scoring 41.6 to 39.0 on the Noometry Index.
Which is cheaper, Nova 2 Lite or Qwen3.5 122B-A10B?
Nova 2 Lite is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Qwen3.5 122B-A10B lists at $0.40 and $3.20.
Is Nova 2 Lite or Qwen3.5 122B-A10B better for coding?
Nova 2 Lite scores higher on coding benchmarks: 40.1 versus 38.8 in the Noometry coding category.
Which has the bigger context window?
Nova 2 Lite does, with 1M tokens against 262K.
How many benchmarks do Nova 2 Lite and Qwen3.5 122B-A10B share?
18 benchmarks have published results for both models. Nova 2 Lite has 19 scored results on Noometry and Qwen3.5 122B-A10B has 27.