# Nova 2 Lite vs Qwen1.5-72B

> Nova 2 Lite is the stronger model overall, scoring 39.7 to 30.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/nova-2-lite-vs-qwen1-5-72b
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Nova 2 Lite scores higher in 8 categories and Qwen1.5-72B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nova 2 Lite leads 43.0 to 11.5.
- Qwen1.5-72B has downloadable open weights; the other is API-only.

## Snapshot

| | Nova 2 Lite | Qwen1.5-72B |
|---|---|---|
| Provider | Amazon | Alibaba (Qwen) |
| Noometry Index | 39.7 | 30.8 |
| Rank | 161 | 285 |
| Context | 1M | — |
| Input $/M | $0.30 | — |
| Output $/M | $2.50 | — |
| Weights | Proprietary | Open |

## Coding

- Nova 2 Lite: 40.7 (#134)
- Qwen1.5-72B: 31.9 (#277)

| Benchmark | Nova 2 Lite | Qwen1.5-72B |
|---|---|---|
| LMArena Coding | 1385 | 1165 |
| BigCodeBench Instruct | — | 33.2% |
| BigCodeBench Complete | — | 40.3% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |

## Agentic & Tool Use

- Nova 2 Lite: 24.1 (#121)
- Qwen1.5-72B: —

| Benchmark | Nova 2 Lite | Qwen1.5-72B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | — |

## Reasoning

- Nova 2 Lite: 27.5 (#118)
- Qwen1.5-72B: 22.2 (#203)

| Benchmark | Nova 2 Lite | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1364 | 1148 |

## Math

- Nova 2 Lite: 37.5 (#156)
- Qwen1.5-72B: 33.2 (#205)

| Benchmark | Nova 2 Lite | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1359 | 1164 |

## Knowledge

- Nova 2 Lite: 43.0 (#94)
- Qwen1.5-72B: 11.5 (#300)

| Benchmark | Nova 2 Lite | Qwen1.5-72B |
|---|---|---|
| LMArena Expert | 1358 | 1136 |
| GPQA Diamond | — | 28.8% |
| Vectara Hallucination Rate | 5.1% | — |

## Multilingual

- Nova 2 Lite: 47.1 (#153)
- Qwen1.5-72B: 33.2 (#253)

| Benchmark | Nova 2 Lite | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1337 | 1135 |
| LMArena Chinese | 1364 | 1186 |
| LMArena French | 1381 | 1159 |
| LMArena German | 1343 | 1084 |
| LMArena Japanese | 1271 | 1061 |
| LMArena Korean | 1284 | 1050 |
| LMArena Russian | 1343 | 1104 |
| LMArena Spanish | 1373 | 1110 |

## Instruction Following

- Nova 2 Lite: 70.5 (#161)
- Qwen1.5-72B: 59.3 (#256)

| Benchmark | Nova 2 Lite | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1335 | 1141 |

## Long Context

- Nova 2 Lite: 40.6 (#150)
- Qwen1.5-72B: 35.1 (#243)

| Benchmark | Nova 2 Lite | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1335 | 1157 |

## Writing & Preference

- Nova 2 Lite: 53.9 (#154)
- Qwen1.5-72B: 37.3 (#258)

| Benchmark | Nova 2 Lite | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1362 | 1166 |
| LMArena Creative Writing | 1291 | 1137 |
| LMArena Multi-Turn | 1338 | 1160 |

## FAQ

### Is Nova 2 Lite better than Qwen1.5-72B?

Nova 2 Lite is the stronger model overall, scoring 39.7 to 30.8 on the Noometry Index.

### Is Nova 2 Lite or Qwen1.5-72B better for coding?

Nova 2 Lite scores higher on coding benchmarks: 40.7 versus 31.9 in the Noometry coding category.

### How many benchmarks do Nova 2 Lite and Qwen1.5-72B share?

17 benchmarks have published results for both models. Nova 2 Lite has 19 scored results on Noometry and Qwen1.5-72B has 22.