Model comparison

Nova 2.0 Pro Preview vs Qwen2.5-Coder (1.5B)

Nova 2.0 Pro Preview has enough public results to be ranked (#244); Qwen2.5-Coder (1.5B) does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

Summary

  • Qwen2.5-Coder (1.5B) has downloadable open weights; the other is API-only.

Side by side

Nova 2.0 Pro Preview and Qwen2.5-Coder (1.5B) specifications
Nova 2.0 Pro PreviewQwen2.5-Coder (1.5B)
ProviderAmazonAlibaba (Qwen)
Noometry Index33.4—
Released2025-12-022024-09-18
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked36

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Not comparable

Nova 2.0 Pro Preview: 40.8 (#133), Qwen2.5-Coder (1.5B): —

Coding benchmarks
BenchmarkNova 2.0 Pro PreviewQwen2.5-Coder (1.5B)
SciCode42.7%—

Agentic & Tool Use Not comparable

Nova 2.0 Pro Preview: 21.9 (#136), Qwen2.5-Coder (1.5B): —

Agentic & Tool Use benchmarks
BenchmarkNova 2.0 Pro PreviewQwen2.5-Coder (1.5B)
GDP.pdf2%—

Reasoning Not comparable

Nova 2.0 Pro Preview: 22.4 (#194), Qwen2.5-Coder (1.5B): —

Reasoning benchmarks
BenchmarkNova 2.0 Pro PreviewQwen2.5-Coder (1.5B)
CritPt0%—
Epoch Capabilities Index—113.14
HellaSwag—76.8%
WinoGrande—72.9%

Math Not comparable

Nova 2.0 Pro Preview: —, Qwen2.5-Coder (1.5B): —

Math benchmarks
BenchmarkNova 2.0 Pro PreviewQwen2.5-Coder (1.5B)
GSM8K—86.7%

Knowledge Not comparable

Nova 2.0 Pro Preview: —, Qwen2.5-Coder (1.5B): —

Knowledge benchmarks
BenchmarkNova 2.0 Pro PreviewQwen2.5-Coder (1.5B)
ARC (AI2) Challenge—60.9%
MMLU—68%

Frequently asked questions

Is Nova 2.0 Pro Preview better than Qwen2.5-Coder (1.5B)?

Nova 2.0 Pro Preview has enough public results to be ranked (#244); Qwen2.5-Coder (1.5B) does not yet, so treat this comparison as directional.

How many benchmarks do Nova 2.0 Pro Preview and Qwen2.5-Coder (1.5B) share?

0 benchmarks have published results for both models. Nova 2.0 Pro Preview has 3 scored results on Noometry and Qwen2.5-Coder (1.5B) has 6.

Related comparisons

Go deeper