RankingTerminal-Bench 1.0 · 1.0
Terminal-Bench 1.0 · 1.0
- Bucket
- Coding
- Unit
- percent
- Direction
- Higher is better
- Version
- 1.0
- Display harness
- Amazon Nova 2 technical report
- Board
- https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf
Compare published benchmark results with category weights →
Models
| Model | Score | Harness | Evidence | Source-recorded date |
|---|---|---|---|---|
| GPT-5.1OpenAI | 53.8%Reported settings & sourceNova2 internal agentic scaffold; scaled inference explicitly separate. Comparator setups from cited provider report. First-party reported result; comparator results retain the source evaluation setup. Amazon Nova 2 technical report · Table4 · reviewed 2026-09-06 | Amazon Nova 2 technical report | lab self-report | 2026-09-06 |
| Claude Sonnet 4.5Anthropic | 51%Reported settings & sourceNova2 internal agentic scaffold; scaled inference explicitly separate. Comparator setups from cited provider report. First-party reported result; comparator results retain the source evaluation setup. Amazon Nova 2 technical report · Table4 · reviewed 2026-09-06 | Amazon Nova 2 technical report | lab self-report | 2026-09-06 |
| Claude Haiku 4.5Anthropic | 41.8%Reported settings & sourceNova2 internal agentic scaffold; scaled inference explicitly separate. Comparator setups from cited provider report. First-party reported result; comparator results retain the source evaluation setup. Amazon Nova 2 technical report · Table4 · reviewed 2026-09-06 | Amazon Nova 2 technical report | lab self-report | 2026-09-06 |
| Amazon Nova 2 Pro PreviewAmazon | 41.3%Reported settings & sourceNova2 internal agentic scaffold; scaled inference explicitly separate. Comparator setups from cited provider report. First-party reported result; comparator results retain the source evaluation setup. Amazon Nova 2 technical report · Table4 · reviewed 2026-09-06 | Amazon Nova 2 technical report | lab self-report | 2026-09-06 |
| GPT-5OpenAI | 41.3%Reported settings & sourceNova2 internal agentic scaffold; scaled inference explicitly separate. Comparator setups from cited provider report. First-party reported result; comparator results retain the source evaluation setup. Amazon Nova 2 technical report · Table4 · reviewed 2026-09-06 | Amazon Nova 2 technical report | lab self-report | 2026-09-06 |
| Amazon Nova 2 LiteAmazon | 32.5%Reported settings & sourceNova2 internal agentic scaffold; scaled inference explicitly separate. Comparator setups from cited provider report. First-party reported result; comparator results retain the source evaluation setup. Amazon Nova 2 technical report · Table4 · reviewed 2026-09-06 | Amazon Nova 2 technical report | lab self-report | 2026-09-06 |
| GPT-5 MiniOpenAI | 30.8%Reported settings & sourceNova2 internal agentic scaffold; scaled inference explicitly separate. Comparator setups from cited provider report. First-party reported result; comparator results retain the source evaluation setup. Amazon Nova 2 technical report · Table4 · reviewed 2026-09-06 | Amazon Nova 2 technical report | lab self-report | 2026-09-06 |
| Gemini 2.5 ProGoogle | 25.3%Reported settings & sourceNova2 internal agentic scaffold; scaled inference explicitly separate. Comparator setups from cited provider report. First-party reported result; comparator results retain the source evaluation setup. Amazon Nova 2 technical report · Table4 · reviewed 2026-09-06 | Amazon Nova 2 technical report | lab self-report | 2026-09-06 |
| Gemini 2.5 FlashGoogle | 16.8%Reported settings & sourceNova2 internal agentic scaffold; scaled inference explicitly separate. Comparator setups from cited provider report. First-party reported result; comparator results retain the source evaluation setup. Amazon Nova 2 technical report · Table4 · reviewed 2026-09-06 | Amazon Nova 2 technical report | lab self-report | 2026-09-06 |
| Amazon Nova PremierAmazon | 11.3%Reported settings & sourceNova2 internal agentic scaffold; scaled inference explicitly separate. Comparator setups from cited provider report. First-party reported result; comparator results retain the source evaluation setup. Amazon Nova 2 technical report · Table4 · reviewed 2026-09-06 | Amazon Nova 2 technical report | lab self-report | 2026-09-06 |