RankingTerminal-Bench 1.0 · 1.0

Terminal-Bench 1.0 · 1.0

Data updated 12 Sept 2026

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

ModelScoreHarnessEvidenceSource-recorded date
GPT-5.1OpenAI53.8%
Reported settings & source

Nova2 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 reportlab self-report2026-09-06
Claude Sonnet 4.5Anthropic51%
Reported settings & source

Nova2 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 reportlab self-report2026-09-06
Claude Haiku 4.5Anthropic41.8%
Reported settings & source

Nova2 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 reportlab self-report2026-09-06
Amazon Nova 2 Pro PreviewAmazon41.3%
Reported settings & source

Nova2 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 reportlab self-report2026-09-06
GPT-5OpenAI41.3%
Reported settings & source

Nova2 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 reportlab self-report2026-09-06
Amazon Nova 2 LiteAmazon32.5%
Reported settings & source

Nova2 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 reportlab self-report2026-09-06
GPT-5 MiniOpenAI30.8%
Reported settings & source

Nova2 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 reportlab self-report2026-09-06
Gemini 2.5 ProGoogle25.3%
Reported settings & source

Nova2 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 reportlab self-report2026-09-06
Gemini 2.5 FlashGoogle16.8%
Reported settings & source

Nova2 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 reportlab self-report2026-09-06
Amazon Nova PremierAmazon11.3%
Reported settings & source

Nova2 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 reportlab self-report2026-09-06