RankingTerminal-Bench · 2.1

Terminal-Bench · 2.1

Data updated 22 Nov 2026

Terminal-Bench · 2.1 is published here as its own result table, version 2.1. Scores use percent, and higher values rank better. The display harness is Muse Spark1.3 evaluation methodology. Data updated 22 Nov 2026.

Bucket
Coding
Unit
percent
Direction
Higher is better
Version
2.1
Display harness
Muse Spark1.3 evaluation methodology
Board
https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology

The available records have no admitted matched comparison in the capability core. Raw results remain available below.

Compare published benchmark results with category weights →

Models

Published configurations retain their source and harness labels. Missing results remain unknown.

1–11 of 11 entries

ModelScoreHarnessEvidenceSource-recorded date
Muse Spark 1.3Meta88.8%
Reported settings & source

89tasks; each model nativecoding harness in internalframework/cloudsandbox; officialverifier; GPT owncard; reasoning max; native harness family: Meta (exact harness revision not specified)

Native harnesses differ; not a Terminus2-only comparison.

Muse Spark1.3 evaluation methodology · PDF page4 performance table · reviewed 2026-09-06

Muse Spark1.3 evaluation methodologylab self-report2026-09-06
Claude Opus 5Anthropic89.1%
Reported settings & source

Terminus2only; Gemini selfcomputed, othermodels officialboard/ArtificialAnalysis

Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06

Gemini3.8Flash Model Cardlab self-report2026-09-06
Claude Opus 5Anthropic86.7%
Reported settings & source

89tasks; each model nativecoding harness in internalframework/cloudsandbox; officialverifier; GPT owncard; reasoning max; native harness family: Anthropic (exact harness revision not specified)

Native harnesses differ; not a Terminus2-only comparison.

Muse Spark1.3 evaluation methodology · PDF page4 performance table · reviewed 2026-09-06

Muse Spark1.3 evaluation methodologylab self-report2026-09-06
Claude Sonnet 5Anthropic80.4%
Reported settings & source

Terminus2only; Gemini selfcomputed, othermodels officialboard/ArtificialAnalysis

Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06

Gemini3.8Flash Model Cardlab self-report2026-09-06
Gemini 3.7 FlashGoogle85.8%
Reported settings & source

Terminus2only; Gemini selfcomputed, othermodels officialboard/ArtificialAnalysis

Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06

Gemini3.8Flash Model Cardlab self-report2026-09-06
Gemini 3.8 FlashGoogle89.4%
Reported settings & source

Terminus2only; Gemini selfcomputed, othermodels officialboard/ArtificialAnalysis

Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06

Gemini3.8Flash Model Cardlab self-report2026-09-06
GPT-5.6 SolOpenAI88.8%
Reported settings & source

Terminus2only; Gemini selfcomputed, othermodels officialboard/ArtificialAnalysis

Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06

Gemini3.8Flash Model Cardlab self-report2026-09-06
GPT-5.6 SolOpenAI88.8%
Reported settings & source

89tasks; each model nativecoding harness in internalframework/cloudsandbox; officialverifier; GPT owncard; reasoning max; native harness family: OpenAI (exact harness revision not specified)

Native harnesses differ; not a Terminus2-only comparison.

Muse Spark1.3 evaluation methodology · PDF page4 performance table · reviewed 2026-09-06

Muse Spark1.3 evaluation methodologylab self-report2026-09-06
GPT-5.6 TerraOpenAI87.4%
Reported settings & source

Terminus2only; Gemini selfcomputed, othermodels officialboard/ArtificialAnalysis

Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06

Gemini3.8Flash Model Cardlab self-report2026-09-06
Muse Spark 1.2Meta82.9%
Reported settings & source

89tasks; each model nativecoding harness in internalframework/cloudsandbox; officialverifier; GPT owncard; reasoning xhigh; native harness family: Meta (exact harness revision not specified)

Native harnesses differ; not a Terminus2-only comparison.

Muse Spark1.3 evaluation methodology · PDF page4 performance table · reviewed 2026-09-06

Muse Spark1.3 evaluation methodologylab self-report2026-09-06
Muse Spark 1.3Meta89.2%
Reported settings & source

89tasks; each model nativecoding harness in internalframework/cloudsandbox; officialverifier; GPT owncard; reasoning xhigh; native harness family: Meta (exact harness revision not specified)

Native harnesses differ; not a Terminus2-only comparison.

Muse Spark1.3 evaluation methodology · PDF page4 performance table · reviewed 2026-09-06

Muse Spark1.3 evaluation methodologylab self-report2026-09-06