RankingTerminal-Bench · 2.1
Terminal-Bench · 2.1
- 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
Compare published benchmark results with category weights →
Models
| Model | Score | Harness | Evidence | Source-recorded date |
|---|---|---|---|---|
| Muse Spark 1.3Meta | 88.8%Reported settings & source89tasks; 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 methodology | lab self-report | 2026-09-06 |
| Claude Opus 5Anthropic | 89.1%Reported settings & sourceTerminus2only; Gemini selfcomputed, othermodels officialboard/ArtificialAnalysis Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06 | Gemini3.8Flash Model Card | lab self-report | 2026-09-06 |
| Claude Opus 5Anthropic | 86.7%Reported settings & source89tasks; 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 methodology | lab self-report | 2026-09-06 |
| Claude Sonnet 5Anthropic | 80.4%Reported settings & sourceTerminus2only; Gemini selfcomputed, othermodels officialboard/ArtificialAnalysis Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06 | Gemini3.8Flash Model Card | lab self-report | 2026-09-06 |
| Gemini 3.7 FlashGoogle | 85.8%Reported settings & sourceTerminus2only; Gemini selfcomputed, othermodels officialboard/ArtificialAnalysis Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06 | Gemini3.8Flash Model Card | lab self-report | 2026-09-06 |
| Gemini 3.8 FlashGoogle | 89.4%Reported settings & sourceTerminus2only; Gemini selfcomputed, othermodels officialboard/ArtificialAnalysis Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06 | Gemini3.8Flash Model Card | lab self-report | 2026-09-06 |
| GPT-5.6 SolOpenAI | 88.8%Reported settings & sourceTerminus2only; Gemini selfcomputed, othermodels officialboard/ArtificialAnalysis Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06 | Gemini3.8Flash Model Card | lab self-report | 2026-09-06 |
| GPT-5.6 SolOpenAI | 88.8%Reported settings & source89tasks; 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 methodology | lab self-report | 2026-09-06 |
| GPT-5.6 TerraOpenAI | 87.4%Reported settings & sourceTerminus2only; Gemini selfcomputed, othermodels officialboard/ArtificialAnalysis Gemini3.8Flash Model Card · Model card page5 Results table · reviewed 2026-09-06 | Gemini3.8Flash Model Card | lab self-report | 2026-09-06 |
| Muse Spark 1.2Meta | 82.9%Reported settings & source89tasks; 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 methodology | lab self-report | 2026-09-06 |
| Muse Spark 1.3Meta | 89.2%Reported settings & source89tasks; 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 methodology | lab self-report | 2026-09-06 |