All evidence cases
Terminal-Bench 2.1terminalplain text

Retrieve the fifth-nearest document with MTEB

Encode the query and line-delimited corpus with the pinned Chinese BGE model and return the document ranked fifth by cosine similarity.

mteb-retrieve

Normalized profile

What this task asks for

Encode the query and line-delimited corpus with the pinned Chinese BGE model and return the document ranked fifth by cosine similarity. Use query terminal-bench. Load revision 7999e1d3359715c523056ef9478215996d62a620. Encode through installed MTEB 1.36.8. Write the fifth-highest-similarity source line.

  • data transformation
  • embedding model
  • document corpus
  • retrieval ranking
  • MTEB 1.36.8
  • bge-small-zh-v1.5
  • cosine similarity
  • /app/result.txt
  • specialized algorithmic or domain reasoning
  • ranking or retrieval over incomplete external evidence
  • changes span multiple components or interfaces

Published evidence

Model × harness outcomes

Counts are tied to these exact configurations. Harnesses are not treated as equivalent across benchmarks.

Models
13
Configurations
20
Trials
100

Showing 20 of 20 configurations

ModelHarnessEffortResultPasses
claude-fable-5anthropic · 2026-06-07claude-code2.1.167xhighMixed1 disqualified3/5
claude-fable-5anthropic · 2026-06-05terminus-22.0.0highMixed1/5
claude-opus-4-7anthropic · 2026-05-01claude-code2.1.123maxNo passes0/5
claude-opus-4-7anthropic · 2026-05-01terminus-22.0.0maxMixed2/5
claude-opus-4-8anthropic · 2026-07-09claude-code2.1.205highMixed2/5
claude-sonnet-5anthropic · 2026-07-09claude-code2.1.205highMixed2/5
gemini-3-pro-previewgemini · 2026-05-01gemini-cli0.40.0highMixed1/5
gemini-3-pro-previewgemini · 2026-05-01terminus-22.0.0highMixed2/5
gemini-3.1-pro-previewgemini · 2026-05-05gemini-cli0.40.0highAll passed5/5
gemini-3.1-pro-previewgemini · 2026-05-05terminus-22.0.0highAll passed5/5
glm-5.1zai · 2026-05-01claude-code2.1.123maxNo passes0/5
gpt-5.5openai · 2026-05-01codex0.125.0xhighAll passed5/5
gpt-5.5openai · 2026-05-01terminus-22.0.0xhighAll passed5/5
gpt-5.6-lunaopenai · 2026-07-10codex0.144.0maxAll passed5/5
gpt-5.6-lunaopenai · 2026-07-11codex0.144.1maxAll passed5/5
gpt-5.6-solopenai · 2026-07-10codex0.144.0maxAll passed5/5
gpt-5.6-terraopenai · 2026-07-10codex0.144.0maxAll passed5/5
gpt-5.6-terraopenai · 2026-07-11codex0.144.1maxAll passed5/5
grok-4.5cursor · 2026-07-09cursor-cli2026.07.08-0c04a8adefaultAll passed5/5
muse-spark-1.1openai · 2026-07-09mini-swe-agent2.4.5xhighMixed4/5