All evidence cases
Terminal-Bench 2.1terminalJSON LinesPython

Optimize shape-aware LLM inference batches

Pack every request from two buckets into static-shape batches that obey alignment and shape limits while meeting cost, padding, latency, and time thresholds.

llm-inference-batching-scheduler

Normalized profile

What this task asks for

Pack every request from two buckets into static-shape batches that obey alignment and shape limits while meeting cost, padding, latency, and time thresholds. Include every request exactly once. Use seq_align multiples of 64 with heads_align 32 and hidden_align 4096. Use no more than eight unique shapes across both buckets. Keep shapes identical within a batch. Meet every published per-bucket performance threshold.

  • performance optimization
  • configuration tuning
  • data transformation
  • batch scheduler
  • tensor shapes
  • LLM inference
  • static graphs
  • JSON Lines
  • /app/task_file/output_data/plan_b1.jsonl
  • /app/task_file/output_data/plan_b2.jsonl
  • reverse engineering from incomplete or indirect evidence
  • strict behavioral compatibility or exact-output validation
  • quantitative performance, accuracy, or resource constraints
  • cross-language or cross-format integration

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-code2.1.167xhighAll passed5/5
claude-fable-5anthropic · 2026-06-05terminus-22.0.0highAll passed5/5
claude-opus-4-7anthropic · 2026-05-01claude-code2.1.123maxAll passed5/5
claude-opus-4-7anthropic · 2026-05-01terminus-22.0.0maxNo passes5 errors0/5
claude-opus-4-8anthropic · 2026-07-09claude-code2.1.205highMixed4/5
claude-sonnet-5anthropic · 2026-07-09claude-code2.1.205highMixed1 errors3/5
gemini-3-pro-previewgemini · 2026-05-01gemini-cli0.40.0highAll passed5/5
gemini-3-pro-previewgemini · 2026-05-01terminus-22.0.0highAll passed5/5
gemini-3.1-pro-previewgemini · 2026-05-05gemini-cli0.40.0highMixed1 errors4/5
gemini-3.1-pro-previewgemini · 2026-05-05terminus-22.0.0highAll passed5/5
glm-5.1zai · 2026-05-01claude-code2.1.123maxMixed4 errors1/5
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-agent2.4.5xhighAll passed5/5