Terminal-Bench 2.1terminalPythonTOML
Detect hurdle takeoff and landing frames
Implement an OpenCV script that analyzes a stationary-camera hurdle video and records the single jump's takeoff and landing frame numbers in TOML.
video-processing
Normalized profile
What this task asks for
Implement an OpenCV script that analyzes a stationary-camera hurdle video and records the single jump's takeoff and landing frame numbers in TOML. Use only toml, cv2, and numpy. Accept an MP4 input and generalize beyond the example. Assume a fixed camera and empty first frame. Write exactly jump_takeoff_frame_number and jump_land_frame_number as integers.
Intent
- feature implementation
- data transformation
Work surfaces
- video analysis
- motion events
- command-line interface
Technology
- OpenCV
- NumPy
- MP4
- TOML
Expected artifacts
- /app/jump_analyzer.py
- /app/output.toml
What makes it difficult
- strict behavioral compatibility or exact-output validation
- cross-language or cross-format integration
- 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
| Model | Harness | Effort | Result | Passes |
|---|---|---|---|---|
| claude-fable-5anthropic · 2026-06-07 | claude-code2.1.167 | xhigh | Mixed | 4/5 |
| claude-fable-5anthropic · 2026-06-05 | terminus-22.0.0 | high | Mixed | 1/5 |
| claude-opus-4-7anthropic · 2026-05-01 | claude-code2.1.123 | max | No passes | 0/5 |
| claude-opus-4-7anthropic · 2026-05-01 | terminus-22.0.0 | max | Mixed | 1/5 |
| claude-opus-4-8anthropic · 2026-07-09 | claude-code2.1.205 | high | Mixed | 1/5 |
| claude-sonnet-5anthropic · 2026-07-09 | claude-code2.1.205 | high | Mixed | 1/5 |
| gemini-3-pro-previewgemini · 2026-05-01 | gemini-cli0.40.0 | high | Mixed | 2/5 |
| gemini-3-pro-previewgemini · 2026-05-01 | terminus-22.0.0 | high | Mixed | 2/5 |
| gemini-3.1-pro-previewgemini · 2026-05-05 | gemini-cli0.40.0 | high | Mixed | 1/5 |
| gemini-3.1-pro-previewgemini · 2026-05-05 | terminus-22.0.0 | high | Mixed | 1/5 |
| glm-5.1zai · 2026-05-01 | claude-code2.1.123 | max | Mixed | 1/5 |
| gpt-5.5openai · 2026-05-01 | codex0.125.0 | xhigh | Mixed | 1/5 |
| gpt-5.5openai · 2026-05-01 | terminus-22.0.0 | xhigh | No passes | 0/5 |
| gpt-5.6-lunaopenai · 2026-07-10 | codex0.144.0 | max | Mixed | 1/5 |
| gpt-5.6-lunaopenai · 2026-07-11 | codex0.144.1 | max | Mixed | 1/5 |
| gpt-5.6-solopenai · 2026-07-10 | codex0.144.0 | max | Mixed | 2/5 |
| gpt-5.6-terraopenai · 2026-07-10 | codex0.144.0 | max | Mixed | 3/5 |
| gpt-5.6-terraopenai · 2026-07-11 | codex0.144.1 | max | Mixed | 3/5 |
| grok-4.5cursor · 2026-07-09 | cursor-cli2026.07.08-0c04a8a | default | Mixed | 2/5 |
| muse-spark-1.1openai · 2026-07-09 | mini-swe-agent2.4.5 | xhigh | No passes | 0/5 |