Terminal-Bench 2.1terminaldisk image
Run Windows 3.11 in a controllable QEMU VM
Boot the supplied Windows 3.11 image in snapshot mode with VNC, an Nginx web interface, and a monitor socket for programmatic keyboard input.
install-windows-3.11
Normalized profile
What this task asks for
Boot the supplied Windows 3.11 image in snapshot mode with VNC, an Nginx web interface, and a monitor socket for programmatic keyboard input. Keep /app/isos/win311.img immutable using snapshot mode. Serve VNC display :1 on port 5901. Leave the VM at the Windows desktop. Accept external keyboard control through the QEMU monitor.
Intent
- systems setup
- configuration tuning
Work surfaces
- virtual machine
- VNC service
- HTTP server
- monitor socket
Technology
- QEMU 5.2.0
- Windows 3.11
- VNC
- Nginx
Expected artifacts
- running Windows 3.11 VM
- /tmp/qemu-monitor.sock
- web interface on port 80
What makes it difficult
- cross-platform or cross-architecture execution
- environment provisioning and end-to-end 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 | 2/5 |
| claude-opus-4-7anthropic · 2026-05-01 | claude-code2.1.123 | max | No passes2 errors | 0/5 |
| claude-opus-4-7anthropic · 2026-05-01 | terminus-22.0.0 | max | Mixed1 errors | 3/5 |
| claude-opus-4-8anthropic · 2026-07-09 | claude-code2.1.205 | high | Mixed | 2/5 |
| claude-sonnet-5anthropic · 2026-07-09 | claude-code2.1.205 | high | Mixed | 3/5 |
| gemini-3-pro-previewgemini · 2026-05-01 | gemini-cli0.40.0 | high | No passes | 0/5 |
| gemini-3-pro-previewgemini · 2026-05-01 | terminus-22.0.0 | high | No passes | 0/5 |
| gemini-3.1-pro-previewgemini · 2026-05-05 | gemini-cli0.40.0 | high | No passes | 0/5 |
| gemini-3.1-pro-previewgemini · 2026-05-05 | terminus-22.0.0 | high | No passes1 errors | 0/5 |
| glm-5.1zai · 2026-05-01 | claude-code2.1.123 | max | No passes | 0/5 |
| gpt-5.5openai · 2026-05-01 | codex0.125.0 | xhigh | Mixed | 3/5 |
| 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 | All passed | 5/5 |
| gpt-5.6-lunaopenai · 2026-07-11 | codex0.144.1 | max | Mixed | 4/5 |
| gpt-5.6-solopenai · 2026-07-10 | codex0.144.0 | max | All passed | 5/5 |
| gpt-5.6-terraopenai · 2026-07-10 | codex0.144.0 | max | Mixed | 4/5 |
| gpt-5.6-terraopenai · 2026-07-11 | codex0.144.1 | max | Mixed | 4/5 |
| grok-4.5cursor · 2026-07-09 | cursor-cli2026.07.08-0c04a8a | default | Mixed1 errors · 1 disqualified | 2/5 |
| muse-spark-1.1openai · 2026-07-09 | mini-swe-agent2.4.5 | xhigh | No passes4 errors | 0/5 |