Terminal-Bench Pro
Agents solve 400 terminal tasks across eight domains. Harbor distributes the 200 public tasks. Alibaba keeps the other 200 for private evaluation.
On November 19, 2026, Qwen3.5 led the public set at 51.5%. Claude Opus 4.5 led the private set at 51.0%.
- Made by
- Alibaba
- Released
- December 2025
- Kind
- Terminal tasks
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- Public, plus a private test set
- Measures
- Capability
- Language
- English
- Interaction
- Agentic
- Environment
- Terminal
- Refresh
- One fixed set
- Run by
- A host
- In views
- Agents
- Strongest model tested
- GPT-5.2 #51 on the capability index
- Last model added
- February 2026
- Scores refreshed
- November 20th, 2026
Claude Opus 4.5 leads with 51% among models released by February 2026 Claude Opus 4.5 leads with 51% among models released by February 2026
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. The board reports no overall score, so the headline is the plain mean of its public and private success rates. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.
The newest model with a score here came out in February 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 51.0 Claude Opus 4.5
- 48.7
Qwen3.5 397B-A17B
- 48.1
Gemini 3 Pro
- 47.0 GPT-5.1-Codex
- 43.8 Claude Sonnet 4.5
- 41.3
DeepSeek-V3.2-Speciale
- 38.4 GLM-4.7
- 37.2 GPT-5.2
- 36.0
Qwen3-Max
- 35.8 Claude Haiku 4.5
- 35.3 GLM-4.6
- 34.9
Seed1.8
- 34.8 Kimi K2
- 34.0 Qwen3-Coder-Plus
- 33.8
DeepSeek-V3.1
- 32.5 GPT-5 mini
- 32.4
Qwen3-Coder-480B-A35B
- 31.0 ROME
- 29.9 gpt-oss-120b
- 24.6
Devstral Small 2
- 24.4 GLM-4.5-Air
- 19.4
Gemini 2.5 Flash
- 18.6
Qwen3-Coder-30B-A3B-Instruct
- 0.05 Kimi-Linear-48B-A3B-Instruct
- 1 Claude Opus 4.5 51%
- 2
Qwen3.5 397B-A17B 48.7%
- 3
Gemini 3 Pro 48.1%
- 4 GPT-5.1-Codex 47%
- 5 Claude Sonnet 4.5 43.8%
- 6
DeepSeek-V3.2-Speciale 41.3%
- 7 GLM-4.7 38.4%
- 8 GPT-5.2 37.2%
- 9
Qwen3-Max 36%
- 10 Claude Haiku 4.5 35.8%
- 11 GLM-4.6 35.3%
- 12
Seed1.8 34.9%
- 13 Kimi K2 Sep 2025 34.8%
- 14 Qwen3-Coder-Plus 34%
- 15
DeepSeek-V3.1 33.8%
- 16 GPT-5 mini 32.5%
- 17
Qwen3-Coder-480B-A35B 32.4%
- 18 ROME 31%
- 19 gpt-oss-120b 29.9%
- 20
Devstral Small 2 24.6%
- 21 GLM-4.5-Air 24.4%
- 22
Gemini 2.5 Flash Sep 2025 19.4%
- 23
Qwen3-Coder-30B-A3B-Instruct 18.6%
- 24 Kimi-Linear-48B-A3B-Instruct 0.05%
Source: Official Terminal-Bench Pro leaderboard
- 51.0 Claude Opus 4.5
- 48.7
Qwen3.5 397B-A17B
- 48.1
Gemini 3 Pro
- 47.0 GPT-5.1-Codex
- 43.8 Claude Sonnet 4.5
- 41.3
DeepSeek-V3.2-Speciale
- 38.4 GLM-4.7
- 37.2 GPT-5.2
- 36.0
Qwen3-Max
- 35.8 Claude Haiku 4.5
- 35.3 GLM-4.6
- 34.9
Seed1.8
- 34.8 Kimi K2
- 34.0 Qwen3-Coder-Plus
- 33.8
DeepSeek-V3.1
- 32.5 GPT-5 mini
- 32.4
Qwen3-Coder-480B-A35B
- 29.9 gpt-oss-120b
- 24.6
Devstral Small 2
- 24.4 GLM-4.5-Air
- 19.4
Gemini 2.5 Flash
- 18.6
Qwen3-Coder-30B-A3B-Instruct
- 0.05 Kimi-Linear-48B-A3B-Instruct
- 1 Claude Opus 4.5 51%
- 2
Qwen3.5 397B-A17B 48.7%
- 3
Gemini 3 Pro 48.1%
- 4 GPT-5.1-Codex 47%
- 5 Claude Sonnet 4.5 43.8%
- 6
DeepSeek-V3.2-Speciale 41.3%
- 7 GLM-4.7 38.4%
- 8 GPT-5.2 37.2%
- 9
Qwen3-Max 36%
- 10 Claude Haiku 4.5 35.8%
- 11 GLM-4.6 35.3%
- 12
Seed1.8 34.9%
- 13 Kimi K2 Sep 2025 34.8%
- 14 Qwen3-Coder-Plus 34%
- 15
DeepSeek-V3.1 33.8%
- 16 GPT-5 mini 32.5%
- 17
Qwen3-Coder-480B-A35B 32.4%
- 18 gpt-oss-120b 29.9%
- 19
Devstral Small 2 24.6%
- 20 GLM-4.5-Air 24.4%
- 21
Gemini 2.5 Flash Sep 2025 19.4%
- 22
Qwen3-Coder-30B-A3B-Instruct 18.6%
- 23 Kimi-Linear-48B-A3B-Instruct 0.05%
Source: Official Terminal-Bench Pro leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.5 | 51% | Claude-Code | Nov 2025 | Official leaderboard |
| 2 | | 48.7% | IFlow CLI-0.4.11 | Feb 2026 | Official leaderboard |
| 3 | | 48.1% | IFlow CLI-0.4.11 | Nov 2025 | Official leaderboard |
| 4 | GPT-5.1-Codex | 47% | Codex-CLI | Nov 2025 | Official leaderboard |
| 5 | Claude Sonnet 4.5 | 43.8% | Claude-Code | Sep 2025 | Official leaderboard |
| 6 | | 41.3% | IFlow CLI-0.4.11 | Dec 2025 | Official leaderboard |
| 7 | GLM-4.7 | 38.4% | IFlow CLI-0.4.11 | Dec 2025 | Official leaderboard |
| 8 | GPT-5.2 | 37.2% | IFlow CLI-0.5.7 | Dec 2025 | Official leaderboard |
| 9 | | 36% | IFlow CLI-0.4.11 | Sep 2025 | Official leaderboard |
| 10 | Claude Haiku 4.5 | 35.8% | Claude-Code | Oct 2025 | Official leaderboard |
| 11 | GLM-4.6 | 35.3% | IFlow CLI-0.4.11 | Sep 2025 | Official leaderboard |
| 12 | | 34.9% | IFlow CLI-0.4.11 | Dec 2025 | Official leaderboard |
| 13 | Kimi K2 Sep 2025 | 34.8% | IFlow CLI-0.4.11 | Sep 2025 | Official leaderboard |
| 14 | Qwen3-Coder-Plus | 34% | IFlow CLI-0.4.11 | Sep 2025 | Official leaderboard |
| 15 | | 33.8% | IFlow CLI-0.4.11 | Aug 2025 | Official leaderboard |
| 16 | GPT-5 mini | 32.5% | IFlow CLI-0.4.11 | Aug 2025 | Official leaderboard |
| 17 | | 32.4% | IFlow CLI-0.4.11 | Jul 2025 | Official leaderboard |
| 18 | ROME 30B | 31% | IFlow CLI-0.4.11 | Official leaderboard | |
| 19 | gpt-oss-120b | 29.9% | IFlow CLI-0.4.11 | Aug 2025 | Official leaderboard |
| 20 | | 24.6% | IFlow CLI-0.4.11 | Dec 2025 | Official leaderboard |
| 21 | GLM-4.5-Air | 24.4% | IFlow CLI-0.4.11 | Jul 2025 | Official leaderboard |
| 22 | | 19.4% | IFlow CLI-0.4.11 | Sep 2025 | Official leaderboard |
| 23 | | 18.6% | IFlow CLI-0.4.11 | Jul 2025 | Official leaderboard |
| 24 | Kimi-Linear-48B-A3B-Instruct | 0.05% | IFlow CLI-0.4.11 | Oct 2025 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.5 | 51% | Claude-Code | Nov 2025 | Official leaderboard |
| 2 | | 48.7% | IFlow CLI-0.4.11 | Feb 2026 | Official leaderboard |
| 3 | | 48.1% | IFlow CLI-0.4.11 | Nov 2025 | Official leaderboard |
| 4 | GPT-5.1-Codex | 47% | Codex-CLI | Nov 2025 | Official leaderboard |
| 5 | Claude Sonnet 4.5 | 43.8% | Claude-Code | Sep 2025 | Official leaderboard |
| 6 | | 41.3% | IFlow CLI-0.4.11 | Dec 2025 | Official leaderboard |
| 7 | GLM-4.7 | 38.4% | IFlow CLI-0.4.11 | Dec 2025 | Official leaderboard |
| 8 | GPT-5.2 | 37.2% | IFlow CLI-0.5.7 | Dec 2025 | Official leaderboard |
| 9 | | 36% | IFlow CLI-0.4.11 | Sep 2025 | Official leaderboard |
| 10 | Claude Haiku 4.5 | 35.8% | Claude-Code | Oct 2025 | Official leaderboard |
| 11 | GLM-4.6 | 35.3% | IFlow CLI-0.4.11 | Sep 2025 | Official leaderboard |
| 12 | | 34.9% | IFlow CLI-0.4.11 | Dec 2025 | Official leaderboard |
| 13 | Kimi K2 Sep 2025 | 34.8% | IFlow CLI-0.4.11 | Sep 2025 | Official leaderboard |
| 14 | Qwen3-Coder-Plus | 34% | IFlow CLI-0.4.11 | Sep 2025 | Official leaderboard |
| 15 | | 33.8% | IFlow CLI-0.4.11 | Aug 2025 | Official leaderboard |
| 16 | GPT-5 mini | 32.5% | IFlow CLI-0.4.11 | Aug 2025 | Official leaderboard |
| 17 | | 32.4% | IFlow CLI-0.4.11 | Jul 2025 | Official leaderboard |
| 18 | gpt-oss-120b | 29.9% | IFlow CLI-0.4.11 | Aug 2025 | Official leaderboard |
| 19 | | 24.6% | IFlow CLI-0.4.11 | Dec 2025 | Official leaderboard |
| 20 | GLM-4.5-Air | 24.4% | IFlow CLI-0.4.11 | Jul 2025 | Official leaderboard |
| 21 | | 19.4% | IFlow CLI-0.4.11 | Sep 2025 | Official leaderboard |
| 22 | | 18.6% | IFlow CLI-0.4.11 | Jul 2025 | Official leaderboard |
| 23 | Kimi-Linear-48B-A3B-Instruct | 0.05% | IFlow CLI-0.4.11 | Oct 2025 | Official leaderboard |
Rankings by part
We read 2 parts from the benchmark’s own leaderboard: Public set and Private set. Each ranks models on one part of the test. Qwen3.5 397B-A17B leads Public set and Claude Opus 4.5 leads Private set. Arrows show how far a model moved from its overall rank among the models we track.
Public set
23 models we track have a score here.
- 1
Qwen3.5 397B-A17B ↑1 51.5%
- 2 Claude Opus 4.5 ↓1 51%
- 3 Claude Sonnet 4.5 ↑2 49.5%
- 4
Gemini 3 Pro ↓1 47.9%
- 5 GPT-5.1-Codex ↓1 46.5%
- 6
DeepSeek-V3.2-Speciale 45.2%
- 7 Claude Haiku 4.5 ↑3 44.5%
- 8 GLM-4.7 ↓1 43.1%
- 9 GLM-4.6 ↑2 41.5%
- 10 Kimi K2 Sep 2025 ↑3 40.5%
Private set
23 models we track have a score here.
- 1 Claude Opus 4.5 51%
- 2
Gemini 3 Pro ↑1 48.4%
- 3 GPT-5.1-Codex ↑1 47.5%
- 4
Qwen3.5 397B-A17B ↓2 45.9%
- 5 GPT-5.2 ↑3 38.1%
- 6 Claude Sonnet 4.5 ↓1 38%
- 7
DeepSeek-V3.2-Speciale ↓1 37.4%
- 8 GLM-4.7 ↓1 33.7%
- 9
Qwen3-Max 31.8%
- 10 GPT-5 mini ↑6 30%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Terminal-Bench Pro leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Terminal-Bench Pro leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Terminal agents
- SkillsBench In use 86-87 containerized expert tasks in 11 domains, run with and without Agent Skills. Verifier tests give pass rate and skill lift. GPT-5.5 66.5%
- Terminal-Bench Hard In use Agents complete 44 hard tasks from Terminal-Bench Core in the Terminus 2 harness. Artificial Analysis scores pass@1 averaged over 3 repeats.
Gemma 4 31B IT 36%
- Terminal-Bench 4.1 In use The Terminal-Bench 4.0 tasks with hardened verifiers: agents complete 66 hard tasks in containerized terminals across software, ML, science, security, and operations. Test scripts verify each result, scored as resolution rate. Copilot Fusion 71.2%
- Harbor-Index In use Agents solve about 80 hard tasks drawn from 29 benchmarks run through Harbor adapters, such as HLE, GSO and SWE-bench Pro. Each task keeps its source verifier. GPT-5.5 28.1%
- Terminal-Bench 2.1 Extended Not in model cards Agents complete long command-line tasks in containers, scored by verification tests. Mercor adds 99 new expert-written tasks to the 89 public ones and reports both scores.
Muse Wonder 54%
- o11y-bench Not in model cards Agents query metrics, logs and traces in a live Grafana stack, investigate incidents and fix dashboards. Grading checks claims against facts read from the same environment. Claude Opus 5.5 93.8%
Data audit
9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 9 months ago, in February 2026, for Qwen3.5 397B-A17B. Every benchmark
Catalog record 2 pass
- Pass Task access Public tasks, plus a private test set.
- Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
- Pass Independent runs Scores from the official leaderboard (24 entries).
- Pass Models scored 23 models we track, plus 1 other entry on its leaderboard.
- Warning Newest score The newest came 9 months ago, in February 2026, for Qwen3.5 397B-A17B.
- Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.2 (#51).
- Pass Headroom The best is 51%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on alibaba.github.io: 23 rows for models we track and 1 other entry at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.