SuperCLUE-Terminal
Agents complete tasks in a terminal.
SuperCLUE reports scores in a public workbook.
- Made by
- SuperCLUE
- Kind
- Terminal tasks
- Level
- Expert
- Scored
- Settled by events
- Answers
- Agent task
- Measures
- Capability
- Interaction
- Agentic
- Environment
- Terminal
- Refresh
- One fixed set
- Run by
- A host
- In views
- Agents
- Strongest model tested
- Kimi K3 #25 on the capability index
- Last model added
- September 2026
- Scores refreshed
- November 20th, 2026
MiMo-V2.6 Pro leads with 64.7 among models released by September 2026
Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.
The newest model with a score here came out in September 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
- Claude Opus 5.5
- and 16 more
- 64.7 MiMo-V2.6 Pro
- 60.6 Kimi K3
- 56.6 GLM-5.3
- 55.6
Tencent Hy4 preview
- 53.5 MiMo-V2.6 Flash
- 51.5
DeepSeek V4 Pro 0813
- 50.5
DeepSeek V4.1 Flash
- 49.5
Qwen 3.8 Max
- 48.5 GLM-5.2
- 48.5 GLM-5.3-Flash
- 48.5
Qwen3.8 Flash
- 46.5
DeepSeek V4 Flash 0731
- 39.4
DeepSeek-V4-Pro
- 36.4
MiniMax-M3
- 35.4
Seed2.1 Pro
- 34.3
Tencent Hy3
- 33.3
LongCat-2.0
- 27.3 MiMo-V2.5-Pro
- 1 MiMo-V2.6 Pro api 64.7
- 2 Kimi K3 max / api 60.6
- 3 GLM-5.3 max / api 56.6
- 4
Tencent Hy4 preview high / api 55.6
- 5 MiMo-V2.6 Flash api 53.5
- 6
DeepSeek V4 Pro 0813 max / api 51.5
- 7
DeepSeek V4.1 Flash max / api 50.5
- 8
Qwen 3.8 Max api 49.5
- 9 GLM-5.2 max / api 48.5
- 10 GLM-5.3-Flash max / api 48.5
- 11
Qwen3.8 Flash api 48.5
- 12
DeepSeek V4 Flash 0731 max / api 46.5
- 13
DeepSeek-V4-Pro max / api 39.4
- 14
MiniMax-M3 api 36.4
- 15
Seed2.1 Pro high / api 35.4
- 16
Tencent Hy3 high / api 34.3
- 17
LongCat-2.0 api 33.3
- 18 MiMo-V2.5-Pro api 27.3
Source: Official SuperCLUE-Terminal leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | MiMo-V2.6 Pro | 64.7 | api | Sep 2026 | Official leaderboard |
| 2 | Kimi K3 | 60.6 | max / api | Jul 2026 | Official leaderboard |
| 3 | GLM-5.3 | 56.6 | max / api | Aug 2026 | Official leaderboard |
| 4 | | 55.6 | high / api | Aug 2026 | Official leaderboard |
| 5 | MiMo-V2.6 Flash | 53.5 | api | Sep 2026 | Official leaderboard |
| 6 | | 51.5 | max / api | Aug 2026 | Official leaderboard |
| 7 | | 50.5 | max / api | Sep 2026 | Official leaderboard |
| 8 | | 49.5 | api | Aug 2026 | Official leaderboard |
| 9 | GLM-5.2 | 48.5 | max / api | Jun 2026 | Official leaderboard |
| 10 | GLM-5.3-Flash | 48.5 | max / api | Aug 2026 | Official leaderboard |
| 11 | | 48.5 | api | Aug 2026 | Official leaderboard |
| 12 | | 46.5 | max / api | Jul 2026 | Official leaderboard |
| 13 | | 39.4 | max / api | Apr 2026 | Official leaderboard |
| 14 | | 36.4 | api | Jun 2026 | Official leaderboard |
| 15 | | 35.4 | high / api | Jun 2026 | Official leaderboard |
| 16 | | 34.3 | high / api | Jul 2026 | Official leaderboard |
| 17 | | 33.3 | api | Jul 2026 | Official leaderboard |
| 18 | MiMo-V2.5-Pro | 27.3 | api | Apr 2026 | Official leaderboard |
Rankings by part
We read 2 parts from the benchmark’s own leaderboard: 平均每题交互轮数 and 总题目数量. Each ranks models on one part of the test. DeepSeek V4.1 Flash leads 平均每题交互轮数 and MiMo-V2.5-Pro leads 总题目数量. Arrows show how far a model moved from its overall rank among the models we track.
平均每题交互轮数
18 models we track have a score here.
- 1
DeepSeek V4.1 Flash ↑6 117.7
- 2 GLM-5.3-Flash ↑8 116.4
- 3
MiniMax-M3 ↑11 106.9
- 4 GLM-5.3 ↓1 103.0
- 5
Tencent Hy4 preview ↓1 101.4
- 6
DeepSeek V4 Flash 0731 ↑6 91.6
- 7
DeepSeek V4 Pro 0813 ↓1 84.2
- 8
LongCat-2.0 ↑9 82.9
- 9 MiMo-V2.6 Flash ↓4 76.4
- 10
Qwen 3.8 Max ↓2 75.0
总题目数量
18 models we track have a score here.
- 1 MiMo-V2.5-Pro ↑17 99.0
- 2
DeepSeek-V4-Pro ↑11 99.0
- 3
MiniMax-M3 ↑11 99.0
- 4 GLM-5.2 ↑5 99.0
- 5
Seed2.1 Pro ↑10 99.0
- 6
Tencent Hy3 ↑10 99.0
- 7
LongCat-2.0 ↑10 99.0
- 8 Kimi K3 ↓6 99.0
- 9
DeepSeek V4 Flash 0731 ↑3 99.0
- 10
Qwen 3.8 Max ↓2 99.0
5 models have held number one on the official leaderboard since 2023
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official SuperCLUE-Terminal 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 SuperCLUE-Terminal 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%
- Terminal-Bench Pro Not in model cards Agents solve 400 terminal tasks across eight domains. Harbor distributes the 200 public tasks. Alibaba keeps the other 200 for private evaluation. Claude Opus 4.5 51%
Data audit
8 of 9 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark
Catalog record 1 warning 1 pass
- Warning Task access We don’t know whether the tasks are public.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (18 entries).
- Pass Models scored 18 models we track.
- Pass Newest score The newest is from September 2026, for MiMo-V2.6 Flash.
- Note Frontier models None of the top 10 has a score. The strongest tested is Kimi K3 (#25).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on superclueai.com: 18 rows for models we track 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.