TCSExam-Lite
Version Lite
Agents solve 20 theoretical computer science tasks, five per track. The default solver protocol gives hidden feedback only after submission.
The Lite leaderboard lists eight models, including one provisional result. Its task mix and solver feedback differ from Full.
- Made by
- Moonshot AI
- Released
- November 2026
- Kind
- AI research tasks
- Level
- Research frontier
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Agentic
- Environment
- Code sandbox
- Refresh
- New versions replace it
- Run by
- Anyone
- Based on
- TCSExam
- In views
- Agents
- Strongest model tested
- GPT-6 Astra #4 on the capability index
- Last model added
- October 2026
- Scores refreshed
- November 21st, 2026
Claude Opus 5.5 leads with 72.3 Claude Opus 5.5 leads with 72.3
Best score per entry from the benchmark's paper, read on November 21st, 2026. A paper’s table doesn’t add newer models. 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.
- 1 Claude Opus 5.5 72.3
- 2 GPT-6 Astra 67.0
- 3 Kimi K3.1 Pro 53.5
- 4 Kimi K3 48.6
- 5 GLM-5.3 47.0
- 6
Qwen3.8 Max (0902) 45.4
- 7
DeepSeek V4.1 Flash 1017 42.4
- 8 Grok 4.6 42.1
- 9 DeepSeek V4.1 Flash 0910 39.0
Source: The TCSExam-Lite paper
- 1 Claude Opus 5.5 72.3
- 2 GPT-6 Astra 67.0
- 3 Kimi K3.1 Pro 53.5
- 4 Kimi K3 48.6
- 5 GLM-5.3 47.0
- 6
Qwen3.8 Max (0902) 45.4
- 7
DeepSeek V4.1 Flash 1017 42.4
- 8 Grok 4.6 42.1
Source: The TCSExam-Lite paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | 72.3 | Sep 2026 | Official leaderboard | |
| 2 | GPT-6 Astra | 67.0 | Sep 2026 | Official leaderboard | |
| 3 | Kimi K3.1 Pro | 53.5 | Oct 2026 | Official leaderboard | |
| 4 | Kimi K3 | 48.6 | Jul 2026 | Official leaderboard | |
| 5 | GLM-5.3 | 47.0 | Aug 2026 | Official leaderboard | |
| 6 | | 45.4 | Sep 2026 | Official leaderboard | |
| 7 | | 42.4 | Oct 2026 | Official leaderboard | |
| 8 | Grok 4.6 | 42.1 | Aug 2026 | Official leaderboard | |
| 9 | DeepSeek V4.1 Flash 0910 | 39.0 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | 72.3 | Sep 2026 | Official leaderboard | |
| 2 | GPT-6 Astra | 67.0 | Sep 2026 | Official leaderboard | |
| 3 | Kimi K3.1 Pro | 53.5 | Oct 2026 | Official leaderboard | |
| 4 | Kimi K3 | 48.6 | Jul 2026 | Official leaderboard | |
| 5 | GLM-5.3 | 47.0 | Aug 2026 | Official leaderboard | |
| 6 | | 45.4 | Sep 2026 | Official leaderboard | |
| 7 | | 42.4 | Oct 2026 | Official leaderboard | |
| 8 | Grok 4.6 | 42.1 | Aug 2026 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The TCSExam-Lite paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official TCSExam-Lite 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.
Versions
More in AI research
- PaperBench In use Agent replicates ICML 2024 papers from scratch. LLM judge grades against author-written hierarchical rubrics.
Qwen 3.8 Max 93%
- MLS-Bench In use Agent must invent one algorithmic change in an ML research scaffold whose gain transfers across settings. Scored relative to human baselines. Claude Fable 5.1 50.3%
- PostTrainBench 1.2 In use CLI agent gets a base model, one H100 and a time budget to post-train it for a target benchmark. Scored on normalized gain. Claude Fable 5.1 44.6%
- MLE-bench In use Kaggle-style ML engineering competitions. Agent trains models and is scored against competition leaderboards. GPT-6.2 Astra 96.1%
- PMPP-Hard In use Agents write GPU kernels for 69 tasks that must be correct, and on 48 of them also run within 1.25 times the reference time. The score is the area under the solved-tasks curve over a 10-hour budget, out of 690 task-hours. Kimi K3 0.71
- KernelBench In use Replace PyTorch operators with faster custom GPU kernels. Scored on correctness and speedup.
MiniMax-M3 28.8%
Data audit
All 9 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the benchmark’s paper (9 entries).
- Pass Models scored 8 models we track, plus 1 other entry on its leaderboard.
- Pass Newest score The newest is from October 2026, for Kimi K3.1 Pro.
- Note Frontier models Only 2 of the top 10 have a score. The strongest tested is GPT-6 Astra (#4).
- Note Headroom Scored as an index, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 8 rows for models we track and 1 other entry at the last read.
- Pass Last read November 21st, 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.