TIS-100 Bench
Agents write and optimize assembly programs for 55 puzzles. The ranking counts puzzles where a program improves on the community’s recorded tradeoffs in cycles, nodes, and instructions.
Wincon ranks 16 models on 47 game puzzles and eight tournament puzzles. Each qualifying program passed a fresh game replay and 100,000 simulator tests.
- Made by
- Wincon
- Released
- November 2026
- Kind
- Speed and optimization
- Level
- Competition
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Measures
- Efficiency
- Language
- English
- Interaction
- Agentic
- Environment
- TIS-100
- Items from
- Exams and contests, Another benchmark
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
- GPT-6 Astra #4 on the capability index
- Last model added
- October 2026
- Scores refreshed
- November 20th, 2026
2 models share the top score of 11.0
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.
- 11.0 GPT-6 Astra
- 11.0 Claude Opus 5.5
- 8.00
Gemini 4 Argon
- 7.00 Claude Sonnet 5.5
- 6.00 GPT-6.1 Sol
- 5.00 Claude Fable 5.1
- 2.00 Kimi K3.1 Pro
- 1.00 GLM-5.3
- 1.00
Gemini 3.8 Flash
- 1.00 Claude Haiku 5.5
- 1.00
Muse Wonder
- 0.00
Muse Spark 1.3
- 0.00
DeepSeek V4.1 Flash
- 0.00 Grok 4.7
- 0.00 MiMo-V2.6 Pro
- 0.00 GPT-6 Luna
- 1 GPT-6 Astra 11.0
- 2 Claude Opus 5.5 11.0
- 3
Gemini 4 Argon 8.00
- 4 Claude Sonnet 5.5 7.00
- 5 GPT-6.1 Sol 6.00
- 6 Claude Fable 5.1 5.00
- 7 Kimi K3.1 Pro 2.00
- 8 GLM-5.3 1.00
- 9
Gemini 3.8 Flash 1.00
- 10 Claude Haiku 5.5 1.00
- 11
Muse Wonder 1.00
- 12
Muse Spark 1.3 0.00
- 13
DeepSeek V4.1 Flash 0.00
- 14 Grok 4.7 0.00
- 15 MiMo-V2.6 Pro 0.00
- 16 GPT-6 Luna 0.00
Source: Official TIS-100 Bench leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-6 Astra | 11.0 | Sep 2026 | Official leaderboard | |
| 2 | Claude Opus 5.5 | 11.0 | Sep 2026 | Official leaderboard | |
| 3 | | 8.00 | Sep 2026 | Official leaderboard | |
| 4 | Claude Sonnet 5.5 | 7.00 | Sep 2026 | Official leaderboard | |
| 5 | GPT-6.1 Sol | 6.00 | Sep 2026 | Official leaderboard | |
| 6 | Claude Fable 5.1 | 5.00 | Sep 2026 | Official leaderboard | |
| 7 | Kimi K3.1 Pro | 2.00 | Oct 2026 | Official leaderboard | |
| 8 | GLM-5.3 | 1.00 | Aug 2026 | Official leaderboard | |
| 9 | | 1.00 | Sep 2026 | Official leaderboard | |
| 10 | Claude Haiku 5.5 | 1.00 | Oct 2026 | Official leaderboard | |
| 11 | | 1.00 | Oct 2026 | Official leaderboard | |
| 12 | | 0.00 | Sep 2026 | Official leaderboard | |
| 13 | | 0.00 | Sep 2026 | Official leaderboard | |
| 14 | Grok 4.7 | 0.00 | Sep 2026 | Official leaderboard | |
| 15 | MiMo-V2.6 Pro | 0.00 | Sep 2026 | Official leaderboard | |
| 16 | GPT-6 Luna | 0.00 | Sep 2026 | Official leaderboard |
Rankings by part
We read 3 parts from the benchmark’s own leaderboard: New frontier points, Puzzles solved and Record proximity. Each ranks models on one part of the test. GPT-6 Astra leads 2 of them, and Claude Opus 5.5 leads the other one. Arrows show how far a model moved from its overall rank among the models we track.
New frontier points
16 models we track have a score here.
- 1 Claude Opus 5.5 ↑1 72.0
- 2 GPT-6 Astra ↓1 32.0
- 3
Gemini 4 Argon 28.0
- 4 Claude Fable 5.1 ↑2 19.0
- 5 Claude Sonnet 5.5 ↓1 14.0
- 6 GPT-6.1 Sol ↓1 12.0
- 7 Kimi K3.1 Pro 5.00
- 8 GLM-5.3 1.00
- 9
Gemini 3.8 Flash 1.00
- 10 Claude Haiku 5.5 1.00
Puzzles solved
16 models we track have a score here.
- 1 GPT-6 Astra 55.0
- 2 Claude Opus 5.5 55.0
- 3 GPT-6.1 Sol ↑2 54.0
- 4
Gemini 4 Argon ↓1 54.0
- 5
Gemini 3.8 Flash ↑4 53.0
- 6 Claude Sonnet 5.5 ↓2 53.0
- 7 Claude Fable 5.1 ↓1 52.0
- 8 Kimi K3.1 Pro ↓1 52.0
- 9
Muse Wonder ↑2 49.0
- 10 Claude Haiku 5.5 45.0
Record proximity
16 models we track have a score here.
- 1 GPT-6 Astra 78%
- 2 Claude Opus 5.5 77.2%
- 3
Gemini 4 Argon 76.2%
- 4 GPT-6.1 Sol ↑1 75.6%
- 5 Claude Fable 5.1 ↑1 70.2%
- 6 Claude Sonnet 5.5 ↓2 69.9%
- 7
Gemini 3.8 Flash ↑2 66%
- 8 Kimi K3.1 Pro ↓1 64.6%
- 9
Muse Wonder ↑2 58.8%
- 10 Claude Haiku 5.5 53.7%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official TIS-100 Bench 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 TIS-100 Bench 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 Coding
- SWE-bench Verified In use 500 human-validated GitHub issues from 12 Python repos. Agent writes a patch that must pass hidden tests. Claude Opus 4.7 83.5%
- LiveCodeBench v6 In use Competitive programming problems collected after model cutoffs from LeetCode, AtCoder, Codeforces. Scored pass@1 on hidden tests.
DeepSeek-V4-Pro 93.5%
- SWE-bench Multilingual In use 300 GitHub-issue tasks across nine programming languages in SWE-bench format. Patch graded by repository tests. Claude Fable 5.2 96.6%
- DeepSWE In use 113 original long-horizon engineering tasks across 91 repos and five languages, written from scratch. Hand-written verifiers accept alternative solutions. GPT-6 Astra 74.1%
- SciCode In use Scientist-curated research coding problems split into subproblems across natural sciences. Code checked against test cases.
Seed2.1 Pro 59.8%
- Codeforces rating In use Model solves recent Codeforces contest problems. An Elo-style rating is computed from simulated contest performance.
DeepSeek V4.1 Flash 3,471
Data audit
All 10 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Pass Independent runs Scores from the official leaderboard (16 entries).
- Pass Models scored 16 models we track.
- Pass Newest score The newest is from October 2026, for Kimi K3.1 Pro.
- Pass Frontier models 6 of the top 10 have a score, led by GPT-6 Astra (#4).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on tis-100.wincon.dev: 16 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.