Benchmark Almanac

TIS-100 Bench

GPT-6 Astra 11.0 leads since November 2026
Not in model cards

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
In and out
Text, Code → Code, Actions
Interaction
Agentic
Environment
TIS-100
Refresh
One fixed set
Run by
Anyone
In views
Games, Agents
Strongest model tested
GPT-6 Astra #4 on the capability index
Last model added
October 2026
Scores refreshed
November 20th, 2026
16
Models scored on its own leaderboard

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.

  1. 1 GPT-6 Astra 11.0
  2. 2 Claude Opus 5.5 11.0
  3. 3 Gemini 4 Argon 8.00
  4. 4 Claude Sonnet 5.5 7.00
  5. 5 GPT-6.1 Sol 6.00
  6. 6 Claude Fable 5.1 5.00
  7. 7 Kimi K3.1 Pro 2.00
  8. 8 GLM-5.3 1.00
  9. 9 Gemini 3.8 Flash 1.00
  10. 10 Claude Haiku 5.5 1.00
  11. 11 Muse Wonder 1.00
  12. 12 Muse Spark 1.3 0.00
  13. 13 DeepSeek V4.1 Flash 0.00
  14. 14 Grok 4.7 0.00
  15. 15 MiMo-V2.6 Pro 0.00
  16. 16 GPT-6 Luna 0.00

Source: Official TIS-100 Bench leaderboard

#ModelScoreSettingDateSource
1 GPT-6 Astra 11.0 Sep 2026 Official leaderboard
2 Claude Opus 5.5 11.0 Sep 2026 Official leaderboard
3 Gemini 4 Argon 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 Gemini 3.8 Flash 1.00 Sep 2026 Official leaderboard
10 Claude Haiku 5.5 1.00 Oct 2026 Official leaderboard
11 Muse Wonder 1.00 Oct 2026 Official leaderboard
12 Muse Spark 1.3 0.00 Sep 2026 Official leaderboard
13 DeepSeek V4.1 Flash 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. 1 Claude Opus 5.5 ↑1 72.0
  2. 2 GPT-6 Astra ↓1 32.0
  3. 3 Gemini 4 Argon 28.0
  4. 4 Claude Fable 5.1 ↑2 19.0
  5. 5 Claude Sonnet 5.5 ↓1 14.0
  6. 6 GPT-6.1 Sol ↓1 12.0
  7. 7 Kimi K3.1 Pro 5.00
  8. 8 GLM-5.3 1.00
  9. 9 Gemini 3.8 Flash 1.00
  10. 10 Claude Haiku 5.5 1.00

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI
Own leaderboard 1 leader

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.

Plot with other benchmarks
On the benchmark’s own leaderboard
0.00 2.50 5.00 7.50 10.0 12.5 2027 0.00 2.50 5.00 7.50 10.0 12.5 2027

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

All 523 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.

How we check