Benchmark Almanac

Brainf**k coding benchmark

GPT-6 Astra 100% leads since November 2026
Not in model cards

Models write Brainfuck programs for tasks such as copying input and adding digits. Tests check the output of each program.

Kaggle publishes scores for 18 distinct model versions.

Made by
Pedro Schoen
Released
November 2026
Kind
Function-level problems
Level
University
Scored
Checked automatically
Answers
Code
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Code
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Strongest model tested
GPT-6 Astra #4 on the capability index
Last model added
November 2026
Scores refreshed
November 20th, 2026
19
Models scored on its own leaderboard

4 models share the top score of 100%

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 100%
  2. 2 Grok 4.7 100%
  3. 3 Claude Opus 5.5 100%
  4. 4 GPT-6.1 Sol 100%
  5. 5 Claude Sonnet 5.5 99.6%
  6. 6 GPT-6.2 Sol 89.3%
  7. 7 GPT-6 Sol 78.3%
  8. 8 Gemini 3.8 Flash 77.1%
  9. 9 Gemini 3 Flash 69.9%
  10. 10 GPT-6 Luna 61.3%
  11. 11 Claude Sonnet 5 57.1%
  12. 12 Gemini 2.5 Pro Jun 2025 53.3%
  13. 13 Claude Haiku 5.5 53.3%
  14. 14 Gemma 4 26B A4B 50%
  15. 15 Gemini 2.5 Flash Sep 2025 41%
  16. 16 gpt-oss-120b 40%
  17. 17 Claude Haiku 4.5 20%
  18. 18 GPT-5.4 Mini 13.3%
  19. 19 GPT-5.4 Nano 6.67%

Source: Official Brainf**k coding benchmark leaderboard

#ModelScoreSettingReleasedRun onSource
1 GPT-6 Astra 100% Sep 2026 Nov 2026 Official leaderboard
2 Grok 4.7 100% Sep 2026 Nov 2026 Official leaderboard
3 Claude Opus 5.5 100% Sep 2026 Nov 2026 Official leaderboard
4 GPT-6.1 Sol 100% Sep 2026 Nov 2026 Official leaderboard
5 Claude Sonnet 5.5 99.6% Sep 2026 Nov 2026 Official leaderboard
6 GPT-6.2 Sol 89.3% Nov 2026 Nov 2026 Official leaderboard
7 GPT-6 Sol 78.3% Sep 2026 Nov 2026 Official leaderboard
8 Gemini 3.8 Flash 77.1% Sep 2026 Nov 2026 Official leaderboard
9 Gemini 3 Flash 69.9% Dec 2025 Nov 2026 Official leaderboard
10 GPT-6 Luna 61.3% Sep 2026 Nov 2026 Official leaderboard
11 Claude Sonnet 5 57.1% Jun 2026 Nov 2026 Official leaderboard
12 Gemini 2.5 Pro Jun 2025 53.3% Jun 2025 Nov 2026 Official leaderboard
13 Claude Haiku 5.5 53.3% Oct 2026 Nov 2026 Official leaderboard
14 Gemma 4 26B A4B 50% Apr 2026 Nov 2026 Official leaderboard
15 Gemini 2.5 Flash Sep 2025 41% Sep 2025 Nov 2026 Official leaderboard
16 gpt-oss-120b 40% Aug 2025 Nov 2026 Official leaderboard
17 Claude Haiku 4.5 20% Oct 2025 Nov 2026 Official leaderboard
18 GPT-5.4 Mini 13.3% Mar 2026 Nov 2026 Official leaderboard
19 GPT-5.4 Nano 6.67% Mar 2026 Nov 2026 Official leaderboard

Number one over time

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

OpenAI
Own leaderboard Passed 85% in Nov 2026, by GPT-6 Astra

Source: Official Brainf**k coding benchmark leaderboard

GPT-6 Astra on the official leaderboard passed 85% in September 2026

Models released before it came out already scored that high. 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 Best so far
0% 20% 40% 60% 80% 100% 2025 2026 2027 Near the ceiling (85%) GPT-6 Astra Gemini 3.8 Flash Gemini 3 Flash Gemini 2.5 Pro 0% 20% 40% 60% 80% 100% 2025 2026 2027 Near the ceiling (85%) GPT-6 Astra Gemini 3.8 Flash

Source: Official Brainf**k coding benchmark 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 (19 entries).
  • Pass Models scored 19 models we track.
  • Pass Newest score The newest is from November 2026, for GPT-6.2 Sol.
  • Pass Frontier models 4 of the top 10 have a score, led by GPT-6 Astra (#4).
  • Note Headroom Saturated. The best is 100%, past 85% since September 2026.
Leaderboard import 3 pass
  • Pass Importer We read the board on kaggle.com: 19 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