Benchmark Almanac

Basic reasoning with letters

GLM-5 100% leads since October 2026
Not in model cards

Models count and compare letters within words. The tasks include counting a letter across weekday names and finding words with equal character frequencies.

Kaggle publishes scores for 13 distinct model versions.

Made by
Navneet Prabhat
Released
October 2026
Kind
Language reasoning
Level
School
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Strongest model tested
Claude Sonnet 5.5 #9 on the capability index
Last model added
September 2026
Scores refreshed
November 20th, 2026
13
Entries on its own leaderboard, 11 models we track

3 models share the top score of 100% among models released by September 2026 3 models share the top score of 100% among models released by September 2026

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. 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.

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:

  1. 1 GLM-5 100%
  2. 2 GPT-6 Luna 100%
  3. 3 Claude Sonnet 5.5 100%
  4. 4 Gemma 4 31B IT 75%
  5. 5 Gemini 4 Argon 75%
  6. 6 DeepSeek-R1 May 2025 66.7%
  7. 7 Grok 4.6 50%
  8. 8 Qwen 3 235B A22B Instruct 2506 33.3%
  9. 9 Qwen 3 Next 80B Instruct 33.3%
  10. 10 Claude Opus 4.8 25%
  11. 11 Gemini 3.5 Flash-Lite 25%
  12. 12 Gemini 2.5 Flash Sep 2025 0%
  13. 13 Claude Haiku 4.5 0%

Source: Official Basic reasoning with letters leaderboard

#EntryScoreSettingReleasedRun onSource
1 GLM-5 100% Feb 2026 Oct 2026 Official leaderboard
2 GPT-6 Luna 100% Sep 2026 Nov 2026 Official leaderboard
3 Claude Sonnet 5.5 100% Sep 2026 Nov 2026 Official leaderboard
4 Gemma 4 31B IT 75% Apr 2026 Nov 2026 Official leaderboard
5 Gemini 4 Argon 75% Sep 2026 Nov 2026 Official leaderboard
6 DeepSeek-R1 May 2025 66.7% May 2025 Oct 2026 Official leaderboard
7 Grok 4.6 50% Aug 2026 Nov 2026 Official leaderboard
8 Qwen 3 235B A22B Instruct 2506 33.3% Oct 2026 Official leaderboard
9 Qwen 3 Next 80B Instruct 33.3% Oct 2026 Official leaderboard
10 Claude Opus 4.8 25% May 2026 Nov 2026 Official leaderboard
11 Gemini 3.5 Flash-Lite 25% Jul 2026 Nov 2026 Official leaderboard
12 Gemini 2.5 Flash Sep 2025 0% Sep 2025 Nov 2026 Official leaderboard
13 Claude Haiku 4.5 0% Oct 2025 Nov 2026 Official leaderboard
#ModelScoreSettingReleasedRun onSource
1 GLM-5 100% Feb 2026 Oct 2026 Official leaderboard
2 GPT-6 Luna 100% Sep 2026 Nov 2026 Official leaderboard
3 Claude Sonnet 5.5 100% Sep 2026 Nov 2026 Official leaderboard
4 Gemma 4 31B IT 75% Apr 2026 Nov 2026 Official leaderboard
5 Gemini 4 Argon 75% Sep 2026 Nov 2026 Official leaderboard
6 DeepSeek-R1 May 2025 66.7% May 2025 Oct 2026 Official leaderboard
7 Grok 4.6 50% Aug 2026 Nov 2026 Official leaderboard
8 Claude Opus 4.8 25% May 2026 Nov 2026 Official leaderboard
9 Gemini 3.5 Flash-Lite 25% Jul 2026 Nov 2026 Official leaderboard
10 Gemini 2.5 Flash Sep 2025 0% Sep 2025 Nov 2026 Official leaderboard
11 Claude Haiku 4.5 0% Oct 2025 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.

Z.ai
Own leaderboard Passed 85% in Oct 2026, by GLM-5
GLM-5 100%

Source: Official Basic reasoning with letters leaderboard

GLM-5 on the official leaderboard passed 85% in February 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 Near the ceiling (85%) GLM-5 DeepSeek-R1 0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) GLM-5 DeepSeek-R1

Source: Official Basic reasoning with letters 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 Knowledge

All 332 in Knowledge
  • MMLU-Pro In use Harder 10-option version of MMLU with reasoning-focused questions across 14 subjects. Intern-S2-397B 89.8%
  • MMLU In use 57-subject multiple-choice exam questions from elementary to professional level. Scored by accuracy. Seed1.8 92.3%
  • SuperGPQA In use 26,529 graduate-level multiple-choice questions across 285 disciplines. Accuracy. Qwen 3.6 Max (Preview) 73.9%
  • WideSearch In use 200 bilingual broad info-seeking tasks: agent collects many atomic facts into a table. Scored by success rate and row/item F1. Tencent Hy4 preview 83.9%
  • BBEH micro average In use Models solve harder replacements for each of the 23 BIG-Bench Hard tasks, 4,520 examples in total. The score is the share of all examples answered correctly. Gemma 4 31B IT 74.4%
  • HLE-Diamond In use Models answer 1,000 cleaned expert questions from Humanity's Last Exam, 500 on reasoning and 500 on knowledge, closed book. Graded on exact answers. Claude Fable 5.2 77.9%

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 official leaderboard (13 entries).
  • Pass Models scored 11 models we track, plus 2 other entries on its leaderboard.
  • Pass Newest score The newest is from September 2026, for Gemini 4 Argon.
  • Note Frontier models 2 of the top 10 have a score, which is fine for a retired test. The strongest tested is Claude Sonnet 5.5 (#9).
  • Note Headroom Saturated. The best is 100%, past 85% since February 2026.
Leaderboard import 3 pass
  • Pass Importer We read the board on kaggle.com: 11 rows for models we track and 2 other entries 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