Benchmark Almanac

Sinhala Language Proficiency & Linguistic Mastery

GPT-6 Astra 95.9 leads since November 2026
Not in model cards

Models answer Sinhala prompts about grammar, style, conversation, and literature. Three judges score the responses without seeing the model names.

Kaggle publishes scores for 15 distinct model versions.

Made by
Nadew Damruwan
Released
November 2026
Kind
Chat and instructions in many languages
Level
School
Scored
Graded by a model
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
Sinhala
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Strongest model tested
GPT-6 Astra #4 on the capability index
Last model added
September 2026
Scores refreshed
November 20th, 2026
15
Models scored on its own leaderboard

GPT-6 Astra leads with 95.9 among models released by September 2026

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.

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 GPT-6 Astra 95.9
  2. 2 GPT-6.1 Sol 93.7
  3. 3 Gemini 2.5 Flash Sep 2025 91.4
  4. 4 GPT-5.4 91.4
  5. 5 Gemini 4 Argon 91.3
  6. 6 Gemini 2.5 Pro Jun 2025 91.1
  7. 7 Claude Opus 5.5 90.8
  8. 8 Claude Sonnet 5.5 90.0
  9. 9 GPT-6 Luna 89.4
  10. 10 Gemini 3.8 Flash 89.1
  11. 11 Claude Opus 5 88.8
  12. 12 GPT-5.6 Terra 88.6
  13. 13 Gemini 3.6 Flash 83.3
  14. 14 Grok 4.7 82.0
  15. 15 Grok 4.6 79.7

Source: Official Sinhala Language Proficiency & Linguistic Mastery leaderboard

#ModelScoreSettingReleasedRun onSource
1 GPT-6 Astra 95.9 Sep 2026 Nov 2026 Official leaderboard
2 GPT-6.1 Sol 93.7 Sep 2026 Nov 2026 Official leaderboard
3 Gemini 2.5 Flash Sep 2025 91.4 Sep 2025 Nov 2026 Official leaderboard
4 GPT-5.4 91.4 Mar 2026 Nov 2026 Official leaderboard
5 Gemini 4 Argon 91.3 Sep 2026 Nov 2026 Official leaderboard
6 Gemini 2.5 Pro Jun 2025 91.1 Jun 2025 Nov 2026 Official leaderboard
7 Claude Opus 5.5 90.8 Sep 2026 Nov 2026 Official leaderboard
8 Claude Sonnet 5.5 90.0 Sep 2026 Nov 2026 Official leaderboard
9 GPT-6 Luna 89.4 Sep 2026 Nov 2026 Official leaderboard
10 Gemini 3.8 Flash 89.1 Sep 2026 Nov 2026 Official leaderboard
11 Claude Opus 5 88.8 Jul 2026 Nov 2026 Official leaderboard
12 GPT-5.6 Terra 88.6 Jul 2026 Nov 2026 Official leaderboard
13 Gemini 3.6 Flash 83.3 Jul 2026 Nov 2026 Official leaderboard
14 Grok 4.7 82.0 Sep 2026 Nov 2026 Official leaderboard
15 Grok 4.6 79.7 Aug 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 1 leader

Source: Official Sinhala Language Proficiency & Linguistic Mastery 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
75.0 80.0 85.0 90.0 95.0 100.0 2025 2026 75.0 80.0 85.0 90.0 95.0 100.0 2025 2026

Source: Official Sinhala Language Proficiency & Linguistic Mastery 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 Multilingual

All 545 in Multilingual
  • MMMLU In use MMLU professionally translated into 14 languages. Multiple-choice accuracy. Claude Mythos Preview 92.7%
  • WMT24++ In use English-to-55-language translation of WMT24 test data. Scored with automatic metrics such as MetricX or xCOMET. K-EXAONE 90.5%
  • MMLU-ProX In use MMLU-Pro translated into up to 29 languages with expert review. Multiple-choice accuracy per language. Qwen3.7-Max 87%
  • CLIcK In use Models answer 1,995 multiple-choice questions on Korean language and culture. Questions come from official Korean exams and textbooks in eleven categories. Solar Open 2 90.7%
  • Global MMLU Lite 3.0 In use Models answer 400 human-translated MMLU questions per language in 23 languages. Version 3.0 adds Czech, Hungarian, Oriya, Slovak and Tajik and updates Italian. Accuracy. Claude Opus 5 95.7%
  • MMMB In use Models answer multiple-choice questions about images in six languages across 15 categories. The set has about 12,000 questions. LFM2.5-VL-3B 83%

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 (15 entries).
  • Pass Models scored 15 models we track.
  • Pass Newest score The newest is from September 2026, for Gemini 4 Argon.
  • Pass Frontier models 5 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 kaggle.com: 15 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