Benchmark Almanac

Samskritam Bench v1

Claude Opus 5.5 89.4% leads since October 2026
Not in model cards
Version 1

Models split entire Sanskrit verses into words, parse inflected words, scan verse meter, and generate rare verb forms. Each verse requires every graded part to match.

Samskritam.ai scores six models on 340 private questions. The preview reports zero reviewed questions as of October 23, 2026.

Released
October 2026
Kind
Reading in many languages
Level
University
Scored
Checked automatically
Answers
Short answer
Tasks
Kept private
Measures
Capability
Language
Sanskrit
In and out
Text → Text
Interaction
Single turn
Run by
A host
Strongest model tested
Claude Opus 5.5 #5 on the capability index
Last model added
September 2026
Scores refreshed
November 20th, 2026
6
Models scored on its own leaderboard

Claude Opus 5.5 leads with 89.4% 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 Claude Opus 5.5 89.4%
  2. 2 Gemini 3.8 Flash 78.8%
  3. 3 GPT-6 Sol 77.9%
  4. 4 Claude Sonnet 5.5 72.9%
  5. 5 Gemini 4 Argon 71.8%
  6. 6 Sarvam 105B reasoning off 14.4%

Source: Official Samskritam Bench v1 leaderboard

#ModelScoreSettingDateSource
1 Claude Opus 5.5 89.4% Sep 2026 Official leaderboard
2 Gemini 3.8 Flash 78.8% Sep 2026 Official leaderboard
3 GPT-6 Sol 77.9% Sep 2026 Official leaderboard
4 Claude Sonnet 5.5 72.9% Sep 2026 Official leaderboard
5 Gemini 4 Argon 71.8% Sep 2026 Official leaderboard
6 Sarvam 105B 14.4% reasoning off Mar 2026 Official leaderboard

Rankings by part

We read 4 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as padapatha, parse and scan. Gemini 3.8 Flash leads 2 of them, and Claude Opus 5.5 leads the other 2. Arrows show how far a model moved from its overall rank among the models we track.

padapatha

6 models we track have a score here.

  1. 1 Gemini 3.8 Flash ↑1 81.1%
  2. 2 Claude Opus 5.5 ↓1 81.1%
  3. 3 Gemini 4 Argon ↑2 77.8%
  4. 4 GPT-6 Sol ↓1 76.7%
  5. 5 Claude Sonnet 5.5 ↓1 76.7%
  6. 6 Sarvam 105B 18.9%

Number one over time

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

Anthropic
Own leaderboard Passed 85% in Oct 2026, by Claude Opus 5.5

Source: Official Samskritam Bench v1 leaderboard

Claude Opus 5.5 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% 2026 Near the ceiling (85%) Claude Opus 5.5 Gemini 3.8 Flash Sarvam 105B 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Opus 5.5 Gemini 3.8 Flash

Source: Official Samskritam Bench v1 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.

Versions

We switch the top row to each new version when it comes out. Open it for one row per version. An old version stays in play while people still test it, so whoever first takes it past 85% gets credit for closing it out.

Anthropic
Samskritam Bench v1 Passed 85% in Oct 2026, by Claude Opus 5.5
Samskritam Bench v0 Passed 85% in Oct 2026, by Claude Opus 5.5
Samskritam Bench v1 Passed 85% in Oct 2026, by Claude Opus 5.5

Source: Official leaderboards

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 The tasks are private.
  • Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (6 entries).
  • Pass Models scored 6 models we track.
  • Pass Newest score The newest is from September 2026, for Gemini 4 Argon.
  • Pass Frontier models 3 of the top 10 have a score, led by Claude Opus 5.5 (#5).
  • Note Headroom Saturated. The best is 89.4%, past 85% since September 2026.
Leaderboard import 3 pass
  • Pass Importer We read the board on samskritam.ai: 6 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