Benchmark Almanac

LLM Round-Trip Translation Benchmark

GPT-5 8.69 leads since August 2025
Not in model cards

Models translate text into another language and back. The evaluation measures how well the original meaning survives.

The author publishes the model comparison in the repository.

Made by
Lech Mazur
Kind
Translation
Level
University
Scored
Graded by a model
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
Many languages
In and out
Text → Text
Interaction
Multi-turn
Refresh
One fixed set
Run by
Anyone
In views
Many languages
Strongest model tested
GPT-5 #71 on the capability index
Last model added
September 2025
Scores refreshed
November 20th, 2026
8
Entries on its own leaderboard, 7 models we track

GPT-5 leads with 8.69 among models released by September 2025 GPT-5 leads with 8.69 among models released by September 2025

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 2025, 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-5 medium reasoning 8.69
  2. 2 Grok 4 8.57
  3. 3 Claude Opus 4.1 no reasoning 8.56
  4. 4 Gemini 2.5 Pro Jun 2025 8.53
  5. 5 Qwen3-Max-Preview 8.32
  6. 6 DeepSeek V3.1 Reasoner 8.30
  7. 7 Mistral Medium 3.1 8.29
  8. 8 Kimi K2 Sep 2025 8.28

Source: Official LLM Round-Trip Translation Benchmark leaderboard

#EntryScore ±SettingDateSource
1 GPT-5 8.69 ±0 medium reasoning Aug 2025 Official leaderboard
2 Grok 4 8.57 ±0 Jul 2025 Official leaderboard
3 Claude Opus 4.1 8.56 ±0 no reasoning Aug 2025 Official leaderboard
4 Gemini 2.5 Pro Jun 2025 8.53 ±0 Jun 2025 Official leaderboard
5 Qwen3-Max-Preview 8.32 ±0.1 Sep 2025 Official leaderboard
6 DeepSeek V3.1 Reasoner 8.30 ±0 Official leaderboard
7 Mistral Medium 3.1 8.29 ±0.1 Aug 2025 Official leaderboard
8 Kimi K2 Sep 2025 8.28 ±0 Sep 2025 Official leaderboard
#ModelScore ±SettingDateSource
1 GPT-5 8.69 ±0 medium reasoning Aug 2025 Official leaderboard
2 Grok 4 8.57 ±0 Jul 2025 Official leaderboard
3 Claude Opus 4.1 8.56 ±0 no reasoning Aug 2025 Official leaderboard
4 Gemini 2.5 Pro Jun 2025 8.53 ±0 Jun 2025 Official leaderboard
5 Qwen3-Max-Preview 8.32 ±0.1 Sep 2025 Official leaderboard
6 Mistral Medium 3.1 8.29 ±0.1 Aug 2025 Official leaderboard
7 Kimi K2 Sep 2025 8.28 ±0 Sep 2025 Official leaderboard

Rankings by part

We read 10 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Arabic, Chinese and Spanish. GPT-5 leads 9 of them, and Grok 4 leads the other one. Arrows show how far a model moved from its overall rank among the models we track.

Arabic

7 models we track have a score here.

  1. 1 GPT-5 8.69
  2. 2 Claude Opus 4.1 ↑1 8.62
  3. 3 Gemini 2.5 Pro Jun 2025 ↑1 8.57
  4. 4 Grok 4 ↓2 8.43
  5. 5 Qwen3-Max-Preview 8.37
  6. 6 Mistral Medium 3.1 8.29
  7. 7 Kimi K2 Sep 2025 8.25

3 models have held number one on the official leaderboard since 2023

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

Google DeepMind xAI OpenAI
Own leaderboard Not tested since Sep 2025
GPT-5 8.69

Source: Official LLM Round-Trip Translation Benchmark 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
8.20 8.30 8.40 8.50 8.60 8.70 2025 8.20 8.30 8.40 8.50 8.60 8.70 2025

Source: Official LLM Round-Trip Translation 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 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

8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 14 months ago, in September 2025, for Kimi K2. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (8 entries).
  • Pass Models scored 7 models we track, plus 1 other entry on its leaderboard.
  • Warning Newest score The newest came 14 months ago, in September 2025, for Kimi K2.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5 (#71).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 7 rows for models we track and 1 other entry 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