History

Archaic and historical translation

Translate older or domain-specific language into modern equivalents.

task.translate_technicaltask.glossary_terminology_consistency

Evidence quality is currently limited for this use case. Rankings below are useful for exploration, not a strong winner claim.

Provisional leader

claude-sonnet-4

Current leader based on limited benchmark evidence. Treat this ranking as directional until coverage improves.

34.1%

Best benchmark score

45.1%

Confidence

All ranked models — top 3

🥇

claude-sonnet-4

34.1%

🥈

gemini-2.5-flash

32.6%

🥉

Claude-3.5-Sonnet

27.2%

Ranked Models

Evidence Quality

82%

Evidence Points

Top Signal

LanguageBench Translation Official (Split): translation_to:bleu

All Ranked Models

30 of 30 models

Rank	Model	Score	Confidence	Price / 1M	Evidence sources
🥇	claude-sonnet-4 Strong on LanguageBench Translation Official (Split) translation_to:bleu and LanguageBench overall:mean	34.1%	45%	$6.00	LanguageBench Translation Official (Split)LanguageBench
🥈	gemini-2.5-flash Strong on LanguageBench Translation Official (Split) translation_to:bleu and LanguageBench overall:mean	32.6%	38%	$0.17	LanguageBench Translation Official (Split)LanguageBench
#5	Claude-3.5-Sonnet Strong on LanguageBench Translation Official (Split) translation_to:bleu and LanguageBench overall:mean	27.2%	40%	$6.00	LanguageBench Translation Official (Split)LanguageBench
#6	gemini-2.0-flash-001 Strong on LanguageBench Translation Official (Split) translation_to:bleu and LanguageBench overall:mean	26.7%	31%	—	LanguageBench Translation Official (Split)LanguageBench
#7	gpt-4.1 Strong on LanguageBench Translation Official (Split) translation_to:bleu and LanguageBench overall:mean	26.2%	33%	$3.50	LanguageBench Translation Official (Split)LanguageBench
#15	gpt-4.1-20250414 Strong on OpenVLM OCRBench Official ocrbench_score_pct and OpenVLM TextVQA Official textvqa_score_pct	19.0%	28%	—	OpenVLM OCRBench OfficialOpenVLM TextVQA Official
#17	Llama-3.3-70B-Instruct Strong on LanguageBench Translation Official (Split) translation_to:bleu and LanguageBench overall:mean	18.3%	28%	—	LanguageBench Translation Official (Split)LanguageBench
#18	gpt-5-2025-08-07 Strong on OpenVLM OCRBench Official ocrbench_score_pct and Icelandic LLM Leaderboard Average ⬆️	17.1%	22%	—	OpenVLM OCRBench OfficialIcelandic LLM Leaderboard
#19	Llama-3.1-70B-Instruct Strong on LanguageBench Translation Official (Split) translation_to:bleu and LanguageBench overall:mean	17.1%	34%	—	LanguageBench Translation Official (Split)LanguageBench
#22	gemini-2.5-pro Strong on OpenVLM OCRBench Official ocrbench_score_pct and LanguageBench Translation Official (Split) translation_to:bleu	15.7%	44%	$3.44	OpenVLM OCRBench OfficialLanguageBench Translation Official (Split)
#23	gpt-4.1-mini-20250414 Strong on OpenVLM OCRBench Official ocrbench_score_pct and OpenVLM MTVQA Official mtvqa_score_pct	15.7%	23%	—	OpenVLM OCRBench OfficialOpenVLM MTVQA Official
#24	deepseek-r1 Strong on LanguageBench Translation Official (Split) translation_to:bleu and LanguageBench overall:mean	14.7%	33%	$0.27	LanguageBench Translation Official (Split)LanguageBench
#27	gpt-5-mini-2025-08-07 Strong on OpenVLM OCRBench Official ocrbench_score_pct and Icelandic LLM Leaderboard Average ⬆️	13.6%	19%	—	OpenVLM OCRBench OfficialIcelandic LLM Leaderboard
#31	gemini-3.1-pro-preview Strong on Icelandic LLM Leaderboard Average ⬆️ and Vals MedCode overall_accuracy_pct	12.7%	14%	$4.50	Icelandic LLM LeaderboardVals MedCode
#33	gemini-3-pro-preview Strong on Humanity's Last Exam Leaderboard hle_accuracy_pct and Icelandic LLM Leaderboard Average ⬆️	12.4%	16%	$4.50	Humanity's Last Exam LeaderboardIcelandic LLM Leaderboard
#38	phi-4 Strong on LanguageBench overall:mean and LanguageBench Translation Official (Split) translation_to:bleu	10.9%	27%	—	LanguageBenchLanguageBench Translation Official (Split)
#43	gemini-3-flash-preview Strong on Icelandic LLM Leaderboard Average ⬆️ and Vals Legal Bench overall_accuracy_pct	10.6%	13%	$1.13	Icelandic LLM LeaderboardVals Legal Bench
#48	gpt-5.4-2026-03-05 Strong on Icelandic LLM Leaderboard Average ⬆️ and Vectara HHEM Leaderboard overall_hallucination_error_pct	10.0%	12%	—	Icelandic LLM LeaderboardVectara HHEM Leaderboard
#50	gpt-5.2-2025-12-11 Strong on Humanity's Last Exam Leaderboard hle_accuracy_pct and FACTS Benchmark Suite facts_grounding_score_pct	9.9%	12%	—	Humanity's Last Exam LeaderboardFACTS Benchmark Suite
#53	Grok-4-0709 Strong on Galileo Agent Leaderboard v2 Avg TSQ and Galileo Agent Leaderboard v2 Avg AC	9.8%	14%	—	Galileo Agent Leaderboard v2Galileo Agent Leaderboard v2
#55	gpt-5.1-2025-11-13 Strong on Icelandic LLM Leaderboard Average ⬆️ and Vals MedScribe overall_accuracy_pct	9.8%	12%	—	Icelandic LLM LeaderboardVals MedScribe
#57	kimi-k2.5-thinking Strong on Icelandic LLM Leaderboard Average ⬆️ and Humanity's Last Exam Leaderboard hle_accuracy_pct	9.7%	14%	—	Icelandic LLM LeaderboardHumanity's Last Exam Leaderboard
#60	claude-sonnet-4.6 Strong on Icelandic LLM Leaderboard Average ⬆️ and Vals Tax Eval v2 overall_accuracy_pct	9.5%	12%	$6.00	Icelandic LLM LeaderboardVals Tax Eval v2
#61	gemini-3.1-flash-lite-preview Strong on Icelandic LLM Leaderboard Average ⬆️ and Vals Mortgage Tax overall_accuracy_pct	9.3%	15%	$0.56	Icelandic LLM LeaderboardVals Mortgage Tax
#66	claude-opus-4-5-20251101 Strong on Icelandic LLM Leaderboard Average ⬆️ and Vals Mortgage Tax overall_accuracy_pct	9.0%	11%	—	Icelandic LLM LeaderboardVals Mortgage Tax
#69	o3-20250416 Strong on Aider Polyglot Leaderboard percent_correct_pct and Vals MedQA overall_accuracy_pct	8.8%	12%	$3.50	Aider Polyglot LeaderboardVals MedQA
#73	claude-opus-4-5-20251101-thinking Strong on Humanity's Last Exam Leaderboard hle_accuracy_pct and Vals MedQA overall_accuracy_pct	8.5%	11%	—	Humanity's Last Exam LeaderboardVals MedQA
#76	gpt-4o Strong on OpenVLM OCRBench Official ocrbench_score_pct and OpenVLM MTVQA Official mtvqa_score_pct	8.3%	11%	$0.26	OpenVLM OCRBench OfficialOpenVLM MTVQA Official
#83	o4-mini Strong on Icelandic LLM Leaderboard Average ⬆️ and Aider Polyglot Leaderboard percent_correct_pct	8.1%	12%	$1.93	Icelandic LLM LeaderboardAider Polyglot Leaderboard
#90	GPT-4.1-nano-2025-04-14 Strong on OpenVLM OCRBench Official ocrbench_score_pct and OpenVLM MTVQA Official mtvqa_score_pct	7.8%	15%	—	OpenVLM OCRBench OfficialOpenVLM MTVQA Official

Compare Models

Select two different models above to compare their evidence side by side.

▶Ranking diagnostics & missing models

Source lift

Ranked

Sources

Quality

Low

Vals Legal Bench

25 rows · 0.5% avg lift

Vals MedQA

24 rows · 0.5% avg lift

Vals Mortgage Tax

24 rows · 0.5% avg lift

Vals Tax Eval v2

24 rows · 0.5% avg lift

Missing frontier models

grok-4-1-fast-reasoning

Thin evidence after weighting

Rank #12

19.5%

grok-4-1-fast-non-reasoning

Thin evidence after weighting

Rank #15

14.9%

▶Taxonomy & task details

Core tasks

task.translate_technicaltask.glossary_terminology_consistency

Required modes

mode.multilingualmode.format_preservation

Domains

domain.history_linguistics

Related in History

Historical document summarization

Summarize historical documents into timelines and key entities.