Productivity

Cross-lingual summary

Summarize a document in one language into another language.

task.cross_lingual_summarization

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.

26.5%

Best benchmark score

36.4%

Confidence

All ranked models — top 3

🥇

claude-sonnet-4

26.5%

🥈

gemini-2.5-flash

25.7%

🥉

gemini-3.1-pro-preview

24.8%

Ranked Models

Evidence Quality

81%

Evidence Points

Top Signal

LanguageBench: overall:mean

All Ranked Models

30 of 30 models

Rank	Model	Score	Confidence	Price / 1M	Evidence sources
🥇	claude-sonnet-4 Strong on LanguageBench overall:mean and Galileo Agent Leaderboard v2 Avg TSQ	26.5%	36%	$6.00	LanguageBenchGalileo Agent Leaderboard v2
🥈	gemini-2.5-flash Strong on LanguageBench overall:mean and Galileo Agent Leaderboard v2 Avg TSQ	25.7%	36%	$0.17	LanguageBenchGalileo Agent Leaderboard v2
🥉	gemini-3.1-pro-preview Strong on Vals Finance Agent overall_accuracy_pct and SimpleQA Verified simpleqa_verified_score_pct	24.8%	29%	$4.50	Vals Finance AgentSimpleQA Verified
#4	gemini-2.5-pro Strong on Galileo Agent Leaderboard v2 Avg TSQ and FACTS Benchmark Suite facts_grounding_score_pct	23.2%	44%	$3.44	Galileo Agent Leaderboard v2FACTS Benchmark Suite
#5	gpt-4.1-20250414 Strong on MMLongBench-Doc Leaderboard acc_score_pct and Galileo Agent Leaderboard v2 Avg TSQ	20.8%	31%	—	MMLongBench-Doc LeaderboardGalileo Agent Leaderboard v2
#6	gpt-5-2025-08-07 Strong on Vals Finance Agent overall_accuracy_pct and FACTS Benchmark Suite facts_grounding_score_pct	20.6%	27%	—	Vals Finance AgentFACTS Benchmark Suite
#7	gpt-5-mini-2025-08-07 Strong on Vals Finance Agent overall_accuracy_pct and Vals Finance Agent complex_retrieval_accuracy_pct	20.1%	31%	—	Vals Finance AgentVals Finance Agent
#8	Grok-4-0709 Strong on Galileo Agent Leaderboard v2 Avg TSQ and Vals Finance Agent overall_accuracy_pct	19.9%	30%	—	Galileo Agent Leaderboard v2Vals Finance Agent
#9	gemini-3-pro-preview Strong on Vals Finance Agent overall_accuracy_pct and SimpleQA Verified simpleqa_verified_score_pct	19.6%	28%	$4.50	Vals Finance AgentSimpleQA Verified
#10	gpt-5.2-2025-12-11 Strong on Vals Finance Agent overall_accuracy_pct and FACTS Benchmark Suite facts_grounding_score_pct	18.1%	22%	—	Vals Finance AgentFACTS Benchmark Suite
#11	claude-sonnet-4.6 Strong on Vals Finance Agent overall_accuracy_pct and Vals Finance Agent complex_retrieval_accuracy_pct	17.6%	23%	$6.00	Vals Finance AgentVals Finance Agent
#12	gemini-3.1-flash-lite-preview Strong on Vals Finance Agent overall_accuracy_pct and Vals Mortgage Tax overall_accuracy_pct	17.0%	25%	$0.56	Vals Finance AgentVals Mortgage Tax
#13	gpt-5.4-2026-03-05 Strong on Vals Finance Agent overall_accuracy_pct and Vals Mortgage Tax overall_accuracy_pct	17.0%	22%	—	Vals Finance AgentVals Mortgage Tax
#14	Claude-3.5-Sonnet Strong on LanguageBench overall:mean and LanguageBench Translation Official (Split) translation_to:bleu	16.7%	23%	$6.00	LanguageBenchLanguageBench Translation Official (Split)
#15	gemini-3-flash-preview Strong on Vals Finance Agent overall_accuracy_pct and FACTS Benchmark Suite average_score_pct	16.1%	24%	$1.13	Vals Finance AgentFACTS Benchmark Suite
#16	gpt-5.1-2025-11-13 Strong on Vals Finance Agent overall_accuracy_pct and Vals Case Law v2 overall_accuracy_pct	15.3%	23%	—	Vals Finance AgentVals Case Law v2
#17	claude-opus-4-5-20251101 Strong on Vals Mortgage Tax overall_accuracy_pct and FACTS Benchmark Suite facts_grounding_score_pct	14.7%	23%	—	Vals Mortgage TaxFACTS Benchmark Suite
#18	gemini-2.0-flash-001 Strong on LanguageBench overall:mean and LanguageBench Translation Official (Split) translation_to:bleu	14.3%	17%	—	LanguageBenchLanguageBench Translation Official (Split)
#19	o3-20250416 Strong on Vals Mortgage Tax overall_accuracy_pct and SciArena Leaderboard rating_elo	14.1%	22%	$3.50	Vals Mortgage TaxSciArena Leaderboard
#20	gpt-4.1 Strong on LanguageBench overall:mean and LanguageBench Grammar/Clarity Official (Split) grammar_clarity_score_pct	14.0%	17%	$3.50	LanguageBenchLanguageBench Grammar/Clarity Official (Split)
#23	grok-4-fast-reasoning Strong on Vals Finance Agent overall_accuracy_pct and Vals Finance Agent complex_retrieval_accuracy_pct	13.2%	28%	$0.28	Vals Finance AgentVals Finance Agent
#25	claude-opus-4-6-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals Mortgage Tax overall_accuracy_pct	12.3%	14%	—	Vals Finance AgentVals Mortgage Tax
#26	grok-4-1-fast-reasoning Strong on Vals Finance Agent overall_accuracy_pct and BFCL Multi-turn Official Multi Turn Acc	12.0%	21%	$0.28	Vals Finance AgentBFCL Multi-turn Official
#27	claude-opus-4-5-20251101-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals Mortgage Tax overall_accuracy_pct	11.5%	14%	—	Vals Finance AgentVals Mortgage Tax
#29	kimi-k2.5-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals Mortgage Tax overall_accuracy_pct	11.1%	16%	—	Vals Finance AgentVals Mortgage Tax
#30	claude-sonnet-4-5-20250929-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals Mortgage Tax overall_accuracy_pct	10.8%	14%	—	Vals Finance AgentVals Mortgage Tax
#31	claude-opus-4-1-20250805 Strong on Vals Mortgage Tax overall_accuracy_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct	10.5%	20%	—	Vals Mortgage TaxVectara HHEM Leaderboard
#34	phi-4 Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and LanguageBench overall:mean	9.7%	17%	—	Vectara HHEM LeaderboardLanguageBench
#37	grok-3 Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and SimpleQA Verified simpleqa_verified_score_pct	9.4%	14%	$6.00	Vectara HHEM LeaderboardSimpleQA Verified
#38	gemini-2.5-flash-lite Strong on Galileo Agent Leaderboard v2 Avg TSQ and Vectara HHEM Leaderboard overall_hallucination_error_pct	9.4%	13%	$0.17	Galileo Agent Leaderboard v2Vectara HHEM Leaderboard

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 Mortgage Tax

38 rows · 1.3% avg lift

Vals Legal Bench

38 rows · 0.4% avg lift

Vals Tax Eval v2

36 rows · 0.4% avg lift

Vals MedQA

35 rows · 0.4% avg lift

Missing frontier models

No obvious gaps right now.

▶Taxonomy & task details

Core tasks

task.cross_lingual_summarization

Required modes

mode.multilingualmode.long_context

Domains

domain.general_business

Related in Productivity

Knowledge base Q&A (fast, no citations)

Answer KB questions grounded in retrieved text without citations.

Knowledge base Q&A (with citations)

Answer questions grounded in an internal KB, with evidence.

Document summarization

Summarize long business documents into scannable outputs.

Decision memo

Recommend a decision with options, constraints, and risks.